Saved in:
Bibliographic Details
Main Authors: Huang, Xiang, Cheng, Sitao, Huang, Shanshan, Shen, Jiayu, Xu, Yong, Zhang, Chaoyun, Qu, Yuzhong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.11886
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909222844760064
author Huang, Xiang
Cheng, Sitao
Huang, Shanshan
Shen, Jiayu
Xu, Yong
Zhang, Chaoyun
Qu, Yuzhong
author_facet Huang, Xiang
Cheng, Sitao
Huang, Shanshan
Shen, Jiayu
Xu, Yong
Zhang, Chaoyun
Qu, Yuzhong
contents Employing Large Language Models (LLMs) for semantic parsing has achieved remarkable success. However, we find existing methods fall short in terms of reliability and efficiency when hallucinations are encountered. In this paper, we address these challenges with a framework called QueryAgent, which solves a question step-by-step and performs step-wise self-correction. We introduce an environmental feedback-based self-correction method called ERASER. Unlike traditional approaches, ERASER leverages rich environmental feedback in the intermediate steps to perform selective and differentiated self-correction only when necessary. Experimental results demonstrate that QueryAgent notably outperforms all previous few-shot methods using only one example on GrailQA and GraphQ by 7.0 and 15.0 F1. Moreover, our approach exhibits superiority in terms of efficiency, including runtime, query overhead, and API invocation costs. By leveraging ERASER, we further improve another baseline (i.e., AgentBench) by approximately 10 points, revealing the strong transferability of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11886
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction
Huang, Xiang
Cheng, Sitao
Huang, Shanshan
Shen, Jiayu
Xu, Yong
Zhang, Chaoyun
Qu, Yuzhong
Computation and Language
Artificial Intelligence
Employing Large Language Models (LLMs) for semantic parsing has achieved remarkable success. However, we find existing methods fall short in terms of reliability and efficiency when hallucinations are encountered. In this paper, we address these challenges with a framework called QueryAgent, which solves a question step-by-step and performs step-wise self-correction. We introduce an environmental feedback-based self-correction method called ERASER. Unlike traditional approaches, ERASER leverages rich environmental feedback in the intermediate steps to perform selective and differentiated self-correction only when necessary. Experimental results demonstrate that QueryAgent notably outperforms all previous few-shot methods using only one example on GrailQA and GraphQ by 7.0 and 15.0 F1. Moreover, our approach exhibits superiority in terms of efficiency, including runtime, query overhead, and API invocation costs. By leveraging ERASER, we further improve another baseline (i.e., AgentBench) by approximately 10 points, revealing the strong transferability of our approach.
title QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2403.11886