Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
arXiv preprint arXiv:2505.12415 (2025)
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Tables present unique challenges for language models due to their structured row-column interactions, necessitating specialized approaches for effective comprehension. While large language models (LLMs) have demonstrated potential in table reasoning through prompting and techniques like chain-of-thought (CoT) and program-of-thought (PoT), optimizing their performance for table question answering remains underexplored. In this paper, we introduce region-based Table-R1, a novel reinforcement learning approach that enhances LLM table understanding by integrating region evidence into reasoning steps. Our method employs Region-Enhanced Supervised Fine-Tuning (RE-SFT) to guide models in identifying relevant table regions before generating answers, incorporating textual, symbolic, and program-based reasoning. Additionally, Table-Aware Group Relative Policy Optimization (TARPO) introduces a mixed reward system to dynamically balance region accuracy and answer correctness, with decaying region rewards and consistency penalties to align reasoning steps. Experiments show that Table-R1 achieves an average performance improvement of 14.36 points across multiple base models on three benchmark datasets, even outperforming baseline models with ten times the parameters, while TARPO reduces response token consumption by 67.5% compared to GRPO, significantly advancing LLM capabilities in efficient tabular reasoning.
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
LLMs exhibit data referencing errors across model sizes; a critic model detects them at 78.2% F1 and boosts accuracy up to 12% via filtering and rejection sampling.
V-tableR1 uses a critic VLM for dense step-level feedback and a new PGPO algorithm to shift multimodal table reasoning from pattern matching to verifiable logical steps, achieving SOTA accuracy with a 4B open-source model.
SpreadsheetAgent uses incremental multi-format reading, structural sketching, and verification to raise spreadsheet benchmark accuracy from 35.27% to 38.16%.
BV-Blend blends prompt-local and semantic-cluster historical reward statistics via SEM-derived weights to stabilize critic-free RL advantage estimation.
citing papers explorer
-
Multi-Objective Exploration and Preference Optimization via Mutual Information
Maximizing joint conditional mutual information I(Y; C_Z, W, Z | X) decomposes multi-objective LLM alignment into preference-specific DPO terms plus an I(Y;W|X) exploration term that reduces reward-distribution overlap.
-
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
LLMs exhibit data referencing errors across model sizes; a critic model detects them at 78.2% F1 and boosts accuracy up to 12% via filtering and rejection sampling.
-
V-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization
V-tableR1 uses a critic VLM for dense step-level feedback and a new PGPO algorithm to shift multimodal table reasoning from pattern matching to verifiable logical steps, achieving SOTA accuracy with a 4B open-source model.
-
Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning
SpreadsheetAgent uses incremental multi-format reading, structural sketching, and verification to raise spreadsheet benchmark accuracy from 35.27% to 38.16%.
-
BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards
BV-Blend blends prompt-local and semantic-cluster historical reward statistics via SEM-derived weights to stabilize critic-free RL advantage estimation.