TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning
Current Large Language Models (LLMs) exhibit limited ability to understand table structures and to apply precise numerical reasoning, which is crucial for tasks such as table question answering (TQA) and table-based fact verification (TFV). To address these challenges, we introduce our Tool-Augmented Reasoning framework for Tables (TART), which integrates LLMs with specialized tools. TART contains three key components: a table formatter to ensure accurate data representation, a tool maker to develop specific computational tools, and an explanation generator to maintain explainability. We also present the TOOLTAB dataset, a new benchmark designed specifically for training LLMs in table-tool integration. Our experiments indicate that TART achieves substantial improvements over existing methods (e.g., Chain-of-Thought) by improving both the precision of data processing and the clarity of the reasoning process. Notably, TART paired with CodeLlama achieves 90.0% of the accuracy of the closed-sourced LLM GPT-3.5-turbo, highlighting its robustness in diverse real-world scenarios. All the code and data are available at https://github.com/XinyuanLu00/TART.
Code (1)
Tasks
Fact VerificationQuestion AnsweringTable-based Fact VerificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents
Tool-augmented vision-language models (VLMs) can solve multimodal, multi-step tasks by calling external tools, yet they remain fragile in practice. Existing works have two common gaps. Supervised fine-tuning (SFT) is bui…
Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoning
Recent medical MLLMs have made significant progress in generating step-by-step textual reasoning chains. However, they still struggle with complex clinical tasks that necessitate dynamic and iterative focusing on fine-gr…
Reinforcement LearningOpenTable-R1: A Reinforcement Learning Augmented Tool Agent for Open-Domain Table Question Answering
Open-domain table question answering traditionally relies on a two-stage pipeline: static table retrieval followed by a closed-domain answer. In contrast, we propose an end-to-end agentic framework that embeds multi-turn…
Language ModelingLanguage ModellingLarge Language ModelQuestion Answering+1David vs. Goliath: Verifiable Agent-to-Agent Jailbreaking via Reinforcement Learning
The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming safety evaluation in tool-augmented environments from a subjective NLP t…
Reinforcement LearningICX360: In-Context eXplainability 360 Toolkit
Large Language Models (LLMs) have become ubiquitous in everyday life and are entering higher-stakes applications ranging from summarizing meeting transcripts to answering doctors' questions. As was the case with earlier …