# Critical Confabulation: Can LLMs Hallucinate for Social Good?

arXiv: https://arxiv.org/abs/2511.07722 · HTML: https://mlsanity.com/paper/2511.07722/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 78 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 29 of 29)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Detecting Pretraining Data from Large Language Models](https://mlsanity.com/paper/2310.16789/) (2023)
- [HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2305.11747/) (2023)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Proving Test Set Contamination in Black Box Language Models](https://mlsanity.com/paper/2310.17623/) (2023)
- [Do Membership Inference Attacks Work on Large Language Models?](https://mlsanity.com/paper/2402.07841/) (2024)
- [Time Travel in LLMs: Tracing Data Contamination in Large Language Models](https://mlsanity.com/paper/2308.08493/) (2023)
- [Investigating Data Contamination in Modern Benchmarks for Large Language Models](https://mlsanity.com/paper/2311.09783/) (2023)
- [What's In My Big Data?](https://mlsanity.com/paper/2310.20707/) (2023)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [LLM Dataset Inference: Did you train on my dataset?](https://mlsanity.com/paper/2406.06443/) (2024)
- [A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility](https://mlsanity.com/paper/2504.07086/) (2025)
- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play](https://mlsanity.com/paper/2405.06373/) (2024)
- [Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method](https://mlsanity.com/paper/2409.14781/) (2024)
- [Confabulation: The Surprising Value of Large Language Model Hallucinations](https://mlsanity.com/paper/2406.04175/) (2024)
- [TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models](https://mlsanity.com/paper/2311.17667/) (2023)
- [A Survey on Large Language Model Hallucination via a Creativity Perspective](https://mlsanity.com/paper/2402.06647/) (2024)
- [On Context Utilization in Summarization with Large Language Models](https://mlsanity.com/paper/2310.10570/) (2023)
- [Training Unbiased Diffusion Models From Biased Dataset](https://mlsanity.com/paper/2403.01189/) (2024)
- [Towards Reproducible LLM Evaluation: Quantifying Uncertainty in LLM Benchmark Scores](https://mlsanity.com/paper/2410.03492/) (2024)
- [Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation](https://mlsanity.com/paper/2408.15205/) (2024)
- [The Unreasonable Effectiveness of Eccentric Automatic Prompts](https://mlsanity.com/paper/2402.10949/) (2024)
- [Restoring Hebrew Diacritics Without a Dictionary](https://mlsanity.com/paper/2105.05209/) (2021)
- [Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses](https://mlsanity.com/paper/2409.14324/) (2024)
- [StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children's Story-Based Learning](https://mlsanity.com/paper/2311.09756/) (2023)
- [KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning](https://mlsanity.com/paper/2505.09825/) (2025)
- [A Dataset and Model for Realistic License Plate Deblurring](https://mlsanity.com/paper/2404.13677/) (2024)

## Built on by (most cited first, 2 of 2)

- [Why Slop Matters](https://mlsanity.com/paper/2601.06060/) (2025)
- [AI Virtue: What is "Good" Knowledge in the Age of Artificial Intelligence?](https://mlsanity.com/paper/2607.01776/) (2026)

## Abstract (arXiv)

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.