paper-with-me

Papers

Lower Layer Matters: Alleviating Hallucination via Multi-Layer Fusion Contrastive Decoding with Truthfulness Refocused

2024-08-16 · Dingwei Chen, Feiteng Fang, Shiwen Ni, Feng Liang, Ruifeng Xu, Min Yang, Chengming Li

Large Language Models (LLMs) have demonstrated exceptional performance across various natural language processing tasks, yet they occasionally tend to yield content that factually inaccurate or discordant with the expected output, a phenomenon empirically referred to as "hallucination". To tackle this issue, recent works have investigated contrastive decoding between the original model and an amateur model with induced hallucination, which has shown promising results. Nonetheless, this method may undermine the output distribution of the original LLM caused by its coarse contrast and simplistic subtraction operation, potentially leading to errors in certain cases. In this paper, we introduce a novel contrastive decoding framework termed LOL (LOwer Layer Matters). Our approach involves concatenating the contrastive decoding of both the final and lower layers between the original model and the amateur model, thereby achieving multi-layer fusion to aid in the mitigation of hallucination. Additionally, we incorporate a truthfulness refocused module that leverages contextual guidance to enhance factual encoding, further capturing truthfulness during contrastive decoding. Extensive experiments conducted on two publicly available datasets illustrate that our proposed LOL framework can substantially alleviate hallucination while surpassing existing baselines in most cases. Compared with the best baseline, we improve by average 4.5 points on all metrics of TruthfulQA. The source code is coming soon.

📄 PDF Abstract BibTeX arXiv:2408.08769

Code (0)

등록된 구현이 없습니다.

Tasks

HallucinationTruthfulQA

Similar Papers 제목 키워드 기반

Alleviating Representational Shift for Continual Fine-tuning

2022-04-22 · Shibo Jie, Zhi-Hong Deng, Ziheng Li

We study a practical setting of continual learning: fine-tuning on a pre-trained model continually. Previous work has found that, when training on new tasks, the features (penultimate layer representations) of previous d…

Continual Learning

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs

2024-11-15 · Xiaofeng Zhang, Yihao Quan, Chaochen Gu, Chen Shen 외

The hallucination problem in multimodal large language models (MLLMs) remains a common issue. Although image tokens occupy a majority of the input sequence of MLLMs, there is limited research to explore the relationship …

Hallucination

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment

2025-12-04 · Kai-Po Chang, Wei-Yuan Cheng, Chi-Pin Huang, Fu-En Yang 외 arxiv

Recent advancement in multimodal LLMs (MLLMs) has demonstrated their remarkable capability to generate descriptive captions for input videos. However, these models suffer from factual inaccuracies in the generated descri…

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models

2025-10-10 · Hoigi Seo, Dong Un Kang, Hyunjin Cho, Joohoon Lee 외 arxiv

Large vision-language models (LVLMs), which integrate a vision encoder (VE) with a large language model, have achieved remarkable success across various tasks. However, there are still crucial challenges in LVLMs such as…

Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

2024-08-04 · Fushuo Huo, Wenchao Xu, Zhong Zhang, Haozhao Wang 외

While Large Vision-Language Models (LVLMs) have rapidly advanced in recent years, the prevalent issue known as the `hallucination' problem has emerged as a significant bottleneck, hindering their real-world deployments. …

Hallucination