Article Instance

HTTP 200 OK
Allow: GET
Content-Type: application/json
Vary: Accept

{
    "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/"
        }
    ]
}