# Chain-of-table: Evolving tables in the reasoning chain for table understanding

DevFeed: [Chain-of-table: Evolving tables in the reasoning chain for table understanding](<https://devfeed.tech/articles/chain-of-table-evolving-tables-in-the-reasoning-chain-for-table-understanding-28554.md>)

Original publisher: [Read original article](<http://blog.research.google/2024/03/chain-of-table-evolving-tables-in.html>)

Author: Google AI (noreply@blogger.com)

Published: 2024-03-11T19:08:00Z

Content type: article

Language: en

Sources: [Google Research](<https://devfeed.tech/sources/google-research.md>)

Topics: [Chain-of-thought](<https://devfeed.tech/topics/chain-of-thought.md>), [Natural language processing](<https://devfeed.tech/topics/nlp.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [data](<https://devfeed.tech/topics/data.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [actor](<https://devfeed.tech/tags/actor.md>), [ai](<https://devfeed.tech/tags/ai.md>), [awards](<https://devfeed.tech/tags/awards.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [chain-of-thought](<https://devfeed.tech/tags/chain-of-thought.md>), [data](<https://devfeed.tech/tags/data.md>), [information](<https://devfeed.tech/tags/information.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [machine-intelligence](<https://devfeed.tech/tags/machine-intelligence.md>), [models](<https://devfeed.tech/tags/models.md>), [natural-language-processing](<https://devfeed.tech/tags/natural-language-processing.md>), [performance](<https://devfeed.tech/tags/performance.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [research](<https://devfeed.tech/tags/research.md>), [table](<https://devfeed.tech/tags/table.md>), [verify](<https://devfeed.tech/tags/verify.md>)

## AI overview

The article presents Chain-of-Table, a framework for table understanding that trains large language models to reason step by step by iteratively updating a table. The approach uses in-context learning to generate operations dynamically and reports improved results on the WikiTQ, TabFact, and FeTaQA benchmarks.

## Source excerpt

Posted by Zilong Wang, Student Researcher, and Chen-Yu Lee, Research Scientist, Cloud AI Team People use tables every day to organize and interpret complex information in a structured, easily accessible format. Due to the ubiquity of such tables, reasoning over tabular data has long been a central topic in natural language processing (NLP). Researchers in this field have aimed to leverage language models to help users answer questions, verify statements, and analyze data based on tables. However, language models are trained over large amounts of plain text, so the inherently structured nature of tabular data can be difficult for language models to fully comprehend and utilize. Recently, large language models (LLMs) have achieved outstanding performance across diverse natural language understanding (NLU) tasks by generating reliable reasoning chains, as shown in works like Chain-of-Thought and Least-to-Most. However, the most suitable way for LLMs to reason over tabular data remains an open question. In "Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding", we propose a framework to tackle table understanding tasks, where we train LLMs to outline their reasoning step by step, updating a given table iteratively to reflect each part of a thought process, akin to how people solve the table-based problems. This enables the LLM to transform the table into simpler and more manageable segments so that it can understand and analyze each part of the table in depth. This approach has yielded significant improvements and achieved new state-of-the-art results on the WikiTQ, TabFact, and FeTaQA benchmarks. The figure below shows the high-level overview of the proposed Chain-of-Table and other methods. Given a complex table where a cyclist's nationality and name are in the same cell, (a) generic, multi-step reasoning is unable to provide the correct answer (b) program-aided reasoning generates and executes programs (e.g., SQL queries) to deliver the answ