Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding

• URL: http://arxiv.org/abs/2509.07676v1
• Date: Tue, 09 Sep 2025 12:43:28 GMT
• Title: Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding
• Authors: Jipeng Li, Zeyu Gao, Yubin Qi, Hande Dong, Weijian Chen, Qiang Lin,
• Abstract summary: Large Language Models (LLMs) have achieved remarkable performance across diverse tasks, yet their susceptibility to generating incorrect content during inference remains a critical unsolved challenge.<n>We propose Feedback-Triggered Regeneration (FTR), a novel framework that synergizes user feedback with enhanced decoding dynamics.<n>Specifically, FTR activates response regeneration only upon receiving negative user feedback, thereby circumventing error propagation from faulty self-assessment while preserving originally correct outputs.
• Score: 4.220190655754022
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) have achieved remarkable performance across diverse tasks, yet their susceptibility to generating incorrect content during inference remains a critical unsolved challenge. While self-correction methods offer potential solutions, their effectiveness is hindered by two inherent limitations: (1) the absence of reliable guidance signals for error localization, and (2) the restricted reasoning depth imposed by conventional next-token decoding paradigms. To address these issues, we propose Feedback-Triggered Regeneration (FTR), a novel framework that synergizes user feedback with enhanced decoding dynamics. Specifically, FTR activates response regeneration only upon receiving negative user feedback, thereby circumventing error propagation from faulty self-assessment while preserving originally correct outputs. Furthermore, we introduce Long-Term Multipath (LTM) decoding, which enables systematic exploration of multiple reasoning trajectories through delayed sequence evaluation, effectively overcoming the myopic decision-making characteristic of standard next-token prediction. Extensive experiments on mathematical reasoning and code generation benchmarks demonstrate that our framework achieves consistent and significant improvements over state-of-the-art prompt-based self-correction methods.

Related papers

• 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)
• PROMISE: Process Reward Models Unlock Test-Time Scaling Laws in Generative Recommendations [52.67948063133533]
  Generative Recommendation has emerged as a promising paradigm, reformulating recommendation as a sequence-to-sequence generation task over hierarchical Semantic IDs.<n>Existing methods suffer from a critical issue we term Semantic Drift, where errors in early, high-level tokens irreversibly divert the generation trajectory into irrelevant semantic subspaces.<n>We propose Promise, a novel framework that integrates dense, step-by-step verification into generative models.
  arXiv  Detail & Related papers  (2026-01-08T07:38:46Z)
• Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction [14.164508061248775]
  Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency.<n>We propose reflective confidence, a novel reasoning framework that transforms low-confidence signals from termination indicators into reflection triggers.<n> Experiments on mathematical reasoning benchmarks, including AIME 2025, demonstrate significant accuracy improvements over advanced early-stopping baselines at comparable computational cost.
  arXiv  Detail & Related papers  (2025-12-21T05:35:07Z)
• Multi-Fidelity Delayed Acceptance: hierarchical MCMC sampling for Bayesian inverse problems combining multiple solvers through deep neural networks [0.3499870393443268]
  Inverse uncertainty quantification (UQ) tasks are computationally demanding when dealing with physics-based models.<n>Data-driven surrogate models may help reduce evaluation costs, but their utility is often limited by the expense of generating high-fidelity data.<n>We propose a Multi-Fidelity Delayed Acceptance scheme for Bayesian inverse problems.
  arXiv  Detail & Related papers  (2025-12-18T11:32:16Z)
• Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models [13.32858759983739]
  Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating text inconsistent with visual inputs.<n>Existing inference-time interventions to mitigate this issue present a challenging trade-off.<n>We present Residual-Update Directed DEcoding Regulation (RUDDER), a framework that steers LVLMs towards visually-grounded generation.
  arXiv  Detail & Related papers  (2025-11-13T13:29:38Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• From Long to Short: LLMs Excel at Trimming Own Reasoning Chains [48.692414597960244]
  O1/R1 style large reasoning models (LRMs) signal a substantial leap forward over conventional instruction-following LLMs.<n>Recent studies show that LRMs are prone to suffer from overthinking.<n>We propose a test-time scaling method, EDIT, which efficiently guides LRMs to identify the shortest correct reasoning paths at test time.
  arXiv  Detail & Related papers  (2025-09-07T19:00:44Z)
• ASCoT: An Adaptive Self-Correction Chain-of-Thought Method for Late-Stage Fragility in LLMs [16.266957200961908]
  Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs)<n>Errors introduced in the later stages of a CoT chain are significantly more likely to corrupt the final answer than identical errors made at the beginning.<n>We introduce the Adaptive Self-Correction Chain-of-Thought (ASCoT) method to address this specific vulnerability.
  arXiv  Detail & Related papers  (2025-08-07T11:26:40Z)
• Hierarchical Verification of Speculative Beams for Accelerating LLM Inference [0.0]
  Hierarchical Verification Tree (HVT) is a novel framework that restructures speculative beam decoding by prioritizing high-likelihood drafts.<n>HVT consistently outperforms existing speculative decoding schemes, achieving substantial reductions in inference time and energy consumption.<n>Findings highlight the potential of hierarchical verification strategies as a new direction for accelerating large language model inference.
  arXiv  Detail & Related papers  (2025-07-30T02:58:03Z)
• Lost at the Beginning of Reasoning [82.18834329384514]
  We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.<n>We introduce a new benchmark specifically constructed with deliberately flawed first reasoning steps to systematically evaluate model self-correction capabilities.
  arXiv  Detail & Related papers  (2025-06-27T09:53:57Z)
• Towards Better Code Generation: Adaptive Decoding with Uncertainty Guidance [28.99265405319943]
  We introduce AdaDec, an adaptive decoding framework guided by token-level uncertainty quantified via Shannon entropy.<n>AdaDec achieves up to a 15.5% improvement in Pass@1 accuracy compared to greedy decoding, matches or outperforms traditional beam search.
  arXiv  Detail & Related papers  (2025-06-10T16:49:46Z)
• Beyond Exponential Decay: Rethinking Error Accumulation in Large Language Models [0.0]
  We show that errors are not uniformly distributed but are concentrated at sparse "key tokens" representing critical decision junctions.<n>We propose a framework for next-generation systems centered on selective preservation of semantically vital tokens.
  arXiv  Detail & Related papers  (2025-05-30T03:57:31Z)
• Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion [52.315729095824906]
  MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD) is a novel framework that introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference.<n>It performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps.<n>Extensive experiments demonstrate PPAD's significant improvements.
  arXiv  Detail & Related papers  (2025-05-26T14:42:35Z)
• Auto-Prompt Generation is Not Robust: Prompt Optimization Driven by Pseudo Gradient [50.15090865963094]
  We introduce PertBench, a comprehensive benchmark dataset that includes a wide range of input perturbations.<n>Our analysis reveals substantial vulnerabilities in existing prompt generation strategies.<n>We propose PGO, a gradient-free prompt generation framework that leverages perturbation types as pseudo-gradient signals.
  arXiv  Detail & Related papers  (2024-12-24T06:05:08Z)
• An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking [50.81324768683995]
  FIRST is a novel approach that integrates a learning-to-rank objective and leveraging the logits of only the first generated token. We extend the evaluation of FIRST to the TREC Deep Learning datasets (DL19-22), validating its robustness across diverse domains. Our experiments confirm that fast reranking with single-token logits does not compromise out-of-domain reranking quality.
  arXiv  Detail & Related papers  (2024-11-08T12:08:17Z)
• DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays [26.032139258562708]
  We propose $textbfDEER (Delay-resilient-Enhanced RL)$, a framework designed to effectively enhance the interpretability and address the random delay issues. In a variety of delayed scenarios, the trained encoder can seamlessly integrate with standard RL algorithms without requiring additional modifications. The results confirm that DEER is superior to state-of-the-art RL algorithms in both constant and random delay settings.
  arXiv  Detail & Related papers  (2024-06-05T09:45:26Z)
• Confident Adaptive Language Modeling [95.45272377648773]
  CALM is a framework for dynamically allocating different amounts of compute per input and generation timestep. We demonstrate the efficacy of our framework in reducing compute -- potential speedup of up to $times 3$ -- while provably maintaining high performance.
  arXiv  Detail & Related papers  (2022-07-14T17:00:19Z)

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.