HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912405375680512 |
|---|---|
| author | Li, Qing Geng, Jiahui Chen, Zongxiong Zhu, Derui Wang, Yuxia Ma, Congbo Lyu, Chenyang Karray, Fakhri |
| author_facet | Li, Qing Geng, Jiahui Chen, Zongxiong Zhu, Derui Wang, Yuxia Ma, Congbo Lyu, Chenyang Karray, Fakhri |
| contents | In recent years, large language models (LLMs) have made remarkable advancements, yet hallucination, where models produce inaccurate or non-factual statements, remains a significant challenge for real-world deployment. Although current classification-based methods, such as SAPLMA, are highly efficient in mitigating hallucinations, they struggle when non-factual information arises in the early or mid-sequence of outputs, reducing their reliability. To address these issues, we propose Hallucination Detection-Neural Differential Equations (HD-NDEs), a novel method that systematically assesses the truthfulness of statements by capturing the full dynamics of LLMs within their latent space. Our approaches apply neural differential equations (Neural DEs) to model the dynamic system in the latent space of LLMs. Then, the sequence in the latent space is mapped to the classification space for truth assessment. The extensive experiments across five datasets and six widely used LLMs demonstrate the effectiveness of HD-NDEs, especially, achieving over 14% improvement in AUC-ROC on the True-False dataset compared to state-of-the-art techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00088 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs Li, Qing Geng, Jiahui Chen, Zongxiong Zhu, Derui Wang, Yuxia Ma, Congbo Lyu, Chenyang Karray, Fakhri Computation and Language Artificial Intelligence Machine Learning In recent years, large language models (LLMs) have made remarkable advancements, yet hallucination, where models produce inaccurate or non-factual statements, remains a significant challenge for real-world deployment. Although current classification-based methods, such as SAPLMA, are highly efficient in mitigating hallucinations, they struggle when non-factual information arises in the early or mid-sequence of outputs, reducing their reliability. To address these issues, we propose Hallucination Detection-Neural Differential Equations (HD-NDEs), a novel method that systematically assesses the truthfulness of statements by capturing the full dynamics of LLMs within their latent space. Our approaches apply neural differential equations (Neural DEs) to model the dynamic system in the latent space of LLMs. Then, the sequence in the latent space is mapped to the classification space for truth assessment. The extensive experiments across five datasets and six widely used LLMs demonstrate the effectiveness of HD-NDEs, especially, achieving over 14% improvement in AUC-ROC on the True-False dataset compared to state-of-the-art techniques. |
| title | HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2506.00088 |