AI RESEARCH
From Table to Cell: Attention for Better Reasoning with TABALIGN
arXiv CS.AI
•
ArXi:2605.14465v1 Announce Type: new Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constrain the planner to a left-to-right factorization at odds with table permutation invariance, and score intermediate states by generated content alone, overlooking cell grounding.