paper-with-me

홈 › Papers

Better Think with Tables: Leveraging Tables to Enhance Large Language Model Comprehension

2024-12-22 · Jio Oh, Geon Heo, Seungjun Oh, Jindong Wang, Xing Xie, Steven Euijong Whang

Despite the recent advancement of Large Langauge Models (LLMs), they struggle with complex queries often involving multiple conditions, common in real-world scenarios. We propose Thinking with Tables, a technique that assists LLMs to leverage tables for intermediate thinking aligning with human cognitive behavior. By introducing a pre-instruction that triggers an LLM to organize information in tables, our approach achieves a 40.29\% average relative performance increase, higher robustness, and show generalizability to different requests, conditions, or scenarios. We additionally show the influence of data structuredness for the model by comparing results from four distinct structuring levels that we introduce.

📄 PDF Abstract BibTeX arXiv:2412.17189

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

TabSD: Large Free-Form Table Question Answering with SQL-Based Table Decomposition

2025-02-19 · Yuxiang Wang, Junhao Gan, Jianzhong Qi

Question answering on free-form tables (TableQA) is challenging due to the absence of predefined schemas and the presence of noise in large tables. While Large Language Models (LLMs) have shown promise in TableQA, they s…

Answer GenerationFormQuestion Answering

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

2023-12-14 · Yuan Sui, Jiaru Zou, Mengyu Zhou, Xinyi He 외

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. Ex…

Language ModelingLanguage ModellingLarge Language ModelSemantic Similarity+1

Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning

2026-03-25 · Kun-Yang Yu, Zhi Zhou, Shi-Yu Tian, Xiao-Wen Yang 외 arxiv

Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities across modalities such as images and text. However, tabular data, despite being a critical real-world modality, remains relativ…

Information Extraction

TableLlama: Towards Open Large Generalist Models for Tables

2023-11-15 · North American Chapter of the Association for Computational Linguistics 2024 6 · Tianshu Zhang, Xiang Yue, Yifei Li, Huan Sun

Semi-structured tables are ubiquitous. There has been a variety of tasks that aim to automatically interpret, augment, and query tables. Current methods often require pretraining on tables or special model architecture d…

Column Type Annotation

TabVec: Table Vectors for Classification of Web Tables

2018-02-17 · Ghasemi-Gol Majid, Szekely Pedro

There are hundreds of millions of tables in Web pages that contain useful information for many applications. Leveraging data within these tables is difficult because of the wide variety of structures, formats and data en…

ClassificationGeneral Classification