BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929726559354880 |
|---|---|
| author | Liu, Yuxuan Sun, Hongda Guo, Wenya Xiao, Xinyan Mao, Cunli Yu, Zhengtao Yan, Rui |
| author_facet | Liu, Yuxuan Sun, Hongda Guo, Wenya Xiao, Xinyan Mao, Cunli Yu, Zhengtao Yan, Rui |
| contents | Complex claim fact-checking performs a crucial role in disinformation detection. However, existing fact-checking methods struggle with claim vagueness, specifically in effectively handling latent information and complex relations within claims. Moreover, evidence redundancy, where nonessential information complicates the verification process, remains a significant issue. To tackle these limitations, we propose Bilateral Defusing Verification (BiDeV), a novel fact-checking working-flow framework integrating multiple role-played LLMs to mimic the human-expert fact-checking process. BiDeV consists of two main modules: Vagueness Defusing identifies latent information and resolves complex relations to simplify the claim, and Redundancy Defusing eliminates redundant content to enhance the evidence quality. Extensive experimental results on two widely used challenging fact-checking benchmarks (Hover and Feverous-s) demonstrate that our BiDeV can achieve the best performance under both gold and open settings. This highlights the effectiveness of BiDeV in handling complex claims and ensuring precise fact-checking |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16181 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking Liu, Yuxuan Sun, Hongda Guo, Wenya Xiao, Xinyan Mao, Cunli Yu, Zhengtao Yan, Rui Computation and Language Artificial Intelligence Complex claim fact-checking performs a crucial role in disinformation detection. However, existing fact-checking methods struggle with claim vagueness, specifically in effectively handling latent information and complex relations within claims. Moreover, evidence redundancy, where nonessential information complicates the verification process, remains a significant issue. To tackle these limitations, we propose Bilateral Defusing Verification (BiDeV), a novel fact-checking working-flow framework integrating multiple role-played LLMs to mimic the human-expert fact-checking process. BiDeV consists of two main modules: Vagueness Defusing identifies latent information and resolves complex relations to simplify the claim, and Redundancy Defusing eliminates redundant content to enhance the evidence quality. Extensive experimental results on two widely used challenging fact-checking benchmarks (Hover and Feverous-s) demonstrate that our BiDeV can achieve the best performance under both gold and open settings. This highlights the effectiveness of BiDeV in handling complex claims and ensuring precise fact-checking |
| title | BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.16181 |