MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models
Submission Type: Regular Long Paper
Submission Track: Language Modeling and Analysis of Language Models
Submission Track 2: Natural Language Generation
Keywords: large language models, feedback generation, reasoning, self-correction, in-context learning, prompting, prompt engineering, error correction
TL;DR: We introduce a multi-aspect feedback approach to refine LM generated solutions and reasoning chains.
Abstract: Language Models (LMs) have shown impressive performance in various natural language tasks. However, when it comes to natural language reasoning, LMs still face challenges such as hallucination, generating incorrect intermediate reasoning steps, and making mathematical errors. Recent research has focused on enhancing LMs through *self-improvement* using feedback. Nevertheless, existing approaches relying on a single generic feedback source fail to address the diverse error types found in LM-generated reasoning chains. In this work, we propose **Multi-Aspect Feedback**, an iterative refinement framework that integrates multiple feedback modules, including frozen LMs and external tools, each focusing on a specific error category. Our experimental results demonstrate the efficacy of our approach to addressing several errors in the LM-generated reasoning chain and thus improving the overall performance of an LM in several reasoning tasks. We see an improvement of up to 20% in Mathematical Reasoning and up to 18% in Logical Entailment.
Submission Number: 2497
Loading