From Table to Cell: Attention for Better Reasoning with TABALIGN

Excerpt

arXiv:2605.14465v2 Announce Type: replace Abstract: 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. We conduct a pilot study showing that diffusion language models (DLMs) produce more human-aligned and permutation-stabl