QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback based Self-Correction

arXiv:2403.11886v1 Announce Type: new
Abstract: 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 …

abstract arxiv challenges cs.ai cs.cl efficiency environmental feedback framework hallucinations however language language models large language large language models llms paper parsing reasoning reliability semantic success terms type