Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.06596 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909775929802752 |
|---|---|
| author | Tong, Xin Lin, Zhi Wang, Jingya Jin, Bo |
| author_facet | Tong, Xin Lin, Zhi Wang, Jingya Jin, Bo |
| contents | Large Language Models (LLMs) often produce hallucinations in retrieval-augmented or long-context generation, even when relevant evidence is present. This stems from two issues: head importance is treated as input-agnostic, and raw attention weights poorly reflect each token's true contribution. We present HAVE (Head-Adaptive Gating and ValuE Calibration), a parameter-free decoding framework that directly addresses both challenges. HAVE introduces head-adaptive gating, which performs instance-level soft reweighing of attention heads, and value calibration, which augments attention with the magnitude of value vectors to approximate write-back contribution. Together, these modules construct token-level evidence aligned with model updates and fuse it with the LM distribution through a lightweight uncertainty-scaled policy. HAVE requires no finetuning and operates in a single forward pass, making it efficient and broadly applicable. Experiments across multiple QA benchmarks and LLM families demonstrate that HAVE consistently reduces hallucinations and outperforms strong baselines, including DAGCD, with modest overhead. The framework is transparent, reproducible, and readily integrates with off-the-shelf LLMs, advancing trustworthy generation in real-world settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06596 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models Tong, Xin Lin, Zhi Wang, Jingya Jin, Bo Computation and Language Artificial Intelligence Large Language Models (LLMs) often produce hallucinations in retrieval-augmented or long-context generation, even when relevant evidence is present. This stems from two issues: head importance is treated as input-agnostic, and raw attention weights poorly reflect each token's true contribution. We present HAVE (Head-Adaptive Gating and ValuE Calibration), a parameter-free decoding framework that directly addresses both challenges. HAVE introduces head-adaptive gating, which performs instance-level soft reweighing of attention heads, and value calibration, which augments attention with the magnitude of value vectors to approximate write-back contribution. Together, these modules construct token-level evidence aligned with model updates and fuse it with the LM distribution through a lightweight uncertainty-scaled policy. HAVE requires no finetuning and operates in a single forward pass, making it efficient and broadly applicable. Experiments across multiple QA benchmarks and LLM families demonstrate that HAVE consistently reduces hallucinations and outperforms strong baselines, including DAGCD, with modest overhead. The framework is transparent, reproducible, and readily integrates with off-the-shelf LLMs, advancing trustworthy generation in real-world settings. |
| title | HAVE: Head-Adaptive Gating and ValuE Calibration for Hallucination Mitigation in Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2509.06596 |