KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908677985796096 |
|---|---|
| author | Liu, Zhongxin Wang, Zhiwei Niu, Jun Li, Ying Sun, Hongyu Xu, Meng Wang, He Wu, Gaofei Zhang, Yuqing |
| author_facet | Liu, Zhongxin Wang, Zhiwei Niu, Jun Li, Ying Sun, Hongyu Xu, Meng Wang, He Wu, Gaofei Zhang, Yuqing |
| contents | The emergence of large language models (LLMs) has significantly advanced the development of natural language processing (NLP), especially in text generation tasks like question answering. However, model hallucinations remain a major challenge in natural language generation (NLG) tasks due to their complex causes. We systematically expand on the causes of factual hallucinations from the perspective of knowledge shortcuts, analyzing hallucinations arising from correct and defect-free data and demonstrating that knowledge-shortcut hallucinations are prevalent in generative models. To mitigate this issue, we propose a high similarity pruning algorithm at the data preprocessing level to reduce spurious correlations in the data. Additionally, we design a specific detection method for knowledge-shortcut hallucinations to evaluate the effectiveness of our mitigation strategy. Experimental results show that our approach effectively reduces knowledge-shortcut hallucinations, particularly in fine-tuning tasks, without negatively impacting model performance in question answering. This work introduces a new paradigm for mitigating specific hallucination issues in generative models, enhancing their robustness and reliability in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19482 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models Liu, Zhongxin Wang, Zhiwei Niu, Jun Li, Ying Sun, Hongyu Xu, Meng Wang, He Wu, Gaofei Zhang, Yuqing Computation and Language I.2.7; I.2.6 The emergence of large language models (LLMs) has significantly advanced the development of natural language processing (NLP), especially in text generation tasks like question answering. However, model hallucinations remain a major challenge in natural language generation (NLG) tasks due to their complex causes. We systematically expand on the causes of factual hallucinations from the perspective of knowledge shortcuts, analyzing hallucinations arising from correct and defect-free data and demonstrating that knowledge-shortcut hallucinations are prevalent in generative models. To mitigate this issue, we propose a high similarity pruning algorithm at the data preprocessing level to reduce spurious correlations in the data. Additionally, we design a specific detection method for knowledge-shortcut hallucinations to evaluate the effectiveness of our mitigation strategy. Experimental results show that our approach effectively reduces knowledge-shortcut hallucinations, particularly in fine-tuning tasks, without negatively impacting model performance in question answering. This work introduces a new paradigm for mitigating specific hallucination issues in generative models, enhancing their robustness and reliability in real-world applications. |
| title | KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models |
| topic | Computation and Language I.2.7; I.2.6 |
| url | https://arxiv.org/abs/2503.19482 |