DiVA: Fine-grained Factuality Verification with Agentic-Discriminative Verifier
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915712749010944 |
|---|---|
| author | Huang, Hui Yang, Muyun Arase, Yuki |
| author_facet | Huang, Hui Yang, Muyun Arase, Yuki |
| contents | Despite the significant advancements of Large Language Models (LLMs), their factuality remains a critical challenge, fueling growing interest in factuality verification. Existing research on factuality verification primarily conducts binary judgments (e.g., correct or incorrect), which fails to distinguish varying degrees of error severity. This limits its utility for applications such as fine-grained evaluation and preference optimization. To bridge this gap, we propose the Agentic Discriminative Verifier (DiVA), a hybrid framework that synergizes the agentic search capabilities of generative models with the precise scoring aptitude of discriminative models. We also construct a new benchmark, FGVeriBench, as a robust testbed for fine-grained factuality verification. Experimental results on FGVeriBench demonstrate that our DiVA significantly outperforms existing methods on factuality verification for both general and multi-hop questions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03605 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DiVA: Fine-grained Factuality Verification with Agentic-Discriminative Verifier Huang, Hui Yang, Muyun Arase, Yuki Computation and Language Despite the significant advancements of Large Language Models (LLMs), their factuality remains a critical challenge, fueling growing interest in factuality verification. Existing research on factuality verification primarily conducts binary judgments (e.g., correct or incorrect), which fails to distinguish varying degrees of error severity. This limits its utility for applications such as fine-grained evaluation and preference optimization. To bridge this gap, we propose the Agentic Discriminative Verifier (DiVA), a hybrid framework that synergizes the agentic search capabilities of generative models with the precise scoring aptitude of discriminative models. We also construct a new benchmark, FGVeriBench, as a robust testbed for fine-grained factuality verification. Experimental results on FGVeriBench demonstrate that our DiVA significantly outperforms existing methods on factuality verification for both general and multi-hop questions. |
| title | DiVA: Fine-grained Factuality Verification with Agentic-Discriminative Verifier |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.03605 |