Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning

• URL: http://arxiv.org/abs/2506.01710v1
• Date: Mon, 02 Jun 2025 14:18:09 GMT
• Title: Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
• Authors: Fangyu Lei, Jinxiang Meng, Yiming Huang, Tinghong Chen, Yun Zhang, Shizhu He, Jun Zhao, Kang Liu,
• Abstract summary: Reasoning-Table is the first application of reinforcement learning (RL) to table reasoning, achieving state-of-the-art performance.<n> Reasoning-Table emerges as a robust table reasoning large language model, surpassing larger proprietary models like Claude-3.7-Sonnet by 4.0%.
• Score: 24.624844234355734
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective inference. Supervised fine-tuning (SFT) approaches have achieved notable success but often struggle with generalization and robustness due to biases inherent in imitative learning. We introduce Reasoning-Table, the first application of reinforcement learning (RL) to table reasoning, achieving state-of-the-art performance. Through rigorous data preprocessing, reward design, and tailored training strategies, our method leverages simple rule-based outcome rewards to outperform SFT across multiple benchmarks. Unified training across diverse tasks enables Reasoning-Table to emerge as a robust table reasoning large language model, surpassing larger proprietary models like Claude-3.7-Sonnet by 4.0% on table reasoning benchmarks. The approach also achieves excellent performance on text-to-SQL tasks, reaching 68.3% performance on the BIRD dev dataset with a 7B model. Further experiments demonstrate that Reasoning-Table enhances the model's generalization capabilities and robustness.

Related papers

• TReB: A Comprehensive Benchmark for Evaluating Table Reasoning Capabilities of Large Language Models [30.26407735827857]
  Reasoning with table-structured data poses significant challenges for large language models (LLMs)<n>We present a comprehensive table reasoning evolution benchmark, TReB, which measures both shallow table understanding abilities and deep table reasoning abilities.<n>We create an evaluation framework to robustly measure table reasoning capabilities with three distinct inference modes, TCoT, PoT and ICoT.
  arXiv  Detail & Related papers  (2025-06-23T09:02:04Z)
• Multimodal Tabular Reasoning with Privileged Structured Information [67.40011423365712]
  We introduce TabUlar Reasoning with Bridged infOrmation (sc Turbo)<n>sc Turbo benefits from a structure-aware reasoning trace generator based on DeepSeek-R1.<n>sc Turbo achieves state-of-the-art performance ($+7.2%$ vs. previous SOTA) across multiple datasets.
  arXiv  Detail & Related papers  (2025-06-04T15:46:30Z)
• Table-R1: Region-based Reinforcement Learning for Table Understanding [34.213738690633896]
  We introduce region-based Table-R1, a novel reinforcement learning approach that enhances table understanding.<n>Our method employs Region-Enhanced Supervised Fine-Tuning (RE-SFT) to guide models in identifying relevant table regions.<n>Experiments show that Table-R1 achieves an average performance improvement of 14.36 points across multiple base models.
  arXiv  Detail & Related papers  (2025-05-18T13:40:18Z)
• Towards Better Understanding Table Instruction Tuning: Decoupling the Effects from Data versus Models [62.47618742274461]
  We fine-tune base models from the Mistral, OLMo, and Phi families on existing public training datasets.<n>Our replication achieves performance on par with or surpassing existing table LLMs.<n>We decouple the contributions of training data and the base model, providing insight into their individual impacts.
  arXiv  Detail & Related papers  (2025-01-24T18:50:26Z)
• MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale [66.73529246309033]
  multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks.<n>Existing instruction-tuning datasets only provide phrase-level answers without any intermediate rationales.<n>We introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate rationales.
  arXiv  Detail & Related papers  (2024-12-06T18:14:24Z)
• PoTable: Towards Systematic Thinking via Stage-oriented Plan-then-Execute Reasoning on Tables [13.823024099178172]
  PoTable is a stage-oriented plan-then-execute reasoning approach that achieves systematic thinking on tables.<n>PoTable can produce reliable table reasoning results with highly accurate, steply commented and completely executable programs.
  arXiv  Detail & Related papers  (2024-12-05T15:54:16Z)
• Learning from Imperfect Data: Towards Efficient Knowledge Distillation of Autoregressive Language Models for Text-to-SQL [83.99974309930072]
  Knowledge distillation (KD) is a common approach, which aims to distill the larger teacher model into a smaller student model. We propose to improve the KD with Imperfect Data, namely KID, which effectively boosts the performance without introducing much training budget. KID can not only achieve consistent and significant performance gains across all model types and sizes, but also effectively improve the training efficiency.
  arXiv  Detail & Related papers  (2024-10-15T07:51:00Z)
• TableRAG: Million-Token Table Understanding with Language Models [53.039560091592215]
  TableRAG is a Retrieval-Augmented Generation (RAG) framework specifically designed for LM-based table understanding.<n>TableRAG leverages query expansion combined with schema and cell retrieval to pinpoint crucial information before providing it to the LMs.<n>Our results demonstrate that TableRAG achieves the highest retrieval quality, leading to the new state-of-the-art performance on large-scale table understanding.
  arXiv  Detail & Related papers  (2024-10-07T04:15:02Z)
• ALTER: Augmentation for Large-Table-Based Reasoning [5.164923314261229]
  ALTER(Augmentation for Large-Table-Based Reasoning) is a framework designed to harness the latent augmentation potential in both free-form natural language (NL) questions. By utilizing only a small subset of relevant data from the table, ALTER achieves outstanding performance on table-based reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-07-03T12:34:45Z)
• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [55.33939289989238]
  We propose TAP4LLM as a versatile pre-processor suite for leveraging large language models (LLMs) in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding.
  arXiv  Detail & Related papers  (2023-12-14T15:37:04Z)
• UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science [16.384705926693073]
  This study seeks to extend the power of pretraining methodologies to facilitate the prediction over tables in data science. We introduce UniTabE, a method designed to process tables in a uniform manner, devoid of constraints imposed by specific table structures. In order to implement the pretraining phase, we curated an expansive dataset comprising approximately 13B samples, meticulously gathered from the Kaggle platform.
  arXiv  Detail & Related papers  (2023-07-18T13:28:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.