CoReTab: Improving Multimodal Table Understanding with Code-driven Reasoning

• URL: http://arxiv.org/abs/2601.19193v1
• Date: Tue, 27 Jan 2026 04:49:30 GMT
• Title: CoReTab: Improving Multimodal Table Understanding with Code-driven Reasoning
• Authors: Van-Quang Nguyen, Takayuki Okatani,
• Abstract summary: Existing datasets for multimodal table understanding, such as MMTab, primarily provide short factual answers without explicit multi-step reasoning supervision.<n>We introduce CoReTab, a code-driven reasoning framework that produces scalable, interpretable, and automatically verifiable annotations.<n>We evaluate the resulting model trained on CoReTab across 17 MMTab benchmarks spanning table question answering, fact verification, and table structure understanding.
• Score: 14.419739466403172
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing datasets for multimodal table understanding, such as MMTab, primarily provide short factual answers without explicit multi-step reasoning supervision. Models trained on these datasets often generate brief responses that offers insufficient accuracy and limited interpretability into how these models arrive at the final answer. We introduce CoReTab, a code-driven reasoning framework that produces scalable, interpretable, and automatically verifiable annotations by coupling multi-step reasoning with executable Python code. Using the CoReTab framework, we curate a dataset of 115K verified samples averaging 529 tokens per response and fine-tune open-source MLLMs through a three-stage pipeline. We evaluate the resulting model trained on CoReTab across 17 MMTab benchmarks spanning table question answering, fact verification, and table structure understanding. Our model achieves significant gains of +6.2%, +5.7%, and +25.6%, respectively, over MMTab-trained baselines, while producing transparent and verifiable reasoning traces. These results establish CoReTab as a robust and generalizable supervision framework for improving multi-step reasoning in multimodal table understanding.

Related papers

• Reasoning by Commented Code for Table Question Answering [2.497926557563177]
  Table Question Answering (TableQA) poses a significant challenge for large language models.<n>Existing methods, which depend on end-to-end answer generation or single-line program queries, exhibit limited numerical accuracy and reduced interpretability.<n>This work introduces a commented, step-by-step code-generation framework that incorporates explicit reasoning into the Python program-generation process.
  arXiv  Detail & Related papers  (2026-01-31T06:16:35Z)
• Enhancing TableQA through Verifiable Reasoning Trace Reward [38.96476258377461]
  We introduce RE-Tab, a plug-and-play framework that architecturally enhances trajectory search via lightweight, training-free reward modeling.<n>We demonstrate that providing explicit verifiable rewards during State Transition (What is the best action?'') and Simulative Reasoning (Am I sure about the output?'') is crucial to steer the agent's navigation in table states.<n>A direct plug-and-play implementation of RE-Tab brings up to 41.77% improvement in QA accuracy and 33.33% drop in test-time inference samples for consistent answer.
  arXiv  Detail & Related papers  (2026-01-30T04:06:42Z)
• ReasonTabQA: A Comprehensive Benchmark for Table Question Answering from Real World Industrial Scenarios [42.9161992743627]
  We present ReasonTabQA, a large-scale bilingual benchmark encompassing 1,932 tables across 30 industry domains such as energy and automotive.<n>We also introduce TabCodeRL, a reinforcement learning method that leverages table-aware verifiable rewards to guide the generation of logical reasoning paths.
  arXiv  Detail & Related papers  (2026-01-12T07:36:06Z)
• TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data [10.798423317852288]
  TabDSR is a framework consisting of: (1) a query decomposer that breaks down complex questions, (2) a table sanitizer that cleans and filters noisy tables, and (3) a program-of-thoughts (PoT)-based reasoner.<n>We introduce a new dataset, CalTab151, specifically designed for complex numerical reasoning over tables.<n> Experimental results demonstrate that TabDSR consistently outperforms existing methods, achieving state-of-the-art (SOTA) performance with 8.79%, 6.08%, and 19.87% accuracy improvement on TAT-QA, TableBench, and TabDSR, respectively
  arXiv  Detail & Related papers  (2025-11-04T03:13:02Z)
• ExpliCIT-QA: Explainable Code-Based Image Table Question Answering [0.157286095422595]
  ExpliCIT-QA follows a modular design, consisting of: (1) Multimodal Table Understanding, which uses a Chain-of-Thought approach to extract and transform content from table images; (2) Language-based Reasoning, where a step-by-step explanation in natural language is generated to solve the problem; (3) Automatic Code Generation, where Python/Pandas scripts are created based on the reasoning steps, with feedback for handling errors; (4) Code Execution to compute the final answer; and (5) Natural Language Explanation that describes how the answer was computed.<n>This strategy works towards closing the explainability gap in end-to-end Table
  arXiv  Detail & Related papers  (2025-07-15T19:51:24Z)
• 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)
• RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking [63.253294691180635]
  In real-world scenarios, beyond pure text, a substantial amount of knowledge is stored in tables.<n>We first propose a table-corpora-aware RAG framework, named T-RAG, which consists of the hierarchical memory index, multi-stage retrieval, and graph-aware prompting.
  arXiv  Detail & Related papers  (2025-04-02T04:24:41Z)
• 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)
• TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning [61.14586098005874]
  Current Large Language Models (LLMs) exhibit limited ability to understand table structures and to apply precise numerical reasoning.<n>We introduce our Tool-Augmented Reasoning framework for Tables (TART), which integrates LLMs with specialized tools.<n>TART contains three key components: a table formatter to ensure accurate data representation, a tool maker to develop specific computational tools, and an explanation generator to maintain explainability.
  arXiv  Detail & Related papers  (2024-09-18T06:19:59Z)
• Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding [79.9461269253121]
  We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts. Chain-of-Table achieves new state-of-the-art performance on WikiTQ, FeTaQA, and TabFact benchmarks.
  arXiv  Detail & Related papers  (2024-01-09T07:46:26Z)
• 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)
• MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering [61.48881995121938]
  Real-world queries are complex in nature, often over multiple tables in a relational database or web page. Our model, MultiTabQA, not only answers questions over multiple tables, but also generalizes to generate tabular answers.
  arXiv  Detail & Related papers  (2023-05-22T08:25:15Z)

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.