text string | source string |
|---|---|
significant increase in CD8[+] T cells’ ability to produce IFN-g. (True/False)False Biology & Earth Science... provided in Table S3. Upon analysing the dye- ing performance depicted in Fig. 3A, it be comes clear that both the wool fibers with and without mordant exhibited comparable chlorophyll uptakes, with the unmord... | https://arxiv.org/abs/2505.16566v1 |
at a lower cost than Tesla can. While EVs are not a perfect solution, and Tesla is not a perfect ...How do firms engage in sustainable entrepreneur- ship by working with others?Collaborative innovation What actions are essential to enhance sustainabil- ity? (Select all that apply)a) Co-creating policies, c) Engaging in... | https://arxiv.org/abs/2505.16566v1 |
URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training Dongyang Fan Vinko Sabolˇ cec Martin Jaggi EPFL, Switzerland firstname.lastname@epfl.ch Abstract Large Language Models (LLMs) are commonly pretrained on vast corpora of text without utilizing contextual metadata such as source, quality, or topic, l... | https://arxiv.org/abs/2505.16570v1 |
investigate whether context-aware pretraining can be utilized for more controllable generation than context-free pretraining. In response to the previously raised questions, our findings and contributions can be summarized as follows: •We conduct a comprehensive study on context-conditioned LLM pretraining, high- light... | https://arxiv.org/abs/2505.16570v1 |
/a.altnd c/a.altrbon dioxide, producing oxygen /a.alts /a.alt product /a.alts /a.alt byproduct for other org/a.altnisms. J/a.altv/a.altScript is /a.alt vers/a.alttile l/a.altngu/a.altge used for web development, especi/a.altlly inter/a.altctive user interf/a.altces online.…Figure 1: An example of our context-aware toke... | https://arxiv.org/abs/2505.16570v1 |
we modify the generation in the logit ( Π) level, that is xt∼ΠLLM(x|x1:t−1,∅) +γ ΠLLM(x|x1:t−1, ctx)−ΠLLM(x|x1:t−1,∅) (1) When γ=0, this coincides with context-free generation and when γ=1, this coin- cides with context-conditioned generation. With γ>1, we amplify the guidance of the context. It is worth noting that ... | https://arxiv.org/abs/2505.16570v1 |
topic and format do- mains derived from WebOrganizer [ 24], where topic and format domains are returned by pretrained classifiers. There are 24 categories per taxonomy. In total, we have 576 different Domain Information types. 3. Combinations of Metadata •Full URL + Quality Score : Combines the document’s source with i... | https://arxiv.org/abs/2505.16570v1 |
Conflicting signals of different metadata types. Interestingly, the benefits of URL con- ditioning are negated when additional metadata is introduced as context. For example, combining quality scores with URL conditioning appears to introduce conflicting signals, leading to downstream performance that is even lower tha... | https://arxiv.org/abs/2505.16570v1 |
the inference time. The contexts we used are presented in Table 10 in the Appendix. Conditioning on provided contexts, we observed increased downstream performance, especially in URL- and DI-conditioned pretrained models. Table 3: Enhanced downstream task performance with context-conditioned generation compared to cont... | https://arxiv.org/abs/2505.16570v1 |
the successful guidance of the context. Table 4: Average LLM-as-a-judge evaluation scores (mean ±std) on the different prompt completions on 50 prompts on health & medical and history topics respectively (answer length: 64 tokens). Model type denotes the type of checkpoints used, with "conditioned" being our context-co... | https://arxiv.org/abs/2505.16570v1 |
Continuations are generated from our pretrained DI-conditioned check- points. (Caution of Hallucination!) Steering factor ( γ)Given prompt : Julius Caesar was assassinated because -2 he’d killed too many people and he’d become too dangerous. He was assassinated by senators and officials who were on the wrong side of th... | https://arxiv.org/abs/2505.16570v1 |
Hallucination!) Given prompt : Paris is known for https: //medicalxpress. com/150 years of medical excellence, thanks to the collaboration of doctors, nurses, medical students and researchers. It is also known as the home of major medical discoveries such as the operation of the heart, the discovery of insulin, the dis... | https://arxiv.org/abs/2505.16570v1 |
for Computational Linguistics. doi: 10.18653/v1/2021.acl-long.522. URL https://aclanthology.org/2021.acl-long.522/ . [8]Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori Hashimoto, Luke Zettlemoyer, and Mike Lewis. Contrastive decoding: Open-ended text generation as optimization. In Anna R... | https://arxiv.org/abs/2505.16570v1 |
Wan, Shruti Bhosale, Shun Zhang, Simon Vandenhende, Soumya Batra, Spencer Whitman, Sten Sootla, Stephane Collot, Suchin Gururangan, Sydney Borodinsky, Tamar Herman, Tara Fowler, Tarek Sheasha, Thomas Georgiou, Thomas Scialom, Tobias Speckbacher, Todor Mihaylov, Tong Xiao, Ujjwal Karn, Vedanuj Goswami, Vibhor Gupta, Vig... | https://arxiv.org/abs/2505.16570v1 |
Singhal, Nick Egebo, Nicolas Usunier, Nikhil Mehta, Nikolay Pavlovich Laptev, Ning Dong, Norman Cheng, Oleg Chernoguz, Olivia Hart, Omkar Salpekar, Ozlem Kalinli, Parkin Kent, Parth Parekh, Paul Saab, Pavan Balaji, Pedro Rittner, Philip Bontrager, Pierre Roux, Piotr Dollar, Polina Zvyagina, Prashant Ratanchandani, Prit... | https://arxiv.org/abs/2505.16570v1 |
physical commonsense in natural language. In Proceedings of the AAAI conference on artificial intelligence , volume 34, pages 7432–7439, 2020. [20] Maarten Sap, Hannah Rashkin, Derek Chen, Ronan LeBras, and Yejin Choi. Socialiqa: Commonsense reasoning about social interactions. arXiv preprint arXiv:1904.09728 , 2019. [... | https://arxiv.org/abs/2505.16570v1 |
ble 9.Given the exact same prompt, the continuation can be steered in markedly different directions depending on the contextual guidance. Topic-based guidance is highly visible, while format-based guidance is more subtle. For example, when steering with "News Article", the output tends to include concrete details about... | https://arxiv.org/abs/2505.16570v1 |
at the many other fairs through- out the year. In music, the term "chanson" is often used, especially in the 18th century, to refer to a genre of music that was particularly C.3 LLM Judge We use gpt-4o from OpenAI API to evaluate continuations given a prompt. The prompt used for scoring medical & health domain continua... | https://arxiv.org/abs/2505.16570v1 |
EMULATE: A Multi-Agent Framework for Determining the Veracity of Atomic Claims by Emulating Human Actions Spencer Hong, Meng Luo, Xinyi Wan National University of Singapore Abstract Determining the veracity of atomic claims is an imperative component of many recently proposed fact-checking systems. Many ap- proaches ta... | https://arxiv.org/abs/2505.16576v1 |
the fact verifica- tion process by trying to understand why additional evidence is needed at each step, which enables the system to ignore redundant and irrelevant search results and generate high-quality queries that can better enhance the system’s evidence set. To evaluate the efficacy of our framework, we perform ex... | https://arxiv.org/abs/2505.16576v1 |
the response to the initial search query. In scenario (d), the human would need to formulate additional search queries to fill in the gaps. To the best of our 2 Figure 2: Results on the entire GPT-4.1 model family. The strongest/weakest model according to OpenAI is GPT-4.1/GPT-4.1-nano. Dataset #True #False Total FacTo... | https://arxiv.org/abs/2505.16576v1 |
661 checkworthy claims human-annotated with either True,False , orUnknown . We ignore the Unknown examples and sample 631 claims for our experi- ments. See Table 1 for full dataset statistics. To quantify performance, we report the preci- sion, recall, and F1 scores for each class. We also provide the macro-F1 score, w... | https://arxiv.org/abs/2505.16576v1 |
label-wise F1 scores, the macro-F1 score, and the weighted- F1 score , which confirms the effectiveness of our novel design. We also observe that FIRE always achieves the second best results, which is likely attributed to its iterative retrieval mechanism. To gain a better understanding of the impact that different age... | https://arxiv.org/abs/2505.16576v1 |
Long, and Wenya Wang. 2024. Decomposition dilemmas: Does claim decompo- sition boost or burden fact-checking performance? arXiv preprint arXiv:2411.02400 . Kyungha Kim, Sangyun Lee, Kung-Hsiang Huang, Hou Pong Chan, Manling Li, and Heng Ji. 2024. Can llms produce faithful explanations for fact-checking? towards faithfu... | https://arxiv.org/abs/2505.16576v1 |
arXiv:2505.16582v2 [cs.CL] 26 May 2025O2-Searcher: A Searching-based Agent Model for Open-Domain Open-Ended Question Answering Jianbiao Mei1,2,∗Tao Hu3,2,∗Daocheng Fu2,4,∗Licheng Wen2Xuemeng Yang2 Rong Wu1,2Pinlong Cai2Xinyu Cai2Xing Gao2Yu Yang1 Chengjun Xie3Botian Shi2,†Yong Liu1,5,†Yu Qiao2 1Zhejiang University2Shan... | https://arxiv.org/abs/2505.16582v2 |
understand, and apply knowledge. Recently, several works [ 27,69,17] have begun exploring training LLMs with the search engine to achieve adaptive interaction with the external knowledge for open-domain tasks. However, these efforts primarily focus on evaluating model performance in so-called closed-ended or determinis... | https://arxiv.org/abs/2505.16582v2 |
corresponding knowledge, potentially engaging in knowledge-aware multi-round interac- tions to generate the final answer. Let q0be the initial input query, K0represent an initial internal knowledge state, and Ebe the search environment. In each round t, O2-Searcher autonomously evaluates its current knowledge state Kta... | https://arxiv.org/abs/2505.16582v2 |
steps. Rather than directly incorporating raw contents into knowledge state Kt+1, we introduce a condensation 1https://serper.dev 2https://www.meilisearch.com 3 System : SYSTEM_PROMPT User : Initial query: when did Ford stop producing the 7.3 diesel? Assistant : <think> To determine when Ford stopped producing the 7.3 ... | https://arxiv.org/abs/2505.16582v2 |
include up to five distinct queries, each delimited by <query> tags. Subsequently, the retrieved data is presented within <learnings> tags. Ultimately, once the model deems the gathered information sufficient, it delivers its answer within <answer> tags. Cold start. Drawing inspiration from DeepSeek-R1 [ 9], we first a... | https://arxiv.org/abs/2505.16582v2 |
requirement of adhering to the basic format where answers are en- closed within <answer> tags, we also expect the model to generate answers featuring diverse findings presented in Markdown list format. Consequently, answers with incorrect item formatting will be penalized. Moreover, to promote diversity among the items... | https://arxiv.org/abs/2505.16582v2 |
(1−Sa) (9) p=|M′|/ntot,pred , r =|M′|/ntot,gt, r o,f1= 2·p·r/(p+r) (10) where ϕis the embedding model, xiandyiare the items extracted from the generated answer and the ground-truth answer. ntot,pred andntot,gt stand for the total number of items in the generated set and the ground-truth set, respectively. Ultimately, f... | https://arxiv.org/abs/2505.16582v2 |
for closed-ended question-answering tasks and compare our O2-Searcher against three categories of methods: (1) CoT-based approaches, including CoT [ 51], RAG [ 24], IRCoT [ 44], and Search-o1 [ 27]. These methods leverage Chain-of-Thought reasoning either for direct inference or in combination with Retrieval-Augmented ... | https://arxiv.org/abs/2505.16582v2 |
0.292 0.072 0.293 0.271 Search-R1-base 0.480 0.433 0.638 0.457 0.382 0.196 0.432 0.431 Search-R1-instruct 0.393 0.370 0.610 0.397 0.414 0.146 0.368 0.385 Qwen2.5-3B Direct Inference 0.106 0.149 0.288 0.108 0.244 0.020 0.024 0.134 CoT 0.023 0.021 0.032 0.005 0.021 0.002 0.000 0.015 IRCoT 0.111 0.164 0.312 0.200 0.171 0.... | https://arxiv.org/abs/2505.16582v2 |
5, we depict the evolution of response length, reward value, and valid search results across different training steps during our unified training process, which includes both open-ended and closed-ended questions. The response length undergoes a rapid expansion in the early training stage (before step 50), followed by ... | https://arxiv.org/abs/2505.16582v2 |
the empirical validation being conducted solely on a 3B-parameter model, leaving scalability unevaluated. Dependence on external search also exposes models to noise and misinformation (further limitations are detailed in Appendix A.4). As the first work exploring LLM evaluation and training on open-ended questions, thi... | https://arxiv.org/abs/2505.16582v2 |
system card. arXiv preprint arXiv:2410.21276 , 2024. 10 [15] Weisen Jiang, Han Shi, Longhui Yu, Zhengying Liu, Yu Zhang, Zhenguo Li, and James T Kwok. Forward-backward reasoning in large language models for mathematical verification. arXiv preprint arXiv:2308.07758 , 2023. [16] Carlos E Jimenez, John Yang, Alexander We... | https://arxiv.org/abs/2505.16582v2 |
al. Large language model agent: A survey on methodology, applications and challenges. arXiv preprint arXiv:2503.21460 , 2025. [32] Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. When not to trust language models: Investigating effectiveness of parametric and non-parametri... | https://arxiv.org/abs/2505.16582v2 |
Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in neural information processing systems , 33:5776–5788, 2020. [50] Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chow... | https://arxiv.org/abs/2505.16582v2 |
, 37:121156–121184, 2024. [64] Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Yongliang Shen, Ren Kan, Dongsheng Li, and De- qing Yang. Easytool: Enhancing llm-based agents with concise tool instruction. arXiv preprint arXiv:2401.06201 , 2024. [65] Zhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui, Rolf Jagerman, Hansi Z... | https://arxiv.org/abs/2505.16582v2 |
prompt- engineered, SFT-based, and RL-based methods. Prompt-engineered methods [ 51,50,70,58,15,69] design prompts to provide exemplars or guidance that steer models along specific cognitive pathways, thereby improving problem-solving skills without modifying the underlying parameters. However, these methods do not alt... | https://arxiv.org/abs/2505.16582v2 |
0.75. A.3 More Analysis Analysis of Reward Design. Our analysis investigates the impact of different reward components in the open-ended task, with results presented in Table 3. All variants are trained for 300 steps in the RL training stage. These findings indicate that the choice of reward components significantly af... | https://arxiv.org/abs/2505.16582v2 |
illustrative cases for the closed-end problem, generated by Search-R1 and O2-Searcher, respectively. Fig. 7 presents the limitations of Search-R1, including repetitive searching and ineffective information distillation. In contrast, Fig. 8 demonstrates the efficient search and answering capabilities of O2-Searcher. We ... | https://arxiv.org/abs/2505.16582v2 |
to the modelname). During the late 1980s, the Caterpillar and Detroit Diesel engines are replaced by 6.6L and 7.8L inline-6 diesels produced in a joint venture between Ford and New Holland in Brazil. In 1992, the Ford-New Holland engines are both replaced by a Cummins 5.9L inline-6 diesel. Ford F-Series (seventh genera... | https://arxiv.org/abs/2505.16582v2 |
in Ford Super Duty trucks until the 2007 model year but lasted until 2009 in the Ford Econoline vans (model year 2010) and in the Ford Excursion SUVs until after-Doc 3(Title: "Ford Super Duty") was sold with the 7.3L Power Stroke V8. Initially producing 235 hp/500 lb-ft of torque, the engine was retuned in 2001. Versio... | https://arxiv.org/abs/2505.16582v2 |
User ( Env_feedback ): Search learnings: <learnings> Children learn about the world through play before school and transition to a more focused learning process at school. They have difficulty concentrating, so lessons are typically 40 - 45 minutes long, and learn ing activities should engage multiple senses… </learnin... | https://arxiv.org/abs/2505.16582v2 |
are of significant importance for ensuring content accuracy. 18 A.5 Prompt Details For the prompt-engineered LLM agent, we also apply the multi-round conversation format to generate the final key findings for open-ended problems. The system prompt is presented as follows: System prompt for LLM agents ### Task Descripti... | https://arxiv.org/abs/2505.16582v2 |
actionable key findings based on the user’s require- ments. </think> <answer> [ "Key finding 1: Green energy policies have led to a 15% increase in employment across renewable energy sectors in 2023.", "Key finding 2: Solar panel efficiency improved by 22% due to innovations in perovskite-based designs in recent years.... | https://arxiv.org/abs/2505.16582v2 |
output within the <answer> and </answer> tags. To compress the raw web content, we use the following prompt template: Prompt template for compressing raw web content You are an expert researcher. Follow these instructions when responding: - You may be asked to research subjects that is after your knowledge cutoff, assu... | https://arxiv.org/abs/2505.16582v2 |
to any of the target findings - If a similar entry is found, pair them together - Each input finding can only be paired with one target finding - Each target finding can only be paired with one input finding 3. Output Requirements: You need to output a list in JSON format, where each element is a pair: [ ["input findin... | https://arxiv.org/abs/2505.16582v2 |
subject matter. - Mistakes erode my trust, so be accurate and thorough. - Provide detailed explanations, I’m comfortable with lots of detail. - Value good arguments over authorities, the source is irrelevant. - Consider new technologies and contrarian ideas, not just the conventional wisdom. - You may use high levels o... | https://arxiv.org/abs/2505.16582v2 |
a detailed and coherent content based on the key points and webpage content. The outline is structured as a dictionary, where the keys represent section titles, and the corresponding values are lists of subsection titles. If a main section does not contain any subsections, ensure the content is thorough and comprehensi... | https://arxiv.org/abs/2505.16582v2 |
the formation of a deep economic union. - The current state of globalization and regional integration in Southeast Asia is not conducive to the creation of a deep economic union. - The deep economic union model of the EU does not fully reflect the unique characteristics and needs of Southeast Asian countries. Outlines ... | https://arxiv.org/abs/2505.16582v2 |
and GDP per capita data... #### Political and Geopolitical Challenges - **Territorial Disputes**: The South China Sea is a major source of tension among Southeast Asian countries and between them and China.. - **External Influences**: The region is caught in the geopolitical rivalry between the United States and China.... | https://arxiv.org/abs/2505.16582v2 |
Preprint. Under review. Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering Bowen Jiang2∗, Runchuan Zhu2∗, Jiang Wu1∗†, Zinco Jiang2, Yifan He2, Junyuan Gao3,Jia Yu1,Rui Min1,Yinfan Wang4,Haote Yang1, Songyang Zhang1,Dahua Lin1,Lijun Wu1,Conghui He1‡ 1Shanghai Artificial ... | https://arxiv.org/abs/2505.16591v1 |
languages, whether the benchmark includes language-specific knowledge, and whether it is easy to evaluate. To tackle this problem, we introduce Knowledge- Oriented Language- Specific Simple Question Answering (KoLasSimpleQA), a benchmark comprising simple fact-based QA samples grounded in genuinely language-specific kn... | https://arxiv.org/abs/2505.16591v1 |
their contents. Unlike con- ventional methods focusing only on entry content, we specifically extracted inter-language link information for each entry and counted the number of these links, denoted as nill. An inter-language link is a hyperlink that connects a Wikipedia page in one language to the related page in anoth... | https://arxiv.org/abs/2505.16591v1 |
would be (Lombardy, capital is, Milan), and the corresponding QA pair would be “What is the capital city of the Lombardy region?” Additionally, we extract the reversed triples (E2, R’, E1) and construct QA pairs that explicitly capture inverse relations. This approach allows us to assess whether the model has genuinely... | https://arxiv.org/abs/2505.16591v1 |
"Kon Tum" Q : "In which city is Đăk RơWacommune located? A: "Kon Tum " Q : "ใครเป็นผู้ก่อตั ้งพรรคเพื่อไทรวมพลัง ?" A: "จิตรวรรณ หวังศุภกิจโกศล " Q : "Who is the founder of the Pheu Thai Ruam Palang Party?" A: "Jittrawan Wangsuppakitkosol Q : "Где је смјештен Манастир Ограђеница? " A: "Брајићи (Будва) " Q : "Where is t... | https://arxiv.org/abs/2505.16591v1 |
Q: "Which city is considered the capital of Florida ?" A: "Tallahassee "reversezh huLanguage -specific Q: "久大精盐公司的创 立者是谁？ " A: "范旭东" Q: " Who is the founder of Jiuda Salt Company?" A: "Fan Xudong" Q : " "Melyik zenekar készítette az Oblatio című akusztikus nagylemezt? " A: "Pokolgép" Q : " Which band made the acoustic ... | https://arxiv.org/abs/2505.16591v1 |
those attempted. F-score : A harmonic mean of CO and CGA, balancing correctness and successful attempts. 4 Results & Analysis 4.1 Overall Results and Domain Disparity The overall performance (F-score) of all LLMs on KolasSimpleQA is shown in Tables 3 and 4, with additional metrics in Appendix D. LLMs perform significan... | https://arxiv.org/abs/2505.16591v1 |
R1 92.20 31.28 87.83 17.46 92.39 14.16 93.58 24.20 91.30 30.81 Table 4: Model performance (F-score) (part2/2). “avg.” denotes the average result across all the 9 languages. Red indicates the best, followed by green and then blue. (a) (b)(c) Figure 5: (a) Model performance (F-score) ranking in general and langugage-spec... | https://arxiv.org/abs/2505.16591v1 |
five LRMs rank within the top six for mECE values. This suggests that through thorough reasoning and reflection during inference, LRMs achieve better calibration performance than traditional LLMs. 4.4 Knowledge Memorization Robustness Studies Allen-Zhu & Li (2023); Berglund et al. (2023) have shown that auto-regressive... | https://arxiv.org/abs/2505.16591v1 |
of each thought (see Table 26), with examples in Figures 12 and 13. The number of correct thoughts in a response is denoted as nct. A response with at least one correct thought is labeled Rnct≥1. We applied the above process to responses in both the general and language-specific domains of KoLaSimpleQA. The LRM’s respo... | https://arxiv.org/abs/2505.16591v1 |
Madian Khabsa. The belebele benchmark: a parallel reading comprehension dataset in 122 language variants. arXiv preprint arXiv:2308.16884 , 2023. Lukas Berglund, Meg Tong, Max Kaufmann, Mikita Balesni, Asa Cooper Stickland, Tomasz Korbak, and Owain Evans. The reversal curse: Llms trained on” a is b” fail to learn” b is... | https://arxiv.org/abs/2505.16591v1 |
Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, et al. Gpt-4o system card. arXiv preprint arXiv:2410.21276 , 2024. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Al... | https://arxiv.org/abs/2505.16591v1 |
Ritter, and Wei Xu. Having beer after prayer? measuring cultural bias in large language models. arXiv preprint arXiv:2305.14456 , 2023. Edoardo Maria Ponti, Goran Glava ˇs, Olga Majewska, Qianchu Liu, Ivan Vuli ´c, and Anna Korhonen. XCOPA: A multilingual dataset for causal commonsense reasoning. In Bonnie Webber, Trev... | https://arxiv.org/abs/2505.16591v1 |
Cheng-Yu Lai. Motivations of wikipedia content contributors. Computers in human behavior , 26(6):1377–1383, 2010. Jifan Yu, Xiaozhi Wang, Shangqing Tu, Shulin Cao, Daniel Zhang-Li, Xin Lv, Hao Peng, Zijun Yao, Xiaohan Zhang, Hanming Li, et al. Kola: Carefully benchmarking world knowledge of large language models. arXiv... | https://arxiv.org/abs/2505.16591v1 |
human expert revision/inspection” approach (Liu et al. (2023); Putri et al. (2024)), which is a recent trend. However, the problems in the aforementioned evaluation sets are typically complex: first, they include both factual inquiries and reasoning abilities; second, they usually involve queries about multiple facts o... | https://arxiv.org/abs/2505.16591v1 |
triples between the two entities cannot be extracted based on the text, output []. 4. The language of relations and entities of the extracted triples are consistent with the language of the provided text. 5. For Entity A and Entity B, it is necessary to extract the relationship triples between Entity A and Entity B and... | https://arxiv.org/abs/2505.16591v1 |
have to recall the information about He Xiaozhong . He is a screenwriter from Taiwan and has participated in the creation of quite a few TV dramas. The Taiwan Television's 8 PM slot usually refers to the serial dramas broadcast during the prime time of Taiwan Television. There are many such dramas, such as Unforgettabl... | https://arxiv.org/abs/2505.16591v1 |
Women in the Mother’s Family and The Daughters‘ Rise in the Mother’s Family. 不过，不确定何晓钟是否参与过这些剧集的编剧工作。 另外，可能需要查证何晓钟的编剧 作品。不过由于我目前无法实时搜索，只能依靠已有的知识库。记得何晓钟可能参与过 《含苞》这部剧？或者 《家的脚印 》？或者《娘家》系列？ However, I'm not sure if He Xiaozhong has ever participated in the screenwriting work of these TV dramas. In addition, it may be neces... | https://arxiv.org/abs/2505.16591v1 |
8. Language: The questions are in <language> . Here is an example: [Input materials]: Li Sing Primary School Li Sing Primary School (English: Li Sing Primary School) is a government primary school located in Sai Ying Pun, Hong Kong. It was founded in 1954. In May 1953, Li Baochun announced that he would invest 250,000 ... | https://arxiv.org/abs/2505.16591v1 |
the tail entity). For instance, for the triple ["China", "contains", "Beijing"] , the question ”Which province does China contain?” is invalid, as it has multiple possible answers. Similarly, avoid vague questions like ”What is one of the representative pieces of the Mei’an Qin School?” 9. The language used in the ques... | https://arxiv.org/abs/2505.16591v1 |
because: - They fully contain the important information in the gold target. - They do not contain any information that contradicts the gold target. - Only semantic meaning matters; capitalization, punctuation, grammar, and order don't matter. - Hedging and guessing are permissible, provided that the gold target is full... | https://arxiv.org/abs/2505.16591v1 |
question "What episode did Derek and Meredith get legally married in Grey 's Anatomy?" with gold target "Season 7, Episode 20: White Wedding". Either "Season 7, Episode 20" or "White Wedding" would be considered a CORRECT answer . - Do not punish predicted answers if they omit information that would be clearly inferred... | https://arxiv.org/abs/2505.16591v1 |
87.60 31.52 Qwen2.5-Instruct-7B 57.48 11.58 38.41 5.95 44.50 7.07 34.57 5.98 59.50 17.39 QwQ-32B 87.40 22.11 76.16 19.05 77.03 12.12 79.01 11.97 83.47 26.09 QwQ-32B-Preview 77.17 14.74 70.86 13.10 66.51 9.09 73.46 6.84 77.69 16.30 QwQ-Plus 49.61 12.63 46.36 15.48 37.80 8.08 48.15 7.69 47.93 14.13 Deepseek V3 94.49 33.6... | https://arxiv.org/abs/2505.16591v1 |
50.00 42.01 56.69 36.96 29.82 52.63 54.43 42.28 45.25 Deepseek V3 0.00 3.33 0.00 7.87 1.09 7.02 0.00 1.27 0.17 5.89 Deepseek R1 1.41 1.11 0.59 1.57 0.00 1.75 0.75 1.27 0.41 2.00 Table 18: Model performance (NA) on KoLasSimpleQA (part2/2). zh ko th ar vi general specific general specific general specific general specifi... | https://arxiv.org/abs/2505.16591v1 |
(CGA) on KoLasSimpleQA (part1/2). cs hu ru sr avg. general specific general specific general specific general specific general specific GPT-4o-2024-11-20 92.20 42.86 88.17 32.00 86.81 27.91 93.94 46.27 90.53 41.89 GPT-4o-mini 83.80 31.82 71.43 10.74 68.48 12.73 78.63 26.92 74.59 24.07 o1-mini 86.76 32.73 74.39 16.13 82... | https://arxiv.org/abs/2505.16591v1 |
include the detected language type. [Output]: { "language": "<detected_language>", "shift_expression":[list] } Table 24: Prompt template for splitting the LRM’s reasoning process into thoughts on KoLasSimpleQA (step 1/2) 28 Preprint. Under review. Shift Expression Confirming Prompt Given the thinking process, identify ... | https://arxiv.org/abs/2505.16591v1 |
What Media Frames Reveal About Stance: A Dataset and Study about Memes in Climate Change Discourse Shijia Zhou⛰* Siyao Peng⛰* Simon Luebke/commen◎s Jörg Haßler/commen◎sMario Haim/commen◎sSaif M. Mohammad/canadian-maple-leafBarbara Plank⛰ ⛰MaiNLP & MCML, LMU Munich, Germany /commen◎sDepartment of Media and Communication... | https://arxiv.org/abs/2505.16592v2 |
media, such as Twitter/X (Ross and Rivers, 2019). For example, Figure 1a conveys a convinced stance towards CC by using REAL and IMPACT frames (further detailed in §3.2) to affirm the evidence of global warming and its dishearten- ing consequences. Conversely, Figure 1b conveys askeptical stance using the HOAX frame, c... | https://arxiv.org/abs/2505.16592v2 |
text componants (Hwang and Shwartz, 2023; Chen et al., 2024). Explanation tasks go a step further by generating textual jus- tifications for the labels assigned to memes (Hee et al., 2023). In this study, we curate CLIMATE - MEMES and introduce two meme understanding tasks: stance detection and media frame detection. W... | https://arxiv.org/abs/2505.16592v2 |
1.3 / 6.6 1.83 IMPA ,REAL ,ADEQ meme 50 80.0 / 16.0 / 4.0 1.96 ADEQ ,IMPA ,REAL ConservativeMemes 45 22.2 / 68.9 / 8.9 2.02 HOAX ,PROP ,REAL Total 1,184 78.0 / 17.2 / 4.8 2.11 ADEQ ,IMPA ,HOAX Table 1: The number of memes (#m) in the top 6 fre- quent subreddits, along with percentages of convinced , skeptical , and nei... | https://arxiv.org/abs/2505.16592v2 |
responsibility of certain groups, such as na- tions, organizations, or even generations, to take action on climate change than others; •PROPRIETY reflects debates on whether cur- rent actions are appropriate or effective; •ADEQUACY highlights critiques regarding whether existing measures are sufficient to ad- dress cli... | https://arxiv.org/abs/2505.16592v2 |
frames being HOAX ,PROPRIETY , and CAUSE . These frames reflect skepticism toward the truthfulness of the CC communications, the effectiveness of current actions, and the denial of human activity as the primary cause. In contrast, 82.3% ofr/dankmemes memes exhibit a convinced stance, with REAL being a common frame, hig... | https://arxiv.org/abs/2505.16592v2 |
in skeptical memes, framing is more diverse for convinced ones. 5 Stance and Media Frame Detection To what degree can VLMs detect stance and frames in a meme, and how can we improve their perfor- mance? This section reports various experiments we performed on C LIMATE MEMES . 5.1 Experimental Setups Models. We evaluate... | https://arxiv.org/abs/2505.16592v2 |
51.90 37.09 61.71 54.79 syn 58.23 36.06 59.03 53.01 syn+ocr 59.66 42.71 61.78 55.20 hum 79.32 60.54 64.61 58.31 hum+ocr 67.65 48.96 65.09 58.78 Qwenocr 49.16 34.06 64.02 55.45 syn 68.91 44.66 60.33 53.98 syn+ocr 61.34 39.08 60.88 54.24 hum 73.11 53.28 65.86 58.23 hum+ocr 70.17 51.66 64.98 57.51 Table 2: Performance in ... | https://arxiv.org/abs/2505.16592v2 |
all 8 frames. HOAX achieves the highest score and PRO- PRIETY scores the lowest. For LLMs, Qwen out- performs Mistral with overall performance, but is not consistently the best model for all frames. 5.4 Can frame labels help stance detection? Table 4 investigates whether adding gold frame labels helps stance detection ... | https://arxiv.org/abs/2505.16592v2 |
responsibility labels. memes with humor types exaggeration andperson- ification . Memes with irony andpuns are difficult, receiving the lowest accuracy and F1. Memes with ordinary andcelebrity under personalization cate- gories show strong performance, but NGO stands out as challenging. For responsibility, memes con- c... | https://arxiv.org/abs/2505.16592v2 |
of only a single annotator. Despite lim- ited resources, we carefully refined our annotation guidelines through six iterations, totaling about 540 hours of annotation work. Monthly Frequency: Sample Size May Be Too Small in Some Months to Derive Conclusions About Temporal Trends The monthly frequency of memes in our da... | https://arxiv.org/abs/2505.16592v2 |
public events. International Journal of Communication , 16:23. Yuyan Chen, Songzhou Yan, Zhihong Zhu, Zhixu Li, and Yanghua Xiao. 2024. XMecap: Meme caption generation with sub-image adaptability. In ACM Multimedia 2024 . Joe PL Davidson and Luke Kemp. 2024. Climate catas- trophe: The value of envisioning the worst-cas... | https://arxiv.org/abs/2505.16592v2 |
Vancouver, Canada. Association for Computational Linguistics. Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. The Hateful Memes Chal- lenge: Detecting Hate Speech in Multimodal Memes. InAdvances in Neural Information Processing Sys- tems, volume ... | https://arxiv.org/abs/2505.16592v2 |
Positive Impact , pages 8–18, Online. Association for Compu- tational Linguistics. Viriya Taecharungroj and Pitchanut Nueangjamnong. 2015. Humour 2.0: Styles and types of humour and virality of memes on facebook. Journal of Creative Communications , 10(3):288–302. Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber- Genzel... | https://arxiv.org/abs/2505.16592v2 |
back around here so all people are welcome. The moderators believe in free speech and try not to moderate comments or posts unless it is absolutely necessary. Memes_Of_The_Dank 15 This is a meme subreddit. That should be obvious by now. Also, it is slowly recovering from bots, and that’s good. libertarianmeme 14 For an... | https://arxiv.org/abs/2505.16592v2 |
SimpsonsMemes 1 Memes from The Simpsons! MemePiece 1 The best place to find One Piece memes! We celebrate the comedic and casual side of the series One Piece. Casual or low effort content, normally removed from r/OnePiece, is likely welcome! CrusadeMemes 1 DEUS VULT MemeReserve 1 The Doomsday Global Meme Vault is a fai... | https://arxiv.org/abs/2505.16592v2 |
this task, you will be given CC memes and will be asked the following question: which media frames are used in these CC memes? Choose one or multiple that apply. •REAL emphasizes that there are evidences in- dicating that CC is occurring; •HOAX questions the faithfulness of public communication by politicians, the medi... | https://arxiv.org/abs/2505.16592v2 |
by predicts “negative” for all frames. The reported metrics are averaged over all 235 cases. Figure 8: Correlation heatmap of frames. The values represent pairwise Pearson correlation coefficients. Val- ues marked with * indicate corresponding p-values less than 0.05, indicating significance. This baseline, predicting ... | https://arxiv.org/abs/2505.16592v2 |
state, mem- bers of government, official state delegates to the COP, ministers, representatives of institu- tions such as the UN or EU. •NGO members or environmental activists. Members of protest movements such as Fri- days for Future are considered environ-mentalactivists, whereas “normal” participants in demonstratio... | https://arxiv.org/abs/2505.16592v2 |
31.68 34.73 37.93 meme+hum 59.66 41.76 43.43 51.90 meme+hum+ocr 53.78 37.00 41.04 48.83 meme+syn 53.78 37.45 39.43 46.01 meme+syn+ocr 56.72 39.45 41.55 48.08 2meme 45.38 26.90 31.27 32.56 meme+ocr 52.52 31.22 34.30 36.36 meme+hum 68.49 47.99 46.59 55.31 meme+hum+ocr 66.39 43.66 44.16 52.27 meme+syn 57.38 35.00 36.62 38... | https://arxiv.org/abs/2505.16592v2 |
52.88 53.88 meme+syn+ocr 57.13 48.74 52.03 53.51 3meme 53.44 46.15 49.55 53.47 meme+ocr 48.86 42.50 45.73 53.41 meme+hum 51.91 45.14 47.76 55.38 meme+hum+ocr 53.56 46.75 50.18 55.09 meme+syn 55.62 47.85 51.38 54.45 meme+syn+ocr 55.53 47.74 51.29 54.54 4meme 51.87 45.63 50.22 53.83 meme+ocr 46.36 40.72 43.54 53.40 meme+... | https://arxiv.org/abs/2505.16592v2 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.