mteb_v2_eval_prompts.json

{
  "AILAStatutes": "Identifying the most relevant statutes for a given situation",
  "AfriSentiClassification": "Given a text, categorized by sentiment into positive, negative, or neutral",
  "AlloProfClusteringS2S.v2": "Identify the topic of document titles from Allo Prof dataset",
  "AlloprofReranking": "Given a question, retrieve passages that answer the question",
  "AmazonCounterfactualClassification": "Given an Amazon review, judge whether it is counterfactual.",
  "ArXivHierarchicalClusteringP2P": "Identify the main and secondary category of Arxiv papers based on the titles and abstracts",
  "ArXivHierarchicalClusteringS2S": "Identify the main and secondary category of Arxiv papers based on the titles",
  "ArguAna": "Given a claim, find documents that refute the claim",
  "ArmenianParaphrasePC": "Retrieve semantically similar text",
  "BUCC.v2": "Retrieve parallel sentences",
  "BelebeleRetrieval": "Retrieval the relevant passage for the given query",
  "BibleNLPBitextMining": "Retrieve parallel sentences",
  "BigPatentClustering.v2": "Identify the category of documents from the Big Patent dataset",
  "BiorxivClusteringP2P.v2": "Identify the main category of Biorxiv papers based on the titles and abstracts",
  "BornholmBitextMining": "Retrieve parallel sentences",
  "BrazilianToxicTweetsClassification": "Classify the toxic tweets in Brazilian Portuguese into one of the six categories: LGBTQ+phobia, Xenophobia, Obscene, Insult, Misogyny and Racism.",
  "BulgarianStoreReviewSentimentClassfication": "Classify user reviews into positive, negative or mixed sentiment",
  "CEDRClassification": "Given a comment as query, classify expressed emotions into joy, sadness, surprise, fear, and anger",
  "CLSClusteringP2P.v2": "Identify the main category of scholar papers based on the titles and abstracts",
  "CSFDSKMovieReviewSentimentClassification": "Given a movie review, classify its rating on a scale from 0 to 5",
  "CTKFactsNLI": "Retrieve semantically similar text",
  "CataloniaTweetClassification": "Given a tweet, classify its sentiment into AGAINST, FAVOR or NEUTRAL towards Catalonia's independence.",
  "Core17InstructionRetrieval": "Retrieve relevant passages for the given query with conditions",
  "CovidRetrieval": "Given a question on COVID-19, retrieve news articles that answer the question",
  "CyrillicTurkicLangClassification": "Given a text, classify its language",
  "CzechProductReviewSentimentClassification": "Classify product reviews into positive, neutral, or negative sentiment",
  "DBpediaClassification": "Given the following text, retrieve the appropriate DBpedia category including Company, EducationalInstitution, Artist, Athlete, OfficeHolder, MeanOfTransportation, Building, NaturalPlace, Village, Animal, Plant, Album, Film, WrittenWork.",
  "DalajClassification": "Classify texts based on linguistic acceptability in Swedish",
  "DiaBlaBitextMining": "Retrieve parallel sentences",
  "EstonianValenceClassification": "Given a news article, categorized by sentiment into negatiivne, positiivne, neutraalne or vastuolulin",
  "FaroeseSTS": "Retrieve semantically similar text",
  "FilipinoShopeeReviewsClassification": "Given a shop review, classify its rating on a scale from 1 to 5",
  "FinParaSTS": "Retrieve semantically similar text",
  "FinancialPhrasebankClassification": "Given financial news, categorized by sentiment into positive, negative, or neutral",
  "FloresBitextMining": "Retrieve parallel sentences",
  "GermanSTSBenchmark": "Retrieve semantically similar text",
  "GreekLegalCodeClassification": "Given a greek legal text, classify its topic",
  "GujaratiNewsClassification": "Given a Gujarati news articles, classify ist topic",
  "HALClusteringS2S.v2": "Identify the topic of titles from HAL",
  "HagridRetrieval": "Given a question, retrieve relevant responses",
  "IN22GenBitextMining": "Retrieve parallel sentences",
  "IndicCrosslingualSTS": "Retrieve semantically similar text",
  "IndicGenBenchFloresBitextMining": "Retrieve parallel sentences",
  "IndicLangClassification": "Given a text, classify its language",
  "IndonesianIdClickbaitClassification": "Given an Indonesian news headlines, classify its into clickbait or non-clickbait",
  "IsiZuluNewsClassification": "Given a news article, classify its topic",
  "ItaCaseholdClassification": "Given a judgments, classify its topic",
  "JSICK": "Retrieve semantically similar text",
  "KorHateSpeechMLClassification": "Given a Korean online news comments, classify its fine-grained hate speech classes",
  "KorSarcasmClassification": "Given a twitter, categorized it into sarcasm or not_sarcasm",
  "KurdishSentimentClassification": "Given a text, categorized by sentiment into positive or negative",
  "LEMBPasskeyRetrieval": "Retrieval the relevant passage for the given query",
  "LegalBenchCorporateLobbying": "Given a query, retrieve relevant legal bill summaries",
  "MIRACLRetrievalHardNegatives": "Retrieve Wikipedia passages that answer the question",
  "MLQARetrieval": "Retrieval the relevant passage for the given query",
  "MacedonianTweetSentimentClassification": "Given a Macedonian tweet, categorized by sentiment into positive, negative, or neutral",
  "MalteseNewsClassification": "Given a maltese new, classify its topic",
  "MasakhaNEWSClassification": "Classify the News in the given texts into one of the seven category: politics,sports,health,business,entertainment,technology,religion ",
  "MasakhaNEWSClusteringS2S": "Identify the topic or theme of the given news articles based on the titles",
  "MassiveIntentClassification": "Given a user utterance as query, find the user intents",
  "MedrxivClusteringP2P.v2": "Identify the main category of Medrxiv papers based on the titles and abstracts",
  "MultiEURLEXMultilabelClassification": "Given a text, classify its topic",
  "MultiHateClassification": "Given a text, categorized by sentiment into hate or non-hate",
  "NTREXBitextMining": "Retrieve parallel sentences",
  "NepaliNewsClassification": "Given a news article, categorized it into business, entertainment or sports",
  "News21InstructionRetrieval": "Retrieve relevant passages for the given query with conditions",
  "NollySentiBitextMining": "Retrieve parallel sentences",
  "NordicLangClassification": "Given a text in a Nordic language, classify the language into one of the following categories: Danish, Swedish, Norwegian (Nynorsk), Norwegian (Bokmål), Faroese, Icelandic.",
  "NorwegianCourtsBitextMining": "Retrieve parallel sentences",
  "NusaParagraphEmotionClassification": "Classify the emotion into one of the following categories: fear, sadness, anger, happy, love, surprise, shame.",
  "NusaTranslationBitextMining": "Retrieve parallel sentences",
  "NusaX-senti": "Given a text, categorized by sentiment into positive or negative",
  "NusaXBitextMining": "Retrieve parallel sentences",
  "OdiaNewsClassification": "Given a news article, categorized it into business, entertainment or sports",
  "OpusparcusPC": "Retrieve semantically similar text",
  "PAC": "Classify Polish contract clauses into one of the following two types: \"Safe Contract Clauses\" and \"Unfair Contract Clauses\".",
  "PawsXPairClassification": "Retrieve semantically similar text",
  "PlscClusteringP2P.v2": "Identify the category of titles+abstracts from Library of Science",
  "PoemSentimentClassification": "Given the following verse from a poem, classify its sentiment as negative, neutral, positive, or mixed.",
  "PolEmo2.0-OUT": "Classify the sentiment of products and school online reviews",
  "PpcPC": "Retrieve semantically similar text",
  "PunjabiNewsClassification": "Given a news article, categorized it into two-classes",
  "RTE3": "Retrieve semantically similar text",
  "Robust04InstructionRetrieval": "Retrieve relevant passages for the given query with conditions",
  "RomaniBibleClustering": "Identify verses from the Bible in Kalderash Romani by book.",
  "RuBQReranking": "Given a question, retrieve Wikipedia passages that answer the question",
  "SCIDOCS": "Given a scientific paper title, retrieve paper abstracts that are cited by the given paper",
  "SIB200ClusteringS2S": "Identify the category of documents",
  "SICK-R": "Retrieve semantically similar text",
  "STS12": "Retrieve semantically related sentences",
  "STS13": "Retrieve semantically similar text",
  "STS14": "Retrieve semantically similar text",
  "STS15": "Retrieve semantically similar text",
  "STS17": "Retrieve semantically similar text",
  "STS22.v2": "Given a document, retrieve semantically related documents",
  "STSB": "Retrieve semantically similar text",
  "STSBenchmark": "Retrieve semantically similar text",
  "STSES": "Given a Spanish sentence, retrieve semantically related Spanish sentences",
  "ScalaClassification": "Classify passages into correct or correct in Scandinavian Languages based on linguistic acceptability",
  "SemRel24STS": "Retrieve semantically similar text",
  "SentimentAnalysisHindi": "Given a hindi text, categorized by sentiment into positive, negative or neutral",
  "SinhalaNewsClassification": "Given a news article, categorized it into political, business, technology, sports and Entertainment",
  "SiswatiNewsClassification": "Identify fine-grained news categories in Siswati language.",
  "SlovakMovieReviewSentimentClassification": "Given a movie review, categorized it into positive or negative",
  "SpartQA": "Given the following spatial reasoning question, retrieve the right answer.",
  "SprintDuplicateQuestions": "Find questions that have the same meaning as the input question",
  "StackExchangeClustering.v2": "Identify the topic or theme of StackExchange posts based on the titles",
  "StackOverflowQA": "Given a question about coding, retrieval code or passage that can solve user's question",
  "StatcanDialogueDatasetRetrieval": "Retrieval the relevant passage for the given query",
  "SwahiliNewsClassification": "Given a news article, classify its domain",
  "SwednClusteringP2P": "Identify news categories in Swedish passages",
  "SwissJudgementClassification": "Given a news article, categorized it into approval or dismissal",
  "T2Reranking": "Given a Chinese search query, retrieve web passages that answer the question",
  "TERRa": "Given a premise, retrieve a hypothesis that is entailed by the premise",
  "TRECCOVID": "Given a medical query, retrieve documents that answer the query",
  "Tatoeba": "Retrieve parallel sentences",
  "TempReasonL1": "Given the following question about time, retrieve the correct answer.",
  "ToxicConversationsClassification": "Classify the given comments as either toxic or not toxic",
  "TswanaNewsClassification": "Given a news article, classify its topic",
  "TweetTopicSingleClassification": "Gvien a twitter, classify its topic",
  "TwitterHjerneRetrieval": "Retrieve answers to questions asked in Danish tweets",
  "TwitterURLCorpus": "Find tweets that have the same meaning as the input tweet",
  "VoyageMMarcoReranking": "Given a Japanese search query, retrieve web passages that answer the question",
  "WebLINXCandidatesReranking": "Retrieval the relevant passage for the given query",
  "WikiCitiesClustering": "Identify of Wikipedia articles of cities by country",
  "WikiClusteringP2P.v2": "Identify the category of wiki passages",
  "WikipediaRerankingMultilingual": "Retrieval the relevant passage for the given query",
  "WikipediaRetrievalMultilingual": "Retrieval the relevant passage for the given query",
  "WinoGrande": "Given the following sentence, retrieve an appropriate answer to fill in the missing underscored part.",
  "XNLI": "Retrieve semantically similar text",
  "indonli": "Retrieve semantically similar text"
}