Upload README.md with huggingface_hub

README.md

@@ -183,505 +183,278 @@ Explanation: <explanation>
 > ```
 
 <details>
-<summary><b>Abuse Detection (BN)</b></summary>
+<summary><b>Arabic (AR)</b></summary>
 
-**System:** `You are an expert social media image analyzer specializing in identifying abusive content in memes.`
-
-**English Instruction:** `<image> Examine the Bengali meme and decide whether it features abusive content. This includes any form of verbal abuse or personal offense. Classify as: 'abusive' or 'not-abusive'.`
-
-**Native (BN) Instruction:** `<image> এই বাংলা মেমটিতে কি কোনো ধরনের আপত্তিকর বা অবমাননাকর বিষয়বস্তু আছে? আপনার সিদ্ধান্ত অনুযায়ী মেমটিকে 'অপমানজনক' অথবা 'অপমানজনক নয়' লেবেল দিন।`
-
-**English Labels:** `abusive`, `not-abusive` | **Native Labels:** `অপমানজনক`, `অপমানজনক নয়`
-</details>
-
-<details>
-<summary><b>Deepfake Detection (RO)</b></summary>
-
-**System:** `You are an expert image analyst specializing in detecting manipulated or deepfake content in memes.`
-
-**English Instruction:** `<image> Assess the provided Romanian meme. Is the image content authentic, or has it been altered? If altered, was it done using AI (deepfake) or other methods? Based on your analysis, classify the meme as: 'DeepFake', 'Fake', or 'Real'.`
-
-**Native (RO) Instruction:** `<image> Este această memă românească autentică sau a fost manipulată? Dacă a fost manipulată, s-a folosit inteligență artificială (deepfake)? Folosește următoarele etichete pentru a clasifica: 'DeepFake' pentru conținut falsificat cu AI, 'Fake' pentru alt tip de falsificare, sau 'Real' pentru conținut original.`
-
-**English Labels:** `DeepFake`, `Fake`, `Real` | **Native Labels:** `DeepFake`, `Fals`, `Real`
-</details>
-
-<details>
-<summary><b>Emotion Recognition (RO)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in emotion recognition in memes.`
-
-**English Instruction:** `<image> Determine the emotional impact of the Romanian meme. Analyze its components to select the most accurate emotional descriptor from the options provided. Classify as: 'Joy', 'Sadness', 'Anger', 'Fear', 'Surprise', or 'Love'.`
+#### Hateful Content Detection (Prop2Hate)
+**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
+**Instruction:** `<image> Analyze the content of the Arabic meme and determine if it includes hateful language. Consider whether it displays hatred, discrimination, or bias based on identity or protected traits. Classify as: 'Hateful' if applicable, otherwise 'not-hateful'.`
+**Labels:** `Hateful`, `not-hateful`
 
-**Native (RO) Instruction:** `<image> Examinați mema românească și identificați cea mai evidentă emoție transmisă prin text și imagine. Hotărâți care stare emoțională este cea mai puternică. Clasificați ca: 'Bucurie' dacă simțiți fericire, 'Tristețe' dacă se exprimă supărare, 'Furie' dacă este prezentă mânia, 'Frică' pentru anxietate, 'Surpriză' pentru șoc, sau 'Dragoste' pentru afecțiune.`
+#### Propaganda Detection (ArMeme)
+**System:** `You are an expert social media analyst specializing in identifying propaganda techniques in memes.`
+**Instruction:** `<image> Identify if the given Arabic meme is an example of propaganda by checking for biased or misleading narratives intended to affect political or ideological perspectives. Select: 'propaganda' or 'not-propaganda' as appropriate.`
+**Labels:** `propaganda`, `not-propaganda`
 
-**English Labels:** `Joy`, `Sadness`, `Anger`, `Fear`, `Surprise`, `Love` | **Native Labels:** `Bucurie`, `Tristețe`, `Furie`, `Frică`, `Surpriză`, `Dragoste`
 </details>
 
 <details>
-<summary><b>Harmful Content Detection (EN)</b></summary>
+<summary><b>Bengali (BN)</b></summary>
 
-**System:** `You are an expert social media image analyzer specializing in identifying harmful content in memes.`
-
-**Instruction:** `<image> Categorize the meme based on a three-point scale of harmfulness. Scrutinize the image and text to make your judgment. Classify as: 'not-harmful', 'partially-harmful', or 'very-harmful'.`
+#### Abuse Detection (BanglaAbuseMeme)
+**System:** `You are an expert social media image analyzer specializing in identifying abusive content in memes.`
+**Instruction:** `<image> Examine the Bengali meme and decide whether it features abusive content. This includes any form of verbal abuse or personal offense. Classify as: 'abusive' or 'not-abusive'.`
+**Labels:** `abusive`, `not-abusive`
 
-**Labels:** `not-harmful`, `partially-harmful`, `very-harmful`
-</details>
+#### Hateful Content Detection (MUTE)
+**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
+**Instruction:** `<image> Is the provided Bengali meme hateful in nature? Review the meme for any content that expresses discrimination or prejudice. After your review, select one of the two possible classifications. Classify as: 'hateful' or 'not-hateful'.`
+**Labels:** `hateful`, `not-hateful`
 
-<details>
-<summary><b>Harmful Content Detection — COVID-19 (EN)</b></summary>
+#### Sarcasm Detection (BanglaAbuseMeme)
+**System:** `You are an expert social media image analyzer specializing in identifying abusive content in memes.`
+**Instruction:** `<image> Assess the communication style of the Bengali meme. Does it rely on sarcasm to make its point? If the meme is straightforward and means exactly what it says, it is not sarcastic. Classify the content as: 'sarcasm' or 'not-sarcasm'.`
+**Labels:** `sarcasm`, `not-sarcasm`
 
-**System:** `You are an expert social media image analyzer specializing in identifying harmful content in memes.`
+#### Sentiment Analysis (BanglaAbuseMeme)
+**System:** `You are an expert social media image analyzer specializing in identifying abusive content in memes.`
+**Instruction:** `<image> Examine the Bengali meme and identify the sentiment it conveys. Classify the emotion as: 'positive', 'negative', or 'neutral'.`
+**Labels:** `positive`, `negative`, `neutral`
 
-**Instruction:** `<image> Assess the meme's content concerning the COVID-19 crisis and decide on its classification. The categories reflect increasing levels of potential harm, from none to severe. Classify the meme as either: 'not-harmful', 'partially-harmful', or 'very-harmful'.`
+#### Vulgar Content Detection (BanglaAbuseMeme)
+**System:** `You are an expert social media image analyzer specializing in identifying abusive content in memes.`
+**Instruction:** `<image> Evaluate the Bengali meme to see if vulgarity is present. Search for crude, obscene, or improper language or images. Classify as: 'vulgar' if such content is found, otherwise use 'not-vulgar'.`
+**Labels:** `vulgar`, `not-vulgar`
 
-**Labels:** `not-harmful`, `partially-harmful`, `very-harmful`
 </details>
 
 <details>
-<summary><b>Hateful Content Detection (AR — Prop2Hate)</b></summary>
+<summary><b>Chinese (ZH)</b></summary>
 
+#### Hateful Content Detection (Multi3Hate)
 **System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
+**Instruction:** `<image> Your objective is to classify the Chinese meme based on its content. Determine if it conveys a hateful message targeting any specific group. Use one of the two provided labels: 'hateful' or 'not-hateful'.`
+**Labels:** `hateful`, `not-hateful`
 
-**English Instruction:** `<image> Analyze the content of the Arabic meme and determine if it includes hateful language. Consider whether it displays hatred, discrimination, or bias based on identity or protected traits. Classify as: 'Hateful' if applicable, otherwise 'not-hateful'.`
-
-**Native (AR) Instruction:** `<image> تتمثل مهمتك في تمييز المحتوى البغيض في الميمات العربية. هل تحتوي الميم على أي خطاب تمييزي أو عدائي؟ صنفها وفقًا لذلك: 'كراهية' إذا كانت كذلك، أو 'غير كراهية' إذا لم تكن.`
-
-**English Labels:** `Hateful`, `not-hateful` | **Native Labels:** `كراهية`, `غير كراهية`
-</details>
+#### Intention Detection (MET-Meme)
+**System:** `You are an expert social media image analyzer specializing in detecting intentions in memes.`
+**Instruction:** `<image> Please review the Chinese meme and decide on the main reason it was created. Categorize its purpose using one of the provided labels which are: 'Entertaining' for amusement, 'Expressive' for emotional expression, 'Interactive' for engagement, 'Offensive' for provocative intent, or 'Other' for unclear intentions.`
+**Labels:** `Entertaining`, `Expressive`, `Interactive`, `Offensive`, `Other`
 
-<details>
-<summary><b>Hateful Content Detection (BN — MUTE)</b></summary>
+#### Metaphor Detection (MET-Meme)
+**System:** `You are an expert social media image analyzer specializing in identifying metaphors in memes.`
+**Instruction:** `<image> Identify whether the Chinese meme exemplifies metaphorical communication by spotting elements of indirect meaning or symbolism, as opposed to stating facts directly. Classify as: 'Metaphorical' if you find figurative elements, otherwise choose 'Literal'.`
+**Labels:** `Metaphorical`, `Literal`
 
-**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
+#### Offensive Content Detection (MET-Meme)
+**System:** `You are an expert social media image analyzer specializing in identifying offensive content in memes.`
+**Instruction:** `<image> Identify the degree of offensiveness in the supplied Chinese meme. Choose one of the following precise classifications: 'not-offensive', 'slightly-offensive', 'moderately-offensive', or 'very-offensive'.`
+**Labels:** `not-offensive`, `slightly-offensive`, `moderately-offensive`, `very-offensive`
 
-**English Instruction:** `<image> Is the provided Bengali meme hateful in nature? Review the meme for any content that expresses discrimination or prejudice. After your review, select one of the two possible classifications. Classify as: 'hateful' or 'not-hateful'.`
+#### Sentiment Category (MET-Meme)
+**System:** `You are an expert social media image analyzer specializing in sentiment analysis of memes.`
+**Instruction:** `<image> Classify the provided Chinese meme based on its primary emotional content. Your selection must be one of the following: 'Happiness', 'Sorrow', 'Anger', 'Fear', 'Surprise', 'Love', or 'Hate'.`
+**Labels:** `Happiness`, `Sorrow`, `Anger`, `Fear`, `Surprise`, `Love`, `Hate`
 
-**Native (BN) Instruction:** `<image> এই বাংলা মেমটি দেখে বলুন, এতে কি কোনো ঘৃণামূলক বিষয়বস্তু আছে? যদি কোনো ব্যক্তি বা গোষ্ঠীকে আক্রমণ করা হয়ে থাকে, তাহলে এটিকে 'ঘৃণামূলক' হিসেবে চিহ্নিত করুন। যদি তা না হয়, তাহলে এটিকে 'ঘৃণামূলক নয়' হিসেবে চিহ্নিত করুন।`
+#### Sentiment Degree (MET-Meme)
+**System:** `You are an expert social media image analyzer specializing in sentiment analysis of memes.`
+**Instruction:** `<image> Please examine the Chinese meme and classify how strongly its sentiment is expressed. Use the following labels for the intensity: 'slightly' for a low degree, 'moderately' for a medium degree, and 'very' for a high degree of emotional expression.`
+**Labels:** `slightly`, `moderately`, `very`
 
-**English Labels:** `hateful`, `not-hateful` | **Native Labels:** `ঘৃণামূলক`, `ঘৃণামূলক নয়`
 </details>
 
 <details>
-<summary><b>Hateful Content Detection (DE — Multi3Hate)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
-
-**English Instruction:** `<image> Analyze the German meme for hateful content. Determine if it promotes hate, discrimination, or prejudice against protected groups. Classify as: 'hateful' if it contains hate speech, or 'not-hateful' if it does not.`
-
-**Native (DE) Instruction:** `<image> Bewerten Sie das folgende deutsche Meme. Fördert es Hass oder Vorurteile gegen eine bestimmte Gruppe? Ordnen Sie es einer der folgenden Kategorien zu: 'hasserfüllt' oder 'nicht hasserfüllt'.`
+<summary><b>English (EN)</b></summary>
 
-**English Labels:** `hateful`, `not-hateful` | **Native Labels:** `hasserfüllt`, `nicht hasserfüllt`
-</details>
+#### Harmful Content Detection (HarMeme)
+**System:** `You are an expert social media image analyzer specializing in identifying harmful content in memes.`
+**Instruction:** `<image> Categorize the meme based on a three-point scale of harmfulness. Scrutinize the image and text to make your judgment. Classify as: 'not-harmful', 'partially-harmful', or 'very-harmful'.`
+**Labels:** `not-harmful`, `partially-harmful`, `very-harmful`
 
-<details>
-<summary><b>Hateful Content Detection (EN — FHM)</b></summary>
+#### Harmful Content Detection — COVID-19 (HarMeme)
+**System:** `You are an expert social media image analyzer specializing in identifying harmful content in memes.`
+**Instruction:** `<image> Assess the meme's content concerning the COVID-19 crisis and decide on its classification. The categories reflect increasing levels of potential harm, from none to severe. Classify the meme as either: 'not-harmful', 'partially-harmful', or 'very-harmful'.`
+**Labels:** `not-harmful`, `partially-harmful`, `very-harmful`
 
+#### Hateful Content Detection (FHM)
 **System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
-
 **Instruction:** `<image> Analyze the content of the meme to see if it promotes or displays hateful views against specific individuals or groups. Look for discriminatory, prejudiced, or hate speech elements associated with protected characteristics, including race, religion, and gender. Classify as: 'hateful' if present, or 'not-hateful' if absent.`
-
 **Labels:** `hateful`, `not-hateful`
-</details>
-
-<details>
-<summary><b>Hateful Content Detection (EN — MMHS)</b></summary>
 
+#### Hateful Content Detection (MMHS)
 **System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
-
 **Instruction:** `<image> Examine the meme and determine if it contains any form of hate speech. Classify as: 'hateful' if the content is discriminatory or disparaging towards a person or group, and 'not-hateful' if it is not.`
-
 **Labels:** `hateful`, `not-hateful`
-</details>
-
-<details>
-<summary><b>Hateful Content Detection (EN — Multi3Hate)</b></summary>
 
+#### Hateful Content Detection (Multi3Hate)
 **System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
-
 **Instruction:** `<image> Analyze the provided English meme to determine if it contains any form of hate speech, prejudice, or discriminatory content. Based on your analysis, categorize the meme using one of the following labels. Classify as: 'hateful' or 'not-hateful'.`
-
 **Labels:** `hateful`, `not-hateful`
-</details>
-
-<details>
-<summary><b>Hateful Content Detection — Islamophobia (EN)</b></summary>
 
+#### Hateful Content Detection — Islamophobia (MIMIC)
 **System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
-
 **Instruction:** `<image> Please evaluate the provided meme. Your task is to determine if it communicates hateful or discriminatory messages specifically targeting Islam or its adherents. Classify as: 'hateful' or 'not-hateful'.`
-
 **Labels:** `hateful`, `not-hateful`
-</details>
-
-<details>
-<summary><b>Hateful Content Detection (ES — Multi3Hate)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
-
-**English Instruction:** `<image> Identify whether the Spanish meme displays hateful attitudes or sentiments, specifically looking for hate speech against protected groups. Classify your findings as: 'hateful' if hate speech is evident, or 'not-hateful' if it is not.`
-
-**Native (ES) Instruction:** `<image> Considerando el meme en español, ¿se puede catalogar como discurso de odio por atacar o denigrar a un colectivo? Categorízalo como: 'odioso' o 'no odioso'.`
-
-**English Labels:** `hateful`, `not-hateful` | **Native Labels:** `odioso`, `no odioso`
-</details>
-
-<details>
-<summary><b>Hateful Content Detection (HI — Multi3Hate)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
-
-**English Instruction:** `<image> Examine the content of the Hindi meme. Does it contain language or imagery that is discriminatory or incites hatred? Assign one of the following labels: 'hateful' or 'not-hateful'.`
-
-**Native (HI) Instruction:** `<image> Determine if the Hindi meme contains hateful content. Identify whether it expresses hate, discrimination, or prejudice against individuals or groups. Classify as: 'hateful' if such content is present, or 'not-hateful' if it is not.`
-
-**English Labels:** `hateful`, `not-hateful` | **Native Labels:** `घृणास्पद`, `घृणास्पद नहीं`
-</details>
-
-<details>
-<summary><b>Hateful Content Detection (ZH — Multi3Hate)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
-
-**English Instruction:** `<image> Your objective is to classify the Chinese meme based on its content. Determine if it conveys a hateful message targeting any specific group. Use one of the two provided labels: 'hateful' or 'not-hateful'.`
-
-**Native (ZH) Instruction:** `<image> Analyze the Chinese meme for hateful content. Determine if it promotes hate, discrimination, or prejudice against protected groups. Classify as: 'hateful' if it contains hate speech, or 'not-hateful' if it does not.`
-
-**English Labels:** `hateful`, `not-hateful` | **Native Labels:** `仇恨`, `非仇恨`
-</details>
-
-<details>
-<summary><b>Humor Classification (EN)</b></summary>
 
+#### Humor Classification (Memotion)
 **System:** `You are an expert social media image analyzer specializing in emotion recognition in memes.`
-
 **Instruction:** `<image> Classify the level of humor in the meme. Analyze how funny the content is based on its comedic elements. Classify as: 'not-funny' for unfunny content, 'funny' for mildly humorous, 'very-funny' for highly humorous, or 'hilarious' for extremely funny content.`
-
 **Labels:** `not-funny`, `funny`, `very-funny`, `hilarious`
-</details>
-
-<details>
-<summary><b>Intention Detection (EN)</b></summary>
 
+#### Intention Detection (MET-Meme)
 **System:** `You are an expert social media image analyzer specializing in detecting intentions in memes.`
-
 **Instruction:** `<image> Categorize the primary purpose of the meme. What was the creator's main goal in making it? Please classify the intention as: 'Entertaining', 'Expressive', 'Interactive', or 'Offensive'.`
-
 **Labels:** `Entertaining`, `Expressive`, `Interactive`, `Offensive`
-</details>
-
-<details>
-<summary><b>Intention Detection (ZH)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in detecting intentions in memes.`
-
-**English Instruction:** `<image> Please review the Chinese meme and decide on the main reason it was created. Categorize its purpose using one of the provided labels which are: 'Entertaining' for amusement, 'Expressive' for emotional expression, 'Interactive' for engagement, 'Offensive' for provocative intent, or 'Other' for unclear intentions.`
-
-**Native (ZH) Instruction:** `<image> 请对下面的中文表情包进行分类，明确判断其主要意图。参考以下分类标准：'娱乐' 指娱乐性的内容，'表达' 用于表达情绪或观点，'互动' 用于互动交流，'冒犯' 包含冒犯意识，'其他' ���图不清。分类为：'娱乐'、'表达'、'互动'、'冒犯' 或 '其他'。`
-
-**English Labels:** `Entertaining`, `Expressive`, `Interactive`, `Offensive`, `Other` | **Native Labels:** `娱乐`, `表达`, `互动`, `冒犯`, `其他`
-</details>
-
-<details>
-<summary><b>Metaphor Detection (EN)</b></summary>
 
+#### Metaphor Detection (MET-Meme)
 **System:** `You are an expert social media image analyzer specializing in identifying metaphors in memes.`
-
 **Instruction:** `<image> Determine whether the meme uses metaphorical or literal language. Analyze if the content relies on figurative language, symbolism, or indirect meaning. Classify as: 'Metaphorical' if it uses figurative language, or 'Literal' if the meaning is direct and straightforward.`
-
 **Labels:** `Metaphorical`, `Literal`
-</details>
-
-<details>
-<summary><b>Metaphor Detection (ZH)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying metaphors in memes.`
-
-**English Instruction:** `<image> Identify whether the Chinese meme exemplifies metaphorical communication by spotting elements of indirect meaning or symbolism, as opposed to stating facts directly. Classify as: 'Metaphorical' if you find figurative elements, otherwise choose 'Literal'.`
-
-**Native (ZH) Instruction:** `<image> 请根据中文表情包中的语言表达方式判断，是属于隐喻还是字面。若内容具有象征性或使用比喻手法，则分类为 '隐喻'；否则，若表达直白无修饰，则分类为 '字面'。`
-
-**English Labels:** `Metaphorical`, `Literal` | **Native Labels:** `隐喻`, `字面`
-</details>
-
-<details>
-<summary><b>Misogyny Detection (EN — MAMI)</b></summary>
 
+#### Misogyny Detection (MAMI)
 **System:** `You are an expert social media image analyzer specializing in identifying misogynistic content in memes.`
-
 **Instruction:** `<image> Scrutinize the meme to detect any indication of misogynous content, including aspects like prejudice, discrimination, objectification, or aversion towards women. Label the meme 'misogynous' when identified, or 'not-misogynous' if none are observed.`
-
 **Labels:** `misogynous`, `not-misogynous`
-</details>
-
-<details>
-<summary><b>Misogyny Detection (HI-EN — MIMIC2024)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying misogynistic content in memes.`
-
-**English Instruction:** `<image> Observe the Hindi-English meme and ascertain if there are signs of misogyny, such as actions or language indicative of objectification, discrimination, prejudice, or hostility towards women. Classify strictly as: 'misogynous' or 'not-misogynous'.`
-
-**English Labels:** `misogynous`, `not-misogynous` | **Native Labels:** `महिला विरोधी`, `महिला विरोधी नहीं`
-</details>
-
-<details>
-<summary><b>Misogyny Categories (HI-EN — MIMIC2024)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying misogynistic content in memes.`
-
-**English Instruction:** `<image> Inspect the Hindi-English meme and decide whether its misogynous nature stems from objectification, prejudice, humiliation, a combination of these, or is unspecified. Select from the labels: 'Objectification', 'Prejudice', 'Humiliation', 'Objectification, Humiliation', 'Objectification, Prejudice', 'Prejudice, Humiliation', or 'Unspecified'.`
-
-**English Labels:** `Objectification`, `Prejudice`, `Humiliation`, `Objectification, Humiliation`, `Objectification, Prejudice`, `Prejudice, Humiliation`, `Unspecified` | **Native Labels:** `वस्तुकरण`, `पूर्वाग्रह`, `अपमान`, `वस्तुकरण, अपमान`, `वस्तुकरण, पूर्वाग्रह`, `पूर्वाग्रह, अपमान`, `अनिर्दिष्ट`
-</details>
-
-<details>
-<summary><b>Motivational Detection (EN)</b></summary>
 
+#### Motivational Detection (Memotion)
 **System:** `You are an expert social media image analyzer specializing in emotion recognition in memes.`
-
 **Instruction:** `<image> Assess if the meme fits the motivational category by checking for inspirational, encouraging, or uplifting content. Classify using: 'motivational' for memes with these features, 'not-motivational' otherwise.`
-
 **Labels:** `motivational`, `not-motivational`
-</details>
-
-<details>
-<summary><b>Objectification Detection (EN)</b></summary>
 
+#### Objectification Detection (MAMI)
 **System:** `You are an expert social media image analyzer specializing in identifying objectification in memes.`
-
 **Instruction:** `<image> Evaluate the meme for signs that it depicts women as objects, prioritizes appearance over character, or undermines their autonomy. Classify as: 'objectification' when such elements are present; otherwise, use 'not-objectification'.`
-
 **Labels:** `objectification`, `not-objectification`
-</details>
-
-<details>
-<summary><b>Offensive Content Detection (EN — Memotion)</b></summary>
 
+#### Offensive Content Detection (Memotion)
 **System:** `You are an expert social media image analyzer specializing in identifying offensive content in memes.`
-
 **Instruction:** `<image> Carefully read the meme and judge how objectionable the material is. Then, classify it as: 'not-offensive', 'slightly-offensive', 'very-offensive', or 'hateful-offensive', based on the degree of offensiveness present.`
-
 **Labels:** `not-offensive`, `slightly-offensive`, `very-offensive`, `hateful-offensive`
-</details>
-
-<details>
-<summary><b>Offensive Content Detection (EN — MET-Meme)</b></summary>
 
+#### Offensive Content Detection (MET-Meme)
 **System:** `You are an expert social media image analyzer specializing in identifying offensive content in memes.`
-
 **Instruction:** `<image> Judge the degree of offensiveness present in the meme. Evaluate how inappropriate or offensive the content is, and assign one of the following labels: 'not-offensive', 'slightly-offensive', 'moderately-offensive', or 'very-offensive'.`
-
 **Labels:** `not-offensive`, `slightly-offensive`, `moderately-offensive`, `very-offensive`
-</details>
-
-<details>
-<summary><b>Offensive Content Detection (ZH — MET-Meme)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying offensive content in memes.`
-
-**English Instruction:** `<image> Identify the degree of offensiveness in the supplied Chinese meme. Choose one of the following precise classifications: 'not-offensive', 'slightly-offensive', 'moderately-offensive', or 'very-offensive'.`
-
-**Native (ZH) Instruction:** `<image> 对每个中文表情包，判断它的冒犯性级别。分类包括：'不冒犯' —— 完全无冒犯意向，'轻度冒犯' —— 轻微不当，'中度冒犯' —— 明显冒犯，'严重冒犯' —— 极度不当。请据此分辨。`
-
-**English Labels:** `not-offensive`, `slightly-offensive`, `moderately-offensive`, `very-offensive` | **Native Labels:** `不冒犯`, `轻度冒犯`, `中度冒犯`, `严重冒犯`
-</details>
-
-<details>
-<summary><b>Political Content Detection (RO)</b></summary>
-
-**System:** `You are an expert social media analyst specializing in analyzing political content in memes.`
-
-**English Instruction:** `<image> Assess whether the Romanian meme features political topics, including discussions about politicians, legislation, or political controversies. Classify the meme as either 'political' for relevant content, or 'not-political' if absent.`
-
-**Native (RO) Instruction:** `<image> Analizați dacă mema românească se referă la politică prin menționarea politicienilor, politicilor, alegerilor sau evenimentelor asociate. Clasificați ca: 'politic' în cazul unui subiect politic, sau ca: 'nepolitic' dacă nu este politică.`
-
-**English Labels:** `political`, `not-political` | **Native Labels:** `politic`, `nepolitic`
-</details>
-
-<details>
-<summary><b>Propaganda Detection (AR — ArMeme)</b></summary>
-
-**System:** `You are an expert social media analyst specializing in identifying propaganda techniques in memes.`
-
-**English Instruction:** `<image> Identify if the given Arabic meme is an example of propaganda by checking for biased or misleading narratives intended to affect political or ideological perspectives. Select: 'propaganda' or 'not-propaganda' as appropriate.`
-
-**Native (AR) Instruction:** `<image> صنف الميم التالية بناءً على وجود أو غياب العناصر الدعائية. تُعرَّف الدعاية بأنها معلومات، خاصة ذات طبيعة متحيزة أو مضللة، تستخدم للترويج لقضية سياسية. اختر بين 'دعاية' و 'ليست دعاية'.`
-
-**English Labels:** `propaganda`, `not-propaganda` | **Native Labels:** `دعاية`, `ليست دعاية`
-</details>
-
-<details>
-<summary><b>Sarcasm Detection (BN)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying abusive content in memes.`
-
-**English Instruction:** `<image> Assess the communication style of the Bengali meme. Does it rely on sarcasm to make its point? If the meme is straightforward and means exactly what it says, it is not sarcastic. Classify the content as: 'sarcasm' or 'not-sarcasm'.`
-
-**Native (BN) Instruction:** `<image> এই বাংলা মেমের বিষয়বস্তু বিশ্লেষণ করুন। যদি এটি বিদ্রূপ বা শ্লেষ ব্যবহার করে কোনো বার্তা দেয়, তবে তা ব্যঙ্গাত্মক। আপনার সিদ্ধান্ত অনুযায়ী এটিকে 'ব্যঙ্গাত্মক' বা 'ব্যঙ্গাত্মক নয়' হিসেবে চিহ্নিত করুন।`
-
-**English Labels:** `sarcasm`, `not-sarcasm` | **Native Labels:** `ব্যঙ্গাত্মক`, `ব্যঙ্গাত্মক নয়`
-</details>
-
-<details>
-<summary><b>Sarcasm Detection (EN)</b></summary>
 
+#### Sarcasm Detection (Memotion)
 **System:** `You are an expert social media image analyzer specializing in emotion recognition in memes.`
-
 **Instruction:** `<image> Your objective is to identify the type of sarcasm used in the meme. Determine if the content is straightforward or if it uses irony to convey its message. Please assign a classification based on the complexity of the sarcasm. Classify as: 'not-sarcastic', 'general-sarcasm', 'twisted-meaning', or 'very-twisted'.`
-
 **Labels:** `not-sarcastic`, `general-sarcasm`, `twisted-meaning`, `very-twisted`
-</details>
-
-<details>
-<summary><b>Sentiment Analysis (EN — Memotion)</b></summary>
 
+#### Sentiment Analysis (Memotion)
 **System:** `You are an expert social media image analyzer specializing in sentiment analysis of memes.`
-
 **Instruction:** `<image> Review the meme and determine its general emotional sentiment. Based on your analysis, assign one of the following labels: 'very-negative', 'negative', 'neutral', 'positive', or 'very-positive'.`
-
 **Labels:** `very-negative`, `negative`, `neutral`, `positive`, `very-positive`
-</details>
-
-<details>
-<summary><b>Sentiment Analysis (BN)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in identifying abusive content in memes.`
-
-**English Instruction:** `<image> Examine the Bengali meme and identify the sentiment it conveys. Classify the emotion as: 'positive', 'negative', or 'neutral'.`
-
-**Native (BN) Instruction:** `<image> নিম্নলিখিত বাংলা মেমে-র মতবোধ/আবেগ পরীক্ষা করুন এবং শ্রেণীতে ভাগ করুন। বাছাই করুন: 'ইতিবাচক' শান্তিপূর্ণ বা প্রেরণাদায়ক হলে, 'নেতিবাচক' হতাশাজনক বা অপ্রীতিকর হলে, অথবা 'নিরপেক্ষ' কোনো প্রকৃত অনুভূতি না থাকলে।`
-
-**English Labels:** `positive`, `negative`, `neutral` | **Native Labels:** `ইতিবাচক`, `নেতিবাচক`, `নিরপেক্ষ`
-</details>
-
-<details>
-<summary><b>Sentiment Analysis (RO)</b></summary>
 
+#### Sentiment Category (MET-Meme)
 **System:** `You are an expert social media image analyzer specializing in sentiment analysis of memes.`
-
-**English Instruction:** `<image> Investigate the sentiment expressed by the following Romanian meme. Select the appropriate label: 'positive' if the meme is upbeat or approving, 'negative' if it is critical or displeased, or 'neutral' if it remains impartial.`
-
-**Native (RO) Instruction:** `<image> Identifică și clasifică sentimentul din mema următoare. Specificați dacă este 'pozitiv', 'negativ' sau 'neutru'.`
-
-**English Labels:** `positive`, `negative`, `neutral` | **Native Labels:** `pozitiv`, `negativ`, `neutru`
-</details>
-
-<details>
-<summary><b>Sentiment Category (EN)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in sentiment analysis of memes.`
-
 **Instruction:** `<image> For the meme presented, decide which single emotional category it belongs to, considering its overall message and tone. The available classifications are: 'Happiness', 'Sorrow', 'Anger', 'Fear', 'Surprise', 'Love', or 'Hate'.`
-
 **Labels:** `Happiness`, `Sorrow`, `Anger`, `Fear`, `Surprise`, `Love`, `Hate`
-</details>
-
-<details>
-<summary><b>Sentiment Category (ZH)</b></summary>
 
+#### Sentiment Degree (MET-Meme)
 **System:** `You are an expert social media image analyzer specializing in sentiment analysis of memes.`
-
-**English Instruction:** `<image> Classify the provided Chinese meme based on its primary emotional content. Your selection must be one of the following: 'Happiness', 'Sorrow', 'Anger', 'Fear', 'Surprise', 'Love', or 'Hate'.`
-
-**Native (ZH) Instruction:** `<image> 请审视这个中文表情包，并为其指定一个主要的情感类别。从以下列表中选择：'快乐'，'悲伤'，'愤怒'，'恐惧'，'惊讶'，'爱'，'恨'。`
-
-**English Labels:** `Happiness`, `Sorrow`, `Anger`, `Fear`, `Surprise`, `Love`, `Hate` | **Native Labels:** `快乐`, `悲伤`, `愤怒`, `恐惧`, `惊讶`, `爱`, `恨`
-</details>
-
-<details>
-<summary><b>Sentiment Degree (EN)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in sentiment analysis of memes.`
-
 **Instruction:** `<image> Considering the overall sentiment in the meme, classify its intensity by selecting: 'slightly' for minimal emotional presence, 'moderately' for a balanced intensity, or 'very' if the sentiment is intense and vivid.`
-
 **Labels:** `slightly`, `moderately`, `very`
-</details>
-
-<details>
-<summary><b>Sentiment Degree (ZH)</b></summary>
-
-**System:** `You are an expert social media image analyzer specializing in sentiment analysis of memes.`
-
-**English Instruction:** `<image> Please examine the Chinese meme and classify how strongly its sentiment is expressed. Use the following labels for the intensity: 'slightly' for a low degree, 'moderately' for a medium degree, and 'very' for a high degree of emotional expression.`
-
-**Native (ZH) Instruction:** `<image> 判断中文表情包所传达情感的强度。请根据实际情感力度，将其归为：'轻微'、'中等' 或 '非常'。`
-
-**English Labels:** `slightly`, `moderately`, `very` | **Native Labels:** `轻微`, `中等`, `非常`
-</details>
-
-<details>
-<summary><b>Shaming Detection (EN)</b></summary>
 
+#### Shaming Detection (MAMI)
 **System:** `You are an expert social media image analyzer specializing in identifying shaming content in memes.`
-
 **Instruction:** `<image> Classify whether the meme contains shaming content directed at women. Determine if it aims to humiliate, embarrass, or shame women about their appearance, behavior, or choices. Classify as: 'shaming' if such content is present, or 'not-shaming' if it is not.`
-
 **Labels:** `shaming`, `not-shaming`
-</details>
-
-<details>
-<summary><b>Stereotype Detection (EN)</b></summary>
 
+#### Stereotype Detection (MAMI)
 **System:** `You are an expert social media image analyzer specializing in identifying stereotypes in memes.`
-
 **Instruction:** `<image> Review the meme and determine if it contains stereotypical content about women—look for generalized, simplified, or biased messages. Classify as: 'stereotype' if you find such traits, otherwise 'not-stereotype'.`
-
 **Labels:** `stereotype`, `not-stereotype`
-</details>
-
-<details>
-<summary><b>Target Identification (EN)</b></summary>
 
+#### Target Identification (HarMeme)
 **System:** `You are an expert social media image analyzer specializing in identifying harmful content in memes.`
-
 **Instruction:** `<image> For the provided meme, interpret who or what is being singled out. Is the commentary aimed at one person, a community, an organization, all of society, or no target? Make your classification using: 'individual', 'community', 'organization', 'society', or 'none'.`
+**Labels:** `individual`, `community`, `organization`, `society`, `none`
 
+#### Target Identification — COVID-19 (HarMeme)
+**System:** `You are an expert social media image analyzer specializing in identifying harmful content in memes.`
+**Instruction:** `<image> Review the COVID-19 meme and determine the entity that is depicted as the target within the content. Assign one of the following categories: 'individual', 'community', 'organization', 'society', or 'none'.`
 **Labels:** `individual`, `community`, `organization`, `society`, `none`
+
+#### Violence Detection (MAMI)
+**System:** `You are an expert social media image analyzer specializing in identifying violent content in memes.`
+**Instruction:** `<image> Is there content in this meme that shows, glorifies, or promotes physical, sexual, or psychological violence toward women? Please make a determination. Classify as: 'violence' if yes, and 'not-violence' if no.`
+**Labels:** `violence`, `not-violence`
+
 </details>
 
 <details>
-<summary><b>Target Identification — COVID-19 (EN)</b></summary>
+<summary><b>German (DE)</b></summary>
 
-**System:** `You are an expert social media image analyzer specializing in identifying harmful content in memes.`
-
-**Instruction:** `<image> Review the COVID-19 meme and determine the entity that is depicted as the target within the content. Assign one of the following categories: 'individual', 'community', 'organization', 'society', or 'none'.`
+#### Hateful Content Detection (Multi3Hate)
+**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
+**Instruction:** `<image> Analyze the German meme for hateful content. Determine if it promotes hate, discrimination, or prejudice against protected groups. Classify as: 'hateful' if it contains hate speech, or 'not-hateful' if it does not.`
+**Labels:** `hateful`, `not-hateful`
 
-**Labels:** `individual`, `community`, `organization`, `society`, `none`
 </details>
 
 <details>
-<summary><b>Toxicity Detection (RU)</b></summary>
+<summary><b>Hindi / Hindi-English (HI / HI-EN)</b></summary>
 
-**System:** `You are an expert social media image analyzer specializing in identifying toxic content in memes.`
+#### Hateful Content Detection (Multi3Hate)
+**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
+**Instruction:** `<image> Examine the content of the Hindi meme. Does it contain language or imagery that is discriminatory or incites hatred? Assign one of the following labels: 'hateful' or 'not-hateful'.`
+**Labels:** `hateful`, `not-hateful`
 
-**English Instruction:** `<image> Evaluate the Russian meme for the presence of toxicity. This involves identifying any language or imagery that is damaging, disrespectful, or offensive to individuals or groups. Based on your assessment, classify as: 'toxic' or 'not-toxic'.`
+#### Misogyny Detection (MIMIC2024)
+**System:** `You are an expert social media image analyzer specializing in identifying misogynistic content in memes.`
+**Instruction:** `<image> Observe the Hindi-English meme and ascertain if there are signs of misogyny, such as actions or language indicative of objectification, discrimination, prejudice, or hostility towards women. Classify strictly as: 'misogynous' or 'not-misogynous'.`
+**Labels:** `misogynous`, `not-misogynous`
 
-**Native (RU) Instruction:** `<image> Оцените мем на русском языке и выясните, присутствует ли токсичность. Если выражения или визуальные элементы мема унижают, обижают или причиняют вред людям или группам, классифицируйте как: 'токсичный'. Если таких признаков нет, используйте метку: 'нетоксичный'.`
+#### Misogyny Categories (MIMIC2024)
+**System:** `You are an expert social media image analyzer specializing in identifying misogynistic content in memes.`
+**Instruction:** `<image> Inspect the Hindi-English meme and decide whether its misogynous nature stems from objectification, prejudice, humiliation, a combination of these, or is unspecified. Select from the labels: 'Objectification', 'Prejudice', 'Humiliation', 'Objectification, Humiliation', 'Objectification, Prejudice', 'Prejudice, Humiliation', or 'Unspecified'.`
+**Labels:** `Objectification`, `Prejudice`, `Humiliation`, `Objectification, Humiliation`, `Objectification, Prejudice`, `Prejudice, Humiliation`, `Unspecified`
 
-**English Labels:** `toxic`, `not-toxic` | **Native Labels:** `токсичный`, `нетоксичный`
 </details>
 
 <details>
-<summary><b>Violence Detection (EN)</b></summary>
+<summary><b>Romanian (RO)</b></summary>
 
-**System:** `You are an expert social media image analyzer specializing in identifying violent content in memes.`
+#### Deepfake Detection (RoMemes)
+**System:** `You are an expert image analyst specializing in detecting manipulated or deepfake content in memes.`
+**Instruction:** `<image> Assess the provided Romanian meme. Is the image content authentic, or has it been altered? If altered, was it done using AI (deepfake) or other methods? Based on your analysis, classify the meme as: 'DeepFake', 'Fake', or 'Real'.`
+**Labels:** `DeepFake`, `Fake`, `Real`
 
-**Instruction:** `<image> Is there content in this meme that shows, glorifies, or promotes physical, sexual, or psychological violence toward women? Please make a determination. Classify as: 'violence' if yes, and 'not-violence' if no.`
+#### Emotion Recognition (RoMemes)
+**System:** `You are an expert social media image analyzer specializing in emotion recognition in memes.`
+**Instruction:** `<image> Determine the emotional impact of the Romanian meme. Analyze its components to select the most accurate emotional descriptor from the options provided. Classify as: 'Joy', 'Sadness', 'Anger', 'Fear', 'Surprise', or 'Love'.`
+**Labels:** `Joy`, `Sadness`, `Anger`, `Fear`, `Surprise`, `Love`
+
+#### Political Content Detection (RoMemes)
+**System:** `You are an expert social media analyst specializing in analyzing political content in memes.`
+**Instruction:** `<image> Assess whether the Romanian meme features political topics, including discussions about politicians, legislation, or political controversies. Classify the meme as either 'political' for relevant content, or 'not-political' if absent.`
+**Labels:** `political`, `not-political`
+
+#### Sentiment Analysis (RoMemes)
+**System:** `You are an expert social media image analyzer specializing in sentiment analysis of memes.`
+**Instruction:** `<image> Investigate the sentiment expressed by the following Romanian meme. Select the appropriate label: 'positive' if the meme is upbeat or approving, 'negative' if it is critical or displeased, or 'neutral' if it remains impartial.`
+**Labels:** `positive`, `negative`, `neutral`
 
-**Labels:** `violence`, `not-violence`
 </details>
 
 <details>
-<summary><b>Vulgar Content Detection (BN)</b></summary>
+<summary><b>Russian (RU)</b></summary>
 
-**System:** `You are an expert social media image analyzer specializing in identifying abusive content in memes.`
+#### Toxicity Detection (Toxic Memes)
+**System:** `You are an expert social media image analyzer specializing in identifying toxic content in memes.`
+**Instruction:** `<image> Evaluate the Russian meme for the presence of toxicity. This involves identifying any language or imagery that is damaging, disrespectful, or offensive to individuals or groups. Based on your assessment, classify as: 'toxic' or 'not-toxic'.`
+**Labels:** `toxic`, `not-toxic`
 
-**English Instruction:** `<image> Evaluate the Bengali meme to see if vulgarity is present. Search for crude, obscene, or improper language or images. Classify as: 'vulgar' if such content is found, otherwise use 'not-vulgar'.`
+</details>
 
-**Native (BN) Instruction:** `<image> এই বাংলা মেমে কোনো অশ্লীল ভাষা বা ছবি আছে কিনা তা পরীক্ষা করুন শ্রেণীবিন���যাস করুন। মেমটি 'অশ্লীল' নাকি 'অশ্লীল নয়' তা বলুন।`
+<details>
+<summary><b>Spanish (ES)</b></summary>
+
+#### Hateful Content Detection (Multi3Hate)
+**System:** `You are an expert social media image analyzer specializing in identifying hateful content in memes.`
+**Instruction:** `<image> Identify whether the Spanish meme displays hateful attitudes or sentiments, specifically looking for hate speech against protected groups. Classify your findings as: 'hateful' if hate speech is evident, or 'not-hateful' if it is not.`
+**Labels:** `hateful`, `not-hateful`
 
-**English Labels:** `vulgar`, `not-vulgar` | **Native Labels:** `অশ্লীল`, `অশ্লীল নয়`
 </details>
 
 ## Citation