{"pk":49741,"title":"Two Stage Psychology-Guided Fine-Grained Editing and Sampling Approach for Mitigating Hallucination in Large Language Models","subtitle":null,"abstract":"The hallucination issue in large language models (LLMs) significantly restricts their application in high-stakes domains such as healthcare, cognitive science and law. Existing approaches primarily focus on data optimization or decoding strategies but lack a fine-grained analysis of the underlying mechanisms of hallucinations. This paper proposes a psychology-guided two-stage fine-grained editing and sampling framework (PGFES), which, for the first time, introduces psychological classifications of hallucinations into LLM optimization. Firstly, an attention-augmented MLP probe is designed to identify \"truthfulness directions\" corresponding to different hallucination types through feature channel reweighting, enabling fine-grained editing of the model's internal representations during inference. Then, a dynamic weighting mechanism based on Jaccard similarity is employed to compute the weights of multi-path edited outputs, achieving adaptive sampling. Experiments demonstrate that the optimization method incorporating psychology-related concepts improves truthfulness by 20.4% on the TruthfulQA open-domain question-answering task compared to baseline models and exhibits strong generalization across cross-domain datasets.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"Artificial Intelligence; Computer Science; Language Production; Natural Language Processing"}],"section":"Papers with Poster Presentation","is_remote":true,"remote_url":"https://escholarship.org/uc/item/0gn8m1qq","frozenauthors":[{"first_name":"Lei","middle_name":"","last_name":"Chen","name_suffix":"","institution":"School of Information and Software Engineering, University of Electronic Science and Technology of China","department":""},{"first_name":"Xiaohua","middle_name":"","last_name":"Wu","name_suffix":"","institution":"University of Electronic Science and technology","department":""},{"first_name":"Zihan","middle_name":"","last_name":"Xiong","name_suffix":"","institution":"School of Information and Software Engineering, University of Electronic Science and Technology of China","department":""},{"first_name":"Xuanshuo","middle_name":"","last_name":"Kang","name_suffix":"","institution":"School of Information and Software Engineering, University of Electronic Science and Technology of China","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2025-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/49741/galley/37703/download/"}]}