Transfert des infos de ArchRAG vers Taches dans biblio

biblio/ArchiRAG.csv

@@ -7,16 +7,16 @@ Natural Questions, TriviaQA, WebQuestions, CuratedTREC, SQuAD v1.1","Extraction"
 Retriever seulement
 Bi-encodeur 
 Apprentissage supervisé"
-PaperQA2,https://github.com/Future-House/paper-qa,https://arxiv.org/pdf/2409.13740,2024,Agent,"Summarization, Contradiction detection, QA",LitQA2 (bench aussi publié dans le même papier),Full Pipeline,"Coût de calcul énorme, Adaptation non garantie"
-HM-RAG,https://github.com/ocean-luna/HMRAG,https://dl.acm.org/doi/10.1145/3746027.3754761,2025,Agent,"ScienceQA, CrisisMMD","ScienceQA, CrisisMMD",Full Pipeline,Multimodal
+PaperQA2,https://github.com/Future-House/paper-qa,https://arxiv.org/pdf/2409.13740,2024,Agent,"Summarization, Contradiction detection, QA","LitQA2 (bench aussi publié dans le même papier), WikiCrow (outil de génération de pseudo document Wikipedia)",Full Pipeline,"Coût de calcul énorme, Adaptation non garantie"
+HM-RAG,https://github.com/ocean-luna/HMRAG,https://dl.acm.org/doi/10.1145/3746027.3754761,2025,Agent,"","ScienceQA, CrisisMMD",Full Pipeline,Multimodal
 "[Lewis et al., 2020]","https://github.com/huggingface/transformers/blob/master/examples/rag/
  https://huggingface.co/rag/","[Lewis et al., 2020]
 https://arxiv.org/abs/2005.11401",2020,Dense,"Open-domain QA, Jeopardy Question Generation","Natural Question, TriviaQA, WebQuestions, CuratedTrec, MSMARCO NLG task v2.1, SearchQA, FEVER","Full-Pipeline
 DPR+BART","mémoire paramétrique (BART) et non-paramétrique (RAG) en mm temps
 Rédaction orientée très ingénierie
 Finetuning supervisé "
-Contriever,https://github.com/facebookresearch/contriever,https://arxiv.org/abs/2112.09118,2022,Dense,,"Data: Wikipedia, CCNet (50/50)
+Contriever,https://github.com/facebookresearch/contriever,https://arxiv.org/abs/2112.09118,2022,Dense,"QA, taĉhes de BEIR (comment ont-elles été adaptées à la partie retrieval?)","Data: Wikipedia, CCNet (50/50)
 Bench (0-shot learn) : BEIR",Retriever + entrainement par contrastive Learning,"Démonstration de l'entrainement de dense retrieval par constrastive learning (auto-supervisé)
 2022..."
-Atlas,https://github.com/facebookresearch/atlas,https://dl.acm.org/doi/epdf/10.5555/3648699.3648950,2023,Dense,"Knowledge  Intensive tasks (QA, fact checking,...)","Natural Questions, MMLU, KILT, TriviaQA, FEVER, TempLAMA (extraits)",FullPipeline,Few-shot learning with RAG
+Atlas,https://github.com/facebookresearch/atlas,https://dl.acm.org/doi/epdf/10.5555/3648699.3648950,2023,Dense,"fact checking, question answering, dialog generation, entity linking and slot-filling","KILT : - question answering: Natural Questions , TriviaQA, HotpotQA - slot filling: Zero Shot RE, T-REx - entity linking: AIDA CoNLL-YAGO - dialogue: Wizard of Wikipedia - fact checking: FEVER  + MMLU + versions originales de Natural Questions, TriviaQA, FEVER + adaptation de TempLAMA",FullPipeline,Few-shot learning with RAG
 Search in the Chain (SearChain),https://github.com/xsc1234/Search-in-the-Chain,https://arxiv.org/abs/2304.14732,2024,framework,"Knowledge intensive tasks (QA,  slot filling, fact checking, long-form QA)","HotpotQA, Musique, WikiMultiHopQA, StrategyQA, zsRE, T-REx, FEVER, ELI5,... ",Framework d'interaction entre Retriever et Generator,"Multiples allez-retours entre IR et LLM pour construire une chaine de raisonnement (suite de sous taches déterminées par le LLM) qui est vérifiée, documentée et réorientée par le IR. Cela nourri le LLM (et retour au début de la boucle)."
\ No newline at end of file

biblio/Taches.csv

+Intitulé,Benchs,Datasets,Archis/ Framework,Publis,Descriptions
+Open Domain Question Answering,,,DPR,"[Lewis et al., 2020]"
+Question Answering,KILT,"Natural Question, TriviaQA, HotpotQA","PaperQA, SearChain",,Trouver les extraits attendus contenant la réponse
+"Multi-hop question answering",,"HotpotQA, Musique, WikiMultiHopQA, StartegyQA",SearChain,"terme issu de [Xu et al., 2024] - SearChain", 
+Summarization,,,PaperQA
+Détection de contradiction,,,PaperQA
+Jeopardy Question Generation,,,,"[Lewis et al.,2020]"
+Fact Checking,KILT,FEVER,"ATLAS, SearChain"
+Slot Filling,KILT,"Zero shot RE (zsRE), T-REx","ATLAS, SearChain"
+Long-form QA,,ELI5,SearChain
+Entity Linking,KILT,AIDA CoNLL-YAGO,ATLAS
+Dialogue,KILT,Wizards of wikipedia,ATLAS
\ No newline at end of file