Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models

• URL: http://arxiv.org/abs/2501.01059v1
• Date: Thu, 02 Jan 2025 05:07:06 GMT
• Title: Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
• Authors: Yanwen Huang, Yong Zhang, Ning Cheng, Zhitao Li, Shaojun Wang, Jing Xiao,
• Abstract summary: Large language models (LLMs) often suffer from context faithfulness hallucinations. We propose Dynamic Attention-Guided Context Decoding (DAGCD) DAGCD integrates attention distributions and uncertainty signals in a single-pass decoding process.
• Score: 26.51079570548107
• License:
• Abstract: Large language models (LLMs) often suffer from context faithfulness hallucinations, where outputs deviate from retrieved information due to insufficient context utilization and high output uncertainty. Our uncertainty evaluation experiments reveal a strong correlation between high uncertainty and hallucinations. We hypothesize that attention mechanisms encode signals indicative of contextual utilization, validated through probing analysis. Based on these insights, we propose Dynamic Attention-Guided Context Decoding (DAGCD), a lightweight framework that integrates attention distributions and uncertainty signals in a single-pass decoding process. Experiments across QA datasets demonstrate DAGCD's effectiveness, achieving significant improvements in faithfulness and robustness while maintaining computational efficiency.

Related papers

• Breaking Focus: Contextual Distraction Curse in Large Language Models [68.4534308805202]
  We investigate a critical vulnerability in Large Language Models (LLMs) This phenomenon arises when models fail to maintain consistent performance on questions modified with semantically coherent but irrelevant context. We propose an efficient tree-based search methodology to automatically generate CDV examples.
  arXiv  Detail & Related papers  (2025-02-03T18:43:36Z)
• Mitigating Hallucination for Large Vision Language Model by Inter-Modality Correlation Calibration Decoding [66.06337890279839]
  Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding for downstream multi-modal tasks. LVLMs still suffer from generating hallucinations in complex generation tasks, leading to inconsistencies between visual inputs and generated content. We propose an Inter-Modality Correlation Decoding (IMCCD) method to mitigate hallucinations in LVLMs in a training-free manner.
  arXiv  Detail & Related papers  (2025-01-03T17:56:28Z)
• From Uncertainty to Trust: Enhancing Reliability in Vision-Language Models with Uncertainty-Guided Dropout Decoding [6.115580421973011]
  Large vision-language models (LVLMs) demonstrate remarkable capabilities in multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. We propose Dropout Decoding, a novel inference-time approach that quantifies the uncertainty of visual tokens and selectively masks uncertain tokens to improve decoding. Evaluations on benchmarks including CHAIR, THRONE, and MMBench demonstrate that Dropout Decoding significantly reduces object hallucinations (OH) and enhances both reliability and quality of LVLM outputs.
  arXiv  Detail & Related papers  (2024-12-09T13:21:07Z)
• Maintaining Informative Coherence: Migrating Hallucinations in Large Language Models via Absorbing Markov Chains [6.920249042435973]
  Large Language Models (LLMs) are powerful tools for text generation, translation, and summarization. LLMs often suffer from hallucinations-instances where they fail to maintain the fidelity and coherence of contextual information. We propose a novel decoding strategy that leverages absorbing Markov chains to quantify the significance of contextual information.
  arXiv  Detail & Related papers  (2024-10-27T04:51:18Z)
• Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation [96.78845113346809]
  Retrieval-augmented language models (RALMs) have shown strong performance and wide applicability in knowledge-intensive tasks. This paper proposes SynCheck, a lightweight monitor that leverages fine-grained decoding dynamics to detect unfaithful sentences. We also introduce FOD, a faithfulness-oriented decoding algorithm guided by beam search for long-form retrieval-augmented generation.
  arXiv  Detail & Related papers  (2024-06-19T16:42:57Z)
• VALOR-EVAL: Holistic Coverage and Faithfulness Evaluation of Large Vision-Language Models [57.43276586087863]
  Large Vision-Language Models (LVLMs) suffer from hallucination issues, wherein the models generate plausible-sounding but factually incorrect outputs. Existing benchmarks are often limited in scope, focusing mainly on object hallucinations. We introduce a multi-dimensional benchmark covering objects, attributes, and relations, with challenging images selected based on associative biases.
  arXiv  Detail & Related papers  (2024-04-22T04:49:22Z)
• IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding [37.16880672402059]
  Over-reliance on linguistic priors has been identified as a key factor leading to hallucinations. We propose to alleviate this problem by introducing a novel image-biased decoding technique. Our method derives the next-token probability distribution by contrasting predictions from a conventional LVLM with those of an image-biased LVLM.
  arXiv  Detail & Related papers  (2024-02-28T16:57:22Z)
• Sometimes We Want Translationese [48.45003475966808]
  In some applications, faithfulness to the original (input) text is important to preserve. We propose a simple, novel way to quantify whether an NMT system exhibits robustness and faithfulness.
  arXiv  Detail & Related papers  (2021-04-15T17:39:47Z)
• Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery [85.36948722680822]
  We develop a context-aware mixture of deep models termed the alpha-beta network. We improve accuracy and F score by 10% by identifying high-level contexts. In order to ensure training stability, we have used a clustering-based pre-training in both public and in-house datasets.
  arXiv  Detail & Related papers  (2020-03-03T19:35:34Z)

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.