EMNLP Findings2024
TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning
Yuan Sui, Jiaru Zou, Mengyu Zhou, Xinyi He, Lun Du, Shi Han, Dongmei Zhang
Abstract
Table reasoning tasks have shown remarkable progress with the development of large language models (LLMs), which involve interpreting and drawing conclusions from tabular data based on natural language (NL) questions. Existing solutions mainly tested on smaller tables face scalability issues and struggle with complex queries due to incomplete or dispersed data across different table sections. To alleviate these challenges, we propose TAP4LLM as a versatile pre-processor suite for leveraging LLMs in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable subtables 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.
In each module, we design and compare several common methods under various usage scenarios, aiming to shed light on the best practices for leveraging LLMs for tablereasoning tasks. Our experiments show that our method improves LLMs' reasoning capabilities in various tabular tasks and enhances the interaction between LLMs and tabular data by employing effective pre-processing.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
17 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- TableRAG: Million-Token Table Understanding with Language Models cites TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
- TURL: Table Understanding through Representation Learning cites TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
- TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning cites TURL: Table Understanding through Representation Learning
Cited by top-tier papers17
- TableRAG: Million-Token Table Understanding with Language ModelsSi-An Chen, Lesly Miculicich, Julian Eisenschlos, Zifeng Wang et al.NeurIPS 2024 · 86 citations
- PageRank Bandits for Link PredictionYikun Ban, Jiaru Zou, Zihao Li, Yunzhe Qi et al.NeurIPS 2024 · 20 citations
- TableMaster: A Recipe to Advance Table Understanding with Language ModelsLang Cao, Hanbing LiuICLR 2026 · 20 citations
- TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular ReasoningJiaru Zou, Soumya Roy, Vinay Kumar Verma, Ziyi Wang et al.ICLR 2026 · 13 citations
- Large Language Models are Good Relational LearnersFang Wu, Vijay Prakash Dwivedi, Jure LeskovecACL 2025 · 10 citations
Builds on16
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
- TURL: Table Understanding through Representation LearningXiang Deng, Huan Sun, Alyssa Lees, You Wu et al.VLDB 2021 · 2,406 citations
- TaBERT: Pretraining for Joint Understanding of Textual and Tabular DataPengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian RiedelACL 2020 · 417 citations
- GLM-130B: An Open Bilingual Pre-trained ModelAohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang et al.ICLR 2023 · 295 citations
Related papers
- Large Language Models are Versatile Decomposers: Decomposing Evidence and Questions for Table-based ReasoningYunhu Ye, Binyuan Hui, Min Yang, Binhua Li et al.SIGIR 2023 · 75 citations
- AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent FrameworkMeihao Fan, Ju Fan, Nan Tang, Lei Cao et al.VLDB 2025 · 10 citations
- Empowering Tabular Data Preparation with Language Models: Why and How?Mengshi Chen, Yuxiang Sun, Tengchao Li, Jianwei Wang et al.ACL 2026 · 4 citations
- Weaver: Interweaving SQL and LLM for Table ReasoningRohit Khoja, Devanshu Gupta, Yanjie Fu, Dan Roth et al.EMNLP 2025 · 1 citation
- NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data NormalizationMd Mahadi Hasan Nahid, Davood RafieiEMNLP Findings 2024 · 6 citations
