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

📅 2025-06-29
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Large language models (LLMs) suffer from degraded table reasoning performance due to input-length constraints, hindering effective processing of long, wide tables. Method: We propose Adaptive Table Filtering (ATF), a plug-and-play framework that requires no model fine-tuning. ATF dynamically identifies and retains query-relevant table regions via question-aware column semantic description generation, hierarchical clustering, and sparse–dense vector alignment scoring. Its modular design enables cross-task adaptive balancing between information preservation and structural simplification. Contribution/Results: ATF prunes ~70% of table cells on average, significantly improving reasoning accuracy across diverse TableQA benchmarks. Only in rare cases requiring full-table structural understanding does performance marginally decline. Crucially, ATF is the first approach to jointly model LLM-driven semantic comprehension with interpretable, structured filtering—achieving strong efficiency, task-agnostic generalizability, and parameter-free transferability.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

Overcoming input length limits for LLMs with large tables
Pruning uninformative columns and rows adaptively
Balancing informativeness and minimalism across different tasks
Innovation

Methods, ideas, or system contributions that make the work stand out.

Modular question-aware table filtering pipeline
LLM-generated column clustering and alignment
Seamless integration without model retraining
💼 Related Jobs
No related jobs found.
W
Wonjune Jang
Department of Mathematics, Myongji University, Korea