Hallucinated Span Detection with Multi-View Attention Features
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911154463309824 |
|---|---|
| author | Ogasa, Yuya Arase, Yuki |
| author_facet | Ogasa, Yuya Arase, Yuki |
| contents | This study addresses the problem of hallucinated span detection in the outputs of large language models. It has received less attention than output-level hallucination detection despite its practical importance. Prior work has shown that attentions often exhibit irregular patterns when hallucinations occur. Motivated by these findings, we extract features from the attention matrix that provide complementary views capturing (a) whether certain tokens are influential or ignored, (b) whether attention is biased toward specific subsets, and (c) whether a token is generated referring to a narrow or broad context, in the generation. These features are input to a Transformer-based classifier to conduct sequential labelling to identify hallucinated spans. Experimental results indicate that the proposed method outperforms strong baselines on hallucinated span detection with longer input contexts, such as data-to-text and summarisation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04335 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hallucinated Span Detection with Multi-View Attention Features Ogasa, Yuya Arase, Yuki Computation and Language Artificial Intelligence Machine Learning This study addresses the problem of hallucinated span detection in the outputs of large language models. It has received less attention than output-level hallucination detection despite its practical importance. Prior work has shown that attentions often exhibit irregular patterns when hallucinations occur. Motivated by these findings, we extract features from the attention matrix that provide complementary views capturing (a) whether certain tokens are influential or ignored, (b) whether attention is biased toward specific subsets, and (c) whether a token is generated referring to a narrow or broad context, in the generation. These features are input to a Transformer-based classifier to conduct sequential labelling to identify hallucinated spans. Experimental results indicate that the proposed method outperforms strong baselines on hallucinated span detection with longer input contexts, such as data-to-text and summarisation tasks. |
| title | Hallucinated Span Detection with Multi-View Attention Features |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.04335 |