Get Started
Research questionHow can table question answering choose between local and full-table context for each question?As tables grow, irrelevant content can distract models on lookup and local questions, while broader questions may require evidence from across the table. The central difficulty is deciding how much table context each question needs.
AI
Natural Language Processing
Reasoning
Latest papersRecent research connected to this question, newest first.TabScope: Question-Adaptive Scope Selection for Table Question AnsweringThe setting concerns LLM-based question answering over long tables. Evidence includes results on WikiTQ and the SLQA long-table benchmark, with silver reference sub-tables used to assess evidence selection.research paper · Sep 3, 2026
Related questions
How can long-video agents choose evidence-acquisition strategies for focused, broad-coverage, or contrastive questions?How can long-term conversational QA agents retrieve and reason over temporally dispersed dialogue history?How can biomedical question answering retrieve the right evidence and produce accurate answers?How can long-form RAG answer multi-hop questions across changing temporal, spatial, and relational contexts?
Home
Topics
Search
Library