LLM-based Corroborating and Refuting Evidence Retrieval for Scientific Claim Verification
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_ | 1866916649456631808 |
|---|---|
| author | Wang, Siyuan Foulds, James R. Gani, Md Osman Pan, Shimei |
| author_facet | Wang, Siyuan Foulds, James R. Gani, Md Osman Pan, Shimei |
| contents | In this paper, we introduce CIBER (Claim Investigation Based on Evidence Retrieval), an extension of the Retrieval-Augmented Generation (RAG) framework designed to identify corroborating and refuting documents as evidence for scientific claim verification. CIBER addresses the inherent uncertainty in Large Language Models (LLMs) by evaluating response consistency across diverse interrogation probes. By focusing on the behavioral analysis of LLMs without requiring access to their internal information, CIBER is applicable to both white-box and black-box models. Furthermore, CIBER operates in an unsupervised manner, enabling easy generalization across various scientific domains. Comprehensive evaluations conducted using LLMs with varying levels of linguistic proficiency reveal CIBER's superior performance compared to conventional RAG approaches. These findings not only highlight the effectiveness of CIBER but also provide valuable insights for future advancements in LLM-based scientific claim verification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07937 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-based Corroborating and Refuting Evidence Retrieval for Scientific Claim Verification Wang, Siyuan Foulds, James R. Gani, Md Osman Pan, Shimei Artificial Intelligence In this paper, we introduce CIBER (Claim Investigation Based on Evidence Retrieval), an extension of the Retrieval-Augmented Generation (RAG) framework designed to identify corroborating and refuting documents as evidence for scientific claim verification. CIBER addresses the inherent uncertainty in Large Language Models (LLMs) by evaluating response consistency across diverse interrogation probes. By focusing on the behavioral analysis of LLMs without requiring access to their internal information, CIBER is applicable to both white-box and black-box models. Furthermore, CIBER operates in an unsupervised manner, enabling easy generalization across various scientific domains. Comprehensive evaluations conducted using LLMs with varying levels of linguistic proficiency reveal CIBER's superior performance compared to conventional RAG approaches. These findings not only highlight the effectiveness of CIBER but also provide valuable insights for future advancements in LLM-based scientific claim verification. |
| title | LLM-based Corroborating and Refuting Evidence Retrieval for Scientific Claim Verification |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.07937 |