让大模型有目的地编造故事，填补历史空白中的社会缺失
Critical Confabulation: Can LLMs Hallucinate for Social Good?
- 用受控的虚构填补档案缺漏，重构被忽略群体的历史
- 在未公开文本基础上，模型能生成符合证据的连贯叙事
- 适合历史重建、社会正义类研究者使用
大模型会幻觉，但某些受控的虚构可带来社会价值。本文提出‘批判性虚构’概念（受文学与社会理论中‘批判性虚构’启发），利用大模型幻觉‘填补档案因社会政治不平等造成的遗漏’，为历史中的‘隐形人物’重构多元且基于证据的叙事。我们通过开放式叙事填空任务模拟这些缺漏：要求模型在源自未公开文本小说语料库的角色中心时间线上补全被遮蔽事件。评估了经过审计（无数据污染）、完全开源的OLMo-2系列模型，以及未经审计的开源与专有基线模型，在多种提示下生成可控且有用幻觉的能力。结果验证了大模型具备进行批判性虚构的基础叙事理解能力，并表明受控且明确指定的虚构可支持知识生产应用，同时避免推测与历史准确性之间的混淆。
原文摘要 · Abstract (English)
LLMs hallucinate, yet some confabulations can have social affordances if carefully bounded. We propose critical confabulation (inspired by critical fabulation from literary and social theory), the use of LLM hallucinations to "fill-in-the-gap" for omissions in archives due to social and political inequality, and reconstruct divergent yet evidence-bound narratives for history's ``hidden figures''. We simulate these gaps with an open-ended narrative cloze task: asking LLMs to generate a masked event in a character-centric timeline sourced from a novel corpus of unpublished texts. We evaluate audited (for data contamination), fully-open models (the OLMo-2 family) and unaudited open-weight and proprietary baselines under a range of prompts designed to elicit controlled and useful hallucinations. Our findings validate LLMs' foundational narrative understanding capabilities to perform critical confabulation, and show how controlled and well-specified hallucinations can support LLM applications for knowledge production without collapsing speculation into a lack of historical accuracy and fidelity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。