paper-with-me

홈 › Papers

Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning

2026-01-06 · Jinbo Hao, Kai Yang, Qingzhen Su, Yang Chen, Yifan Li, Chao Jiang arxiv

To address hallucination issues in large language models (LLMs), this paper proposes a method for mitigating prompt-induced hallucinations. Building on a knowledge distillation chain-style model, we introduce a code module to guide knowledge-graph exploration and incorporate code as part of the chain-of-thought prompt, forming an external knowledge input that provides more accurate and structured information to the model. Based on this design, we develop an improved knowledge distillation chain-style model and leverage it to analyze and constrain the reasoning process of LLMs, thereby improving inference accuracy. We empirically evaluate the proposed approach using GPT-4 and LLaMA-3.3 on multiple public datasets. Experimental results demonstrate that incorporating code modules significantly enhances the model's ability to capture contextual information and effectively mitigates prompt-induced hallucinations. Specifically, HIT@1, HIT@3, and HIT@5 improve by 15.64%, 13.38%, and 13.28%, respectively. Moreover, the proposed method achieves HIT@1, HIT@3, and HIT@5 scores exceeding 95% across several evaluation settings. These results indicate that the proposed approach substantially reduces hallucination behavior while improving the accuracy and verifiability of large language models.

📄 PDF Abstract BibTeX arXiv:2601.02739

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Similar Papers 제목 키워드 기반

CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement

2025-10-14 · Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee arxiv

Recent advancements in large language models (LLMs) highlight their fluency in generating responses to diverse prompts. However, these models sometimes generate plausible yet incorrect ``hallucinated" facts, undermining …

CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding

2025-09-27 · Xi Zhang, Zaiqiao Meng, Jake Lever, Edmond S. L. Ho arxiv

Multimodal large language models (MLLMs) have recently achieved remarkable progress in radiology by integrating visual perception with natural language understanding. However, they often generate clinically unsupported d…

Natural Language Understanding

Exploring and Mitigating Fawning Hallucinations in Large Language Models

2025-08-31 · Zixuan Shangguan, Yanjie Dong, Lanjun Wang, Xiaoyi Fan 외 arxiv

Large language models (LLMs) have demonstrated exceptional proficiency in language understanding. However, when LLMs align their outputs with deceptive and/or misleading prompts, the generated responses could deviate fro…

Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance

2026-02-01 · Xinrong Chen, Xu Chu, Yingmin Qiu, Hengyuan Zhang 외 arxiv

Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and often produce hallucinations. Hallucinat…

Visual Grounding

Mechanisms of Prompt-Induced Hallucination in Vision-Language Models

2026-01-08 · William Rudman, Michal Golovanevsky, Dana Arad, Yonatan Belinkov 외 arxiv

Large vision-language models (VLMs) are highly capable, yet often hallucinate by favoring textual prompts over visual evidence. We study this failure mode in a controlled object-counting setting, where the prompt oversta…