Question Answering

Also known as QA

Overview

Question answering asks how systems can find, interpret, and combine information to answer questions, from short factual queries to multi-hop reasoning over documents, conversations, images, video, and structured data. Common approaches include retrieval-augmented generation, fine-tuning, knowledge graphs, tool-using agents, and symbolic methods; evaluations span reading comprehension, open-domain and long-document QA, conversational QA, and specialized domains. Current work also focuses on multilingual and multimodal settings, personalization, and recognizing when to clarify or abstain rather than guess. A central tension is that better retrieval or reasoning does not always produce more reliable answers: systems must still handle missing or conflicting evidence, avoid hallucinations, and balance accuracy, coverage, latency, and cost.

Latest papers

CardsList

272 papers17 papers in the last four weeks, down 43% on the four weeks before. 0.1% of all new papers.

  1. Towards Reliable Long-Context Reasoning: Detecting Unanswerable Questions via FactGuard

    Apr 8, 2025Qian-Wen Zhang, Biao Liu, Fang Li +5LLM ReliabilityQuestion Answering

  2. QDA-SQL: Questions Enhanced Dialogue Augmentation for Multi-Turn Text-to-SQL

    Jun 15, 2024Yinggang Sun, Ziming Guo, Haining Yu +5Synthetic Data GenerationQuestion Answering