Critical Confabulation: Can LLMs Hallucinate for Social Good?

TL;DR

This paper explores how large language models can ethically generate plausible historical narratives to fill gaps caused by social and political biases, supporting social good without compromising accuracy.

Contribution

It introduces the concept of critical confabulation, demonstrating how LLMs can generate evidence-bound narratives to address historical omissions and biases.

Findings

LLMs can perform critical confabulation to reconstruct missing historical narratives.

Controlled hallucinations can support knowledge production without losing fidelity.

Validated LLMs' ability to generate plausible, evidence-based historical fill-ins.

Abstract

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cloze task: asking LLMs to generate a masked event in a character-centric timeline sourced from a novel corpus of unpublished texts.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.