Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration? - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Ziming Wang, Zeyu Shi, Haoyi Zhou, Shiqi Gao, Qingyun Sun, Jianxin Li 0002. Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?. In Wanxiang Che, Joyce Nabende, Ekaterina Shutova, Mohammad Taher Pilehvar, editors, Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025, Vienna, Austria, July 27 - August 1, 2025. pages 14830-14853, Association for Computational Linguistics, 2025. [doi]

The following publications are possibly variants of this publication:

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning AttacksSamuele Poppi, Zheng Xin Yong, Yifei He, Bobbie Chern, Han Zhao 0002, Aobo Yang, Jianfeng Chi. naacl 2025: 2358-2372 [doi]

Towards Context-Robust LLMs: A Gated Representation Fine-tuning ApproachShenglai Zeng, Pengfei He, Kai Guo 0003, Tianqi Zheng, Hanqing Lu, Yue Xing 0002, Hui Liu 0031. acl 2025: 10262-10276 [doi]

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit AnalysisXu Wang 0033, Yan Hu, Wenyu Du, Reynold Cheng, Benyou Wang, Difan Zou. icml 2025: [doi]

FINE: LLM Prompt Tuning Fused with Internal and External Knowledge for EAEXin Guo, Le Zhang, Qian Chen 0023, Suge Wang, Jian Liao, Jianxing Zheng. ijcnn 2025: 1-8 [doi]

BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning ScenariosWei Li, Lujun Li 0001, Mark G. Lee, Shengjie Sun, Lei Zhang, Wei Xue, Yike Guo. acl 2025: 138-152 [doi]

runs on WebDSL