ALTER: Augmentation for Large-Table-Based Reasoning

2024/07/03 by Han Zhang, Zhang, Han, Yuheng Ma +3 · 3 citations
Computer Science · #Semantic Web and Ontologies

paper · pdf · doi:10.48550/arxiv.2407.03061

Abstract

While extensive research has explored the use of large language models (LLMs) for table-based reasoning, most approaches struggle with scalability when applied to large tables. To maintain the superior comprehension abilities of LLMs in these scenarios, we introduce ALTER(Augmentation for Large-Table-Based Reasoning)-a framework designed to harness the latent augmentation potential in both free-form natural language (NL) questions, via the query augmentor, and semi-structured tabular data, through the table augmentor. By utilizing only a small subset of relevant data from the table and supplementing it with pre-augmented schema, semantic, and literal information, ALTER achieves outstanding performance on table-based reasoning benchmarks. We also provide a detailed analysis of large-table scenarios, comparing different methods and various partitioning principles. In these scenarios, our method outperforms all other approaches and exhibits robustness and efficiency against perturbations.

Cited by

• Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding
• Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation
• M3TQA: Massively Multilingual Multitask Table Question Answering

Related

• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning
• A Survey of Table Reasoning with Large Language Models
• Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning
• Large Language Models are few(1)-shot Table Reasoners
• Table as a Modality for Large Language Models