Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908749648625664 |
|---|---|
| author | Hao, Jinbo Yang, Kai Su, Qingzhen Chen, Yang Li, Yifan Jiang, Chao |
| author_facet | Hao, Jinbo Yang, Kai Su, Qingzhen Chen, Yang Li, Yifan Jiang, Chao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_02739 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning Hao, Jinbo Yang, Kai Su, Qingzhen Chen, Yang Li, Yifan Jiang, Chao Computation and Language 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. |
| title | Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.02739 |