Better Think with Tables: Leveraging Tables to Enhance Large Language Model Comprehension
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingLarge Language ModelSimilar Papers 제목 키워드 기반
TabSD: Large Free-Form Table Question Answering with SQL-Based Table Decomposition
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 AnsweringTAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning
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+1Thinking with Tables: Enhancing Multi-Modal Tabular Understanding via Neuro-Symbolic Reasoning
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 ExtractionTableLlama: Towards Open Large Generalist Models for Tables
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 AnnotationTabVec: Table Vectors for Classification of Web Tables
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