Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds

• URL: http://arxiv.org/abs/2607.28908v1
• Date: Fri, 31 Jul 2026 00:15:32 GMT
• Title: Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds
• Abstract summary: Large language models (LLMs) are increasingly prompted to "reflect," yet whether this resembles human revision remains unclear.<n>We introduce the Human-LLM Reflection Framework (HRF), a controlled two-pass protocol comparing human and LLM revision.<n>On objective tasks, reflection yields near-zero information gain (Delta I approx 0), behaving as neutral re-generation indistinguishable from re-sampling.<n>On subjective tasks, it yields significant negative gain (Delta I 0), moving predictions away from the target.
• Score: 7.692886317666416
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reflection, the ability to revisit and revise prior reasoning, is central to how humans improve their answers. Large language models (LLMs) are increasingly prompted to "reflect," yet whether this resembles human revision remains unclear. We introduce the Human-LLM Reflection Framework (HRF), a controlled two-pass protocol comparing human and LLM revision under identical conditions across self-, peer-, and cross-agent settings. Using an information-theoretic analysis based on per-iteration cross-entropy reduction, we find two failure modes of LLM reflection. On objective tasks with finite answer spaces, reflection yields near-zero information gain (Delta I approx 0), behaving as neutral re-generation indistinguishable from re-sampling. On subjective tasks, it yields significant negative gain (Delta I < 0), moving predictions away from the target. Human revision, by contrast, yields positive gain in both settings. Cross-agent experiments localize the failure to the revision step, not input quality: LLMs degrade even high-quality human responses. Diagnostic analyses (revision conditioned on first-pass correctness, and oracle-guided revision against a random-reshuffle baseline) show that which sub-step dominates varies by task and by model rather than reducing to a single mechanism: self-error detection is present on objective multiple-choice tasks but weak on subjective ones, and recovery under an oracle error signal exceeds the baseline for some models and falls below it for others. The unifying account is structural: without external information, self-conditioned revision cannot reduce uncertainty about the target, so LLM reflection is better understood as conditioned re-generation than as genuine error-driven revision.

Related papers

• BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents [24.997265534888626]
  We present textbfBenchTrace, a benchmark for evaluating self-evolution ability in LLM agents.<n>BenchTrace is built on a snapshot-reflection dataset of 1,821 annotated episodes spanning six diverse tasks.<n>We propose textbffailure avoidance rate (FAR), a new evaluation metric measuring the fraction of test cases in which the agent successfully avoids the target failure instance.
  arXiv  Detail & Related papers  (2026-05-28T01:25:37Z)
• Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs [63.88783817420284]
  Embodied robots cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials.<n>We introduce Reflective Test-Time Planning, which integrates two modes of reflection: textitreflection-in-action and textitreflection-on-action<n>We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight.
  arXiv  Detail & Related papers  (2026-02-24T18:55:18Z)
• ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval [64.14282916266998]
  Composed Image Retrieval aims to retrieve target images based on a hybrid query comprising a reference image and a modification text.<n>We propose ReCALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline.<n>Experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-02T04:52:54Z)
• Teaching Large Reasoning Models Effective Reflection [62.73646680747003]
  Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks.<n>However, not all reflections are beneficial-many are superficial, offering little to no improvement over the original answer.<n>We first propose Self-Critique Fine-Tuning (SCFT), a training framework that enhances the model's reflective reasoning ability using only self-generated critiques.
  arXiv  Detail & Related papers  (2026-01-19T04:51:53Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Self-Reflective Generation at Test Time [42.02273611421918]
  Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought.<n>Existing self-reflection either performs revisions over full drafts or learns self-correction via expensive training.<n>We propose Self-Reflective Generation at Test Time (SRGen), a lightweight test-time framework that reflects before generating at uncertain points.
  arXiv  Detail & Related papers  (2025-10-03T11:46:04Z)
• Zero-Shot LLMs in Human-in-the-Loop RL: Replacing Human Feedback for Reward Shaping [2.427844597259453]
  Reinforcement learning (RL) often struggles with reward misalignment.<n>Human-in-the-loop (HITL) methods can mitigate this issue, but they also introduce biases.<n>We propose two key contributions to address these challenges.
  arXiv  Detail & Related papers  (2025-03-26T03:17:12Z)
• GRP: Goal-Reversed Prompting for Zero-Shot Evaluation with LLMs [14.906150451947443]
  Using Large Language Models (LLMs) to evaluate and compare two answers typically involves having LLM-based judges select the better answer.<n>We propose a Goal-Reversed Prompting (GRP) approach for pairwise evaluation that shifts the original task from selecting the better answer to choosing the worse one.
  arXiv  Detail & Related papers  (2025-03-08T09:44:24Z)
• 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)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.