Skip to main content

Question Answering

M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework
·2696 words·13 mins
AI Generated 🤗 Daily Papers Natural Language Processing Question Answering 🏢 Singapore University of Technology and Design
M-LongDoc: a new benchmark and retrieval-aware tuning framework revolutionizes multimodal long document understanding, improving model accuracy by 4.6%.
HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems
·2200 words·11 mins
AI Generated 🤗 Daily Papers Natural Language Processing Question Answering 🏢 Renmin University of China
HtmlRAG boosts RAG system accuracy by using HTML, not plain text, to model retrieved knowledge, improving knowledge representation and mitigating LLM hallucination.
GRS-QA -- Graph Reasoning-Structured Question Answering Dataset
·5467 words·26 mins
AI Generated 🤗 Daily Papers Natural Language Processing Question Answering 🏢 University of California Santa Cruz
GRS-QA: New benchmark dataset reveals LLM reasoning limitations!