mlsanityData to 7 Oct 2026

MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models

arXiv 2310.12426 ↗First posted 19 Oct 2023cs.CL cs.AIcited by 13

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

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 a relative improvement of up to 20% in Mathematical Reasoning and up to 18% in Logical Entailment.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 21 of its 21 references that are in the map. First posted on arXiv 19 Oct 2023.

Builds on

21 of 21 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023REFINER: Reasoning Feedback on Intermediate Representations4 Apr

Other references · 20

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  8. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  9. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  10. 2019DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphscited by 883
  11. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 820
  12. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
8 more
  1. 2023Fine-Grained Human Feedback Gives Better Rewards for Language Model Trainingcited by 399
  2. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instructioncited by 245
  3. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddingscited by 238
  4. 2022ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoningcited by 175
  5. 2022Language Models of Code are Few-Shot Commonsense Learnerscited by 160
  6. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  7. 2021Explaining Answers with Entailment Treescited by 148
  8. 2023RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputscited by 104

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 2; 2026: 2.

13 papers.

Sort:

By area:

  1. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  2. 2024Tool Learning with Large Language Models: A Surveycited by 221
  3. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  4. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactionscited by 46
  5. 2024Large Language Models have Intrinsic Self-Correction Abilitycited by 45
  6. 2025Large Language Models Hallucination: A Comprehensive Surveycited by 45
  7. 2024Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generationcited by 27
  8. 2024Can Large Vision-Language Models Correct Semantic Grounding Errors By Themselves?cited by 20
  9. 2023Reasons to Reject? Aligning Language Models with Judgmentscited by 15
  10. 2024Agent Alignment in Evolving Social Normscited by 14
  11. 2026Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revisioncited by 4
  12. 2026From Hallucination to Structure Snowballing: The Alignment Tax of Constrained Decoding in LLM Reflectioncited by 1
1 more
  1. 2025Personalized Causal Graph Reasoning for LLMs: An Implementation for Dietary Recommendationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CriticBench: Benchmarking LLMs for Critique-Correct Reasoning
  2. 2024Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision
  3. 2025Advancing Reasoning in Large Language Models: Promising Methods and Approaches
  4. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debate
  5. 2025A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics
  6. 2024Small Language Models Need Strong Verifiers to Self-Correct Reasoning
  7. 2026Improving Mathematical Reasoning Capabilities in Large Language Models via Reasoning Process Error Classification
  8. 2025RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques