超越档案：从表层事实到 LLM 中的深度人格模拟
Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs
AI总结：
本文提出 CharacterBot，结合鲁迅 17 部杂文集设计四类训练任务，并通过 CharLoRA 多专家机制模拟其语言与深层思维，实验显示其显著优于基线。
摘要：
以往用于大语言模型（LLM）人格模拟的方法通常依赖学习基本的传记信息，或使用有限的角色扮演对话数据集来捕捉人物的回应。然而，对一个人的整体性表征不应止于表层事实或对话，还应深入其思想与思维。在本研究中，我们提出 CharacterBot，该模型旨在复现人物文本作品中所体现的语言模式和独特思维模式。我们以中国著名作家鲁迅为案例，基于其 17 部杂文集提出四项训练任务。其中包括一项专注于掌握外部语言结构和知识的预训练任务，以及三项微调任务：多项选择问答、生成式问答和风格迁移；每项任务都使 LLM 与鲁迅的内在构思和写作风格保持一致。为优化跨任务学习，我们提出 CharLoRA 参数更新机制，其中一个通用语言风格专家与其他任务特定专家协作，以更好地学习语言风格并理解深层思想。我们在三项任务上评估 CharacterBot 的语言准确性和观点理解能力，结果表明，在我们调整后的指标上，它显著优于基线模型。我们希望这项工作能启发未来关于深度人物人格模拟 LLM 的研究，同时重视伦理标准的重要性。
英文摘要：
Previous approaches to persona simulation large language models (LLMs) have typically relied on learning basic biographical information, or using limited role-play dialogue datasets to capture a character's responses. However, a holistic representation of an individual goes beyond surface-level facts or conversations to deeper thoughts and thinking. In this work, we introduce CharacterBot, a model designed to replicate both the linguistic patterns and distinctive thought patterns as manifested in the textual works of a character. Using Lu Xun, a renowned Chinese writer as a case study, we propose four training tasks derived from his 17 essay collections. These include a pre-training task focused on mastering external linguistic structures and knowledge, as well as three fine-tuning tasks: multiple-choice question answering, generative question answering, and style transfer, each aligning the LLM with Lu Xun's internal ideation and writing style. To optimize learning across these tasks, we introduce a CharLoRA parameter updating mechanism, where a general linguistic style expert collaborates with other task-specific experts to better study both the language style and the understanding of deeper thoughts. We evaluate CharacterBot on three tasks for linguistic accuracy and opinion comprehension, demonstrating that it significantly outperforms the baselines on our adapted metrics. We hope this work inspires future research on deep character persona simulation LLMs while considering the importance of ethical standards.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
