Conceptio › Archive › arXiv (All)
arXiv (All) open access

Mitigating Hallucination in Fictional Character Role-Play

Sadeq, Nafis et al. · 2024 · arxiv_all
arXiv (All) · Papers · 2024
Open Source ↗Direct PDF ↓
computation-and-language
Conceptio Open Archive

Analyze & explore related research in Conceptio

Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.

[2406.17260] Mitigating Hallucination in Fictional Character Role-Play Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2406.17260 (cs) [Submitted on 25 Jun 2024 ( v1 ), last revised 8 Nov 2024 (this version, v2)] Title: Mitigating Hallucination in Fictional Character Role-Play Authors: Nafis Sadeq , Zhouhang Xie , Byungkyu Kang , Prarit Lamba , Xiang Gao , Julian McAuley View a PDF of the paper titled Mitigating Hallucination in Fictional Character Role-Play, by Nafis Sadeq and 5 other authors View PDF HTML (experimental) Abstract: Role-playing has wide-ranging applications in customer support, embodied agents, and computational social science. The influence of parametric world knowledge of large language models (LLMs) often causes role-playing characters to act out of character and to hallucinate about things outside the scope of their knowledge. In this work, we focus on the evaluation and mitigation of hallucination in fictional character role-play. We introduce a dataset with over 2,000 characters and 72,000 interviews, including 18,000 adversarial questions. We propose RoleFact, a role-playing method that mitigates hallucination by modulating the influence of parametric knowledge using a pre-calibrated confidence threshold. Experiments show that the proposed method improves the factual precision of generated responses by 18% for adversarial questions with a 44% reduction in temporal hallucination for time-sensitive interviews. The code and the dataset are available at this https URL . Comments: EMNLP 2024 Camera Ready Subjects: Computation and Language (cs.CL) Cite as: arXiv:2406.17260 [cs.CL] (or arXiv:2406.17260v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2406.17260 Focus to learn more arXiv-issued DOI via DataCite Journal reference: Findings of the Association for Computational Linguistics: EMNLP 2024 Related DOI : https://doi.org/10.18653/v1/2024.findings-emnlp.846 Focus to learn more DOI(s) linking to related resources Submission history From: Nafis Sadeq [ view email ] [v1] Tue, 25 Jun 2024 03:56:33 UTC (743 KB) [v2] Fri, 8 Nov 2024 23:11:36 UTC (743 KB) Full-text links: Access Paper: View a PDF of the paper titled Mitigating Hallucination in Fictional Character Role-Play, by Nafis Sadeq and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2024-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

Record · ID 609744 · SHA-256 6c716f4e2190b501
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive