Pith. sign in

REVIEW 12 cited by

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.04398 v2 pith:U2X4KDXE submitted 2024-01-09 cs.CL

Zilong Wang , Hao Zhang , Chun-Liang Li , Julian Martin Eisenschlos , Vincent Perot , Zifeng Wang , Lesly Miculicich , Yasuhisa Fujii
show 3 more authors
Jingbo Shang Chen-Yu Lee Tomas Pfister
This is my paper
classification cs.CL
keywords reasoningchaintabulartablechain-of-tabledatallmstable-based
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Table-based reasoning with large language models (LLMs) is a promising direction to tackle many table understanding tasks, such as table-based question answering and fact verification. Compared with generic reasoning, table-based reasoning requires the extraction of underlying semantics from both free-form questions and semi-structured tabular data. Chain-of-Thought and its similar approaches incorporate the reasoning chain in the form of textual context, but it is still an open question how to effectively leverage tabular data in the reasoning chain. We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts. Specifically, we guide LLMs using in-context learning to iteratively generate operations and update the table to represent a tabular reasoning chain. LLMs can therefore dynamically plan the next operation based on the results of the previous ones. This continuous evolution of the table forms a chain, showing the reasoning process for a given tabular problem. The chain carries structured information of the intermediate results, enabling more accurate and reliable predictions. Chain-of-Table achieves new state-of-the-art performance on WikiTQ, FeTaQA, and TabFact benchmarks across multiple LLM choices.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Utilizing Training Data to Improve LLM Reasoning for Tabular Understanding

    cs.LG 2025-08 conditional novelty 6.0 of 10

    LRTab retrieves error-avoiding prompt conditions learned from incorrect chain-of-thought traces on training tables to improve LLM tabular reasoning, achieving modest gains on WikiTQ and TabFact.

  2. AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data

    cs.CL 2025-07 conditional novelty 6.0 of 10

    AraTable is the first Arabic tabular QA benchmark; its experiments show LLMs are much weaker at reasoning over Arabic tables than at direct lookup.

  3. MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance

    cs.CL 2025-06 conditional novelty 6.0 of 10

    MDBench is a synthetically generated, knowledge-guided benchmark for multi-document QA on which frontier LLMs achieve only about 60% exact match.

  4. MasHost Builds It All: Autonomous Multi-Agent System Directed by Reinforcement Learning

    cs.MA 2025-06 conditional novelty 6.0 of 10

    MasHost uses reinforcement learning to autonomously construct query-adaptive multi-agent graphs, and its authors report the best average accuracy across six LLM benchmarks.

  5. Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Table-r1 combines a layout-transformation self-supervised task and a mix-paradigm GRPO stage so 7B/8B models outperform other small-model table reasoners and approach GPT-4o-level accuracy.

  6. TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning

    cs.AI 2025-09 conditional novelty 5.0 of 10

    TableMind, a two-stage SFT-plus-RL agent trained on an 8B model, reports state-of-the-art results on three table reasoning benchmarks.

  7. ExpliCIT-QA: Explainable Code-Based Image Table Question Answering

    cs.CL 2025-07 conditional novelty 5.0 of 10

    ExpliCIT-QA turns table-image question answering into a traceable sequence of table extraction, natural-language reasoning, code generation, execution, and explanation.

  8. What to Keep and What to Drop: Adaptive Table Filtering Framework

    cs.CL 2025-06 conditional novelty 5.0 of 10

    ATF prunes table columns and rows with LLM scoring plus retrieval, cutting cells by about 70% and improving out-of-domain TableQA accuracy, while hurting in-domain QA and fact verification.

  9. Multimodal Tabular Reasoning with Privileged Structured Information

    cs.LG 2025-06 conditional novelty 5.0 of 10

    An 8B multimodal LLM trained on 9k reasoning traces distilled from structured tables reaches state-of-the-art open-source accuracy on table-image question answering and fact verification.

  10. Speculative Reward Model Boosts Decision Making Ability of LLMs Cost-Effectively

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A plug-and-play external reward model with speculative rejection sampling cuts tree-search cost for LLM decision-making to about 1/10 while keeping or slightly improving accuracy on math, planning, and financial reaso...

  11. MRT at IberLEF-2025 PRESTA Task: Maximizing Recovery from Tables with Multiple Steps

    cs.CL 2025-07 conditional novelty 4.0 of 10

    MRT, an LLM code-generation pipeline for Spanish table QA, achieves 85% accuracy on the IberLEF 2025 PRESTA test set.

  12. MRT at SemEval-2025 Task 8: Maximizing Recovery from Tables with Multiple Steps

    cs.CL 2025-05 conditional novelty 4.0 of 10

    A code-generation pipeline with step-by-step instructions and error recovery scores 70.50% on the SemEval-2025 table question-answering task.

Pith tools