Related papers: Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback

Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback

URL: http://arxiv.org/abs/2506.11930v1
Date: Fri, 13 Jun 2025 16:31:51 GMT
Title: Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback
Authors: Dongwei Jiang, Alvin Zhang, Andrew Wang, Nicholas Andrews, Daniel Khashabi,
Abstract summary: LLMs possess some ability to improve their responses when given external feedback.<n>It remains unclear how effectively and thoroughly these models can incorporate external feedback.
Score: 20.985320124495566
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Recent studies have shown LLMs possess some ability to improve their responses when given external feedback. However, it remains unclear how effectively and thoroughly these models can incorporate extrinsic feedback. In an ideal scenario, if LLMs receive near-perfect and complete feedback, we would expect them to fully integrate the feedback and change their incorrect answers to correct ones. In this paper, we systematically investigate LLMs' ability to incorporate feedback by designing a controlled experimental environment. For each problem, a solver model attempts a solution, then a feedback generator with access to near-complete ground-truth answers produces targeted feedback, after which the solver tries again. We evaluate this pipeline across a diverse range of tasks, including math reasoning, knowledge reasoning, scientific reasoning, and general multi-domain evaluations with state-of-the-art language models including Claude 3.7 (with and without extended thinking). Surprisingly, even under these near-ideal conditions, solver models consistently show resistance to feedback, a limitation that we term FEEDBACK FRICTION. To mitigate this limitation, we experiment with sampling-based strategies like progressive temperature increases and explicit rejection of previously attempted incorrect answers, which yield improvements but still fail to help models achieve target performance. We also perform a rigorous exploration of potential causes of FEEDBACK FRICTION, ruling out factors such as model overconfidence and data familiarity. We hope that highlighting this issue in LLMs and ruling out several apparent causes will help future research in self-improvement.

Related papers

Fostering Appropriate Reliance on Large Language Models: The Role of Explanations, Sources, and Inconsistencies [66.30619782227173]
Large language models (LLMs) can produce erroneous responses that sound fluent and convincing.<n>We identify several features of LLM responses that shape users' reliance.<n>We find that explanations increase reliance on both correct and incorrect responses.<n>We observe less reliance on incorrect responses when sources are provided or when explanations exhibit inconsistencies.
arXiv Detail & Related papers (2025-02-12T16:35:41Z)
Learning to Refine with Fine-Grained Natural Language Feedback [81.70313509881315]
We propose looking at refinement with feedback as a composition of three distinct LLM competencies.<n>A key property of the proposed Detect, Critique, Refine ("DCR") method is that the step 2 critique model can give fine-grained feedback about errors.<n>We show that models of different capabilities benefit from refining with DCR on the task of improving factual consistency of document grounded summaries.
arXiv Detail & Related papers (2024-07-02T16:15:01Z)
When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models [15.781930031346105]
Self-reflection enhances performance in TruthfulQA, but adversely affects results in HotpotQA. We find that self-reflection shows the most benefit when models are less likely to be correct initially, and when overall question difficulty is higher. Based on our findings, we propose guidelines for decisions on when to implement self-reflection.
arXiv Detail & Related papers (2024-04-14T02:47:32Z)
RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models [17.782410287625645]
This paper proposes a benchmark, RefuteBench, covering tasks such as question answering, machine translation, and email writing. The evaluation aims to assess whether models can positively accept feedback in form of refuting instructions and whether they can consistently adhere to user demands throughout the conversation.
arXiv Detail & Related papers (2024-02-21T01:39:56Z)
Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Prompting [0.4662017507844857]
This paper studies such repetitive behavior and its effect by defining a novel setting, Chain-of-Feedback (CoF) To alleviate these troubles, we propose a novel method, Recursive Chain-of-Feedback (R-CoF)
arXiv Detail & Related papers (2024-02-05T00:44:28Z)
Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives [45.87069217634753]
Research indicates without external feedback, Large Language Model's intrinsic reflection is unstable. Our investigation unveils that the key bottleneck is the quality of the self-evaluated feedback. We advocate Self-Contrast: It adaptively explores diverse solving perspectives tailored to the request, contrasts the differences, and summarizes these discrepancies into a checklist which could be used to re-examine and eliminate discrepancies.
arXiv Detail & Related papers (2024-01-04T00:32:33Z)
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
Recent large language models (LLM) are leveraging human feedback to improve their generation quality. We propose LLMRefine, an inference time optimization method to refine LLM's output. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
arXiv Detail & Related papers (2023-11-15T19:52:11Z)
Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment [82.60594940370919]
We propose the FlipFlop experiment to study the multi-turn behavior of Large Language Models (LLMs) We show that models flip their answers on average 46% of the time and that all models see a deterioration of accuracy between their first and final prediction, with an average drop of 17% (the FlipFlop effect) We conduct finetuning experiments on an open-source LLM and find that finetuning on synthetically created data can mitigate - reducing performance deterioration by 60% - but not resolve sycophantic behavior entirely.
arXiv Detail & Related papers (2023-11-14T23:40:22Z)
MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models [64.70153487607172]
Language Models (LMs) have shown impressive performance in various natural language tasks. 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. 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.
arXiv Detail & Related papers (2023-10-19T02:32:39Z)
RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought [56.558892336235914]
Reversing Chain-of-Thought (RCoT) is a novel method to improve large language models' reasoning abilities. RCoT automatically detects and rectifys factual inconsistency in generated solutions. We show that manually written fine-grained feedback can dramatically improve LLMs' reasoning abilities.
arXiv Detail & Related papers (2023-05-19T08:02:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.