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

WonJune Jang
6/30/2025
cs.CL

Official code: torijune/ATF-Adaptive-Table-Filtering-Framework (1 star, CC-BY-4.0, last commit 2025-08-08).

Abstract

Large language models (LLMs) for table-based reasoning often struggle with large tables due to input length limits. We propose ATF (Adaptive Table Filtering Framework), a modular and question-aware filtering pipeline that prunes uninformative columns and rows using LLM-generated column descriptions, clustering, and sparse-dense alignment scores. ATF integrates seamlessly with existing models (e.g., TAPAS, TAPEX) without retraining. Experiments show that ATF reduces table cells by 70%, boosting performance on out-of-domain TableQA tasks while causing slight performance drops on Table Fact Verification, where full-table context is more critical. These results highlight ATF's ability to adaptively balance informativeness and minimalism across tasks. Our code available at: https://github.com/torijune/ATF-Adaptive-Table-Filtering-Framework

View on arXivView PDF

Code Implementations(1)

torijune/ATF-Adaptive-Table-Filtering-FrameworkOfficial100%
CC-BY-4.0

Repo. TCRF-TableColumnRowFiltering Research

10PythonMay 28, 20251 years agoCC-BY-4.0

Similar Papers

When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables

83% match2025

TabScope: Question-Adaptive Scope Selection for Table Question Answering

83% match2026

Exploring Performance Contrasts in TableQA: Step-by-Step Reasoning Boosts Bigger Language Models, Limits Smaller Language Models

81% match2024

TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning

80% match2023

TableBench: A Comprehensive and Complex Benchmark for Table Question Answering

80% match1 repo932024

Benchmarking Table Comprehension In The Wild

80% match2024

Cite this paper

@article{jang2025what,
  title  = {What to Keep and What to Drop: Adaptive Table Filtering Framework},
  author = {WonJune Jang},
  year   = {2025},
  eprint = {2506.23463},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2506.23463v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2506.23463.svg)](https://codeofpaper.com/paper/2506.23463)

Discussion