DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models

• URL: http://arxiv.org/abs/2503.03149v1
• Date: Wed, 05 Mar 2025 03:45:50 GMT
• Title: DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models
• Authors: YiQiu Guo, Yuchen Yang, Zhe Chen, Pingjie Wang, Yusheng Liao, Ya Zhang, Yanfeng Wang, Yu Wang,
• Abstract summary: We present Dynamic Self-Verify Decoding (DSVD), a novel decoding framework that enhances generation reliability through real-time hallucination detection and efficient error correction.<n>Our work establishes that real-time self-verification during generation offers a viable path toward more trustworthy language models without sacrificing practical deployability.
• Score: 31.15459303576494
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The reliability of large language models remains a critical challenge, particularly due to their susceptibility to hallucinations and factual inaccuracies during text generation. Existing solutions either underutilize models' self-correction with preemptive strategies or use costly post-hoc verification. To further explore the potential of real-time self-verification and correction, we present Dynamic Self-Verify Decoding (DSVD), a novel decoding framework that enhances generation reliability through real-time hallucination detection and efficient error correction. DSVD integrates two key components: (1) parallel self-verification architecture for continuous quality assessment, (2) dynamic rollback mechanism for targeted error recovery. Extensive experiments across five benchmarks demonstrate DSVD's effectiveness, achieving significant improvement in truthfulness (Quesetion-Answering) and factual accuracy (FActScore). Results show the DSVD can be further incorporated with existing faithful decoding methods to achieve stronger performance. Our work establishes that real-time self-verification during generation offers a viable path toward more trustworthy language models without sacrificing practical deployability.

Related papers

• Object-Level Verbalized Confidence Calibration in Vision-Language Models via Semantic Perturbation [26.580361841501514]
  Vision-language models (VLMs) excel in various multimodal tasks but frequently suffer from poor calibration. This miscalibration undermines user trust, especially when models confidently provide incorrect or fabricated information. We propose a novel Confidence through Semantic Perturbation (CSP) framework to improve the calibration of verbalized confidence for object-centric queries.
  arXiv  Detail & Related papers  (2025-04-21T04:01:22Z)
• TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reduction [5.925383490825323]
  Vision-language models (VLMs) have achieved remarkable advancements, capitalizing on the impressive capabilities of large language models (LLMs) Despite this, a critical challenge known as hallucination occurs when models overconfidently describe objects or attributes absent from the image. This limitation reduces model reliability in high-stakes applications.
  arXiv  Detail & Related papers  (2025-03-06T14:11:00Z)
• Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling [48.15636223774418]
  Large language models (LLMs) frequently hallucinate due to misaligned self-awareness.<n>Existing approaches mitigate hallucinations via uncertainty estimation or query rejection.<n>We propose the Explicit Knowledge Boundary Modeling framework to integrate fast and slow reasoning systems.
  arXiv  Detail & Related papers  (2025-03-04T03:16:02Z)
• Breaking Focus: Contextual Distraction Curse in Large Language Models [68.4534308805202]
  We investigate a critical vulnerability in Large Language Models (LLMs)<n>This phenomenon arises when models fail to maintain consistent performance on questions modified with semantically coherent but irrelevant context.<n>We propose an efficient tree-based search methodology to automatically generate CDV examples.
  arXiv  Detail & Related papers  (2025-02-03T18:43:36Z)
• Automated Proof Generation for Rust Code via Self-Evolution [69.25795662658356]
  We introduce SAFE, a novel framework that overcomes the lack of human-written proof to enable automated proof generation of Rust code. We demonstrate superior efficiency and precision compared to GPT-4o. This advancement leads to a significant improvement in performance, achieving a 70.50% accuracy rate in a benchmark crafted by human experts.
  arXiv  Detail & Related papers  (2024-10-21T08:15:45Z)
• Improving Retrieval Augmented Language Model with Self-Reasoning [20.715106330314605]
  We propose a novel self-reasoning framework aimed at improving the reliability and traceability of RALMs.<n>The framework involves constructing self-reason trajectories with three processes: a relevance-aware process, an evidence-aware selective process, and a trajectory analysis process.<n>We have evaluated our framework across four public datasets to demonstrate the superiority of our method.
  arXiv  Detail & Related papers  (2024-07-29T09:05:10Z)
• M2CVD: Enhancing Vulnerability Semantic through Multi-Model Collaboration for Code Vulnerability Detection [52.4455893010468]
  Large Language Models (LLMs) have strong capabilities in code comprehension, but fine-tuning costs and semantic alignment issues limit their project-specific optimization. Code models such CodeBERT are easy to fine-tune, but it is often difficult to learn vulnerability semantics from complex code languages. This paper introduces the Multi-Model Collaborative Vulnerability Detection approach (M2CVD) to improve the detection accuracy of code models.
  arXiv  Detail & Related papers  (2024-06-10T00:05:49Z)
• Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor [4.35807211471107]
  This work proposes a novel two-stage consistency learning approach for retrieved information compression in retrieval-augmented language models. The proposed method is empirically validated across multiple datasets, demonstrating notable enhancements in precision and efficiency for question-answering tasks.
  arXiv  Detail & Related papers  (2024-06-04T12:43:23Z)
• Towards Calibrated Robust Fine-Tuning of Vision-Language Models [97.19901765814431]
  This work proposes a robust fine-tuning method that improves both OOD accuracy and confidence calibration simultaneously in vision language models. We show that both OOD classification and OOD calibration errors have a shared upper bound consisting of two terms of ID data. Based on this insight, we design a novel framework that conducts fine-tuning with a constrained multimodal contrastive loss enforcing a larger smallest singular value.
  arXiv  Detail & Related papers  (2023-11-03T05:41:25Z)
• Confidence Attention and Generalization Enhanced Distillation for Continuous Video Domain Adaptation [62.458968086881555]
  Continuous Video Domain Adaptation (CVDA) is a scenario where a source model is required to adapt to a series of individually available changing target domains. We propose a Confidence-Attentive network with geneRalization enhanced self-knowledge disTillation (CART) to address the challenge in CVDA.
  arXiv  Detail & Related papers  (2023-03-18T16:40:10Z)

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.