Language Models can Evaluate Themselves via Probability Discrepancy

Language Models can Evaluate Themselves via Probability Discrepancy Tingyu Xia author Bowen Yu author Yuan Wu author Yi Chang author Chang Zhou author 2024-08 text Findings of the Association for Computational Linguistics: ACL 2024 Lun-Wei Ku editor Andre Martins editor Vivek Srikumar editor Association for Computational Linguistics Bangkok, Thailand conference publication xia-etal-2024-language 10.18653/v1/2024.findings-acl.291 https://aclanthology.org/2024.findings-acl.291/ 2024-08 4889 4901