# Confabulation: The Surprising Value of Large Language Model Hallucinations

arXiv: https://arxiv.org/abs/2406.04175 · HTML: https://mlsanity.com/paper/2406.04175/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 81 references that are in the map.
- First posted on arXiv 6 Jun 2024.

## Builds on (most cited first, 27 of 27)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples](https://mlsanity.com/paper/2310.01469/) (2023)
- [Med-HALT: Medical Domain Hallucination Test for Large Language Models](https://mlsanity.com/paper/2307.15343/) (2023)
- [On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?](https://mlsanity.com/paper/2204.07931/) (2022)
- [Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2109.09784/) (2021)
- [FaithDial: A Faithful Benchmark for Information-Seeking Dialogue](https://mlsanity.com/paper/2204.10757/) (2022)
- [Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?](https://mlsanity.com/paper/2312.03729/) (2023)
- [Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination](https://mlsanity.com/paper/2311.15548/) (2023)
- [Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination](https://mlsanity.com/paper/2305.12256/) (2023)
- [DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations](https://mlsanity.com/paper/2203.09711/) (2022)
- [HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions](https://mlsanity.com/paper/2304.00387/) (2023)
- [The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination](https://mlsanity.com/paper/2304.14347/) (2023)
- [Hallucination Detection and Hallucination Mitigation: An Investigation](https://mlsanity.com/paper/2401.08358/) (2024)
- [Where Do People Tell Stories Online? Story Detection Across Online Communities](https://mlsanity.com/paper/2311.09675/) (2023)
- [Hallucination Improves the Performance of Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2307.12168/) (2023)
- [Hallucination is the last thing you need](https://mlsanity.com/paper/2306.11520/) (2023)
- [Deep Learning Opacity in Scientific Discovery](https://mlsanity.com/paper/2206.00520/) (2022)
- [From human-centered to social-centered artificial intelligence: Assessing ChatGPT's impact through disruptive events](https://mlsanity.com/paper/2306.00227/) (2023)
- [Predicting challenge moments from students' discourse: A comparison of GPT-4 to two traditional natural language processing approaches](https://mlsanity.com/paper/2401.01692/) (2024)
- [User-Controlled Knowledge Fusion in Large Language Models: Balancing Creativity and Hallucination](https://mlsanity.com/paper/2307.16139/) (2023)
- [Multi-Object Tracking with Hallucinated and Unlabeled Videos](https://mlsanity.com/paper/2108.08836/) (2021)
- [The Creative Frontier of Generative AI: Managing the Novelty-Usefulness Tradeoff](https://mlsanity.com/paper/2306.03601/) (2023)
- [Oil & Water? Diffusion of AI Within and Across Scientific Fields](https://mlsanity.com/paper/2405.15828/) (2024)
- [Correction with Backtracking Reduces Hallucination in Summarization](https://mlsanity.com/paper/2310.16176/) (2023)

## Built on by (most cited first, 30 of 43)

- [ELEPHANT: Measuring and understanding social sycophancy in LLMs](https://mlsanity.com/paper/2505.13995/) (2025)
- [StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization](https://mlsanity.com/paper/2410.08815/) (2024)
- [DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing](https://mlsanity.com/paper/2410.12189/) (2024)
- [Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges](https://mlsanity.com/paper/2409.02387/) (2024)
- [Technological folie `a deux: Feedback Loops Between AI Chatbots and Mental Illness](https://mlsanity.com/paper/2507.19218/) (2025)
- [Thinking beyond the anthropomorphic paradigm benefits LLM research](https://mlsanity.com/paper/2502.09192/) (2025)
- [Accommodation and Epistemic Vigilance: A Pragmatic Account of Why LLMs Fail to Challenge Harmful Beliefs](https://mlsanity.com/paper/2601.04435/) (2026)
- [Provocations from the Humanities for Generative AI Research](https://mlsanity.com/paper/2502.19190/) (2025)
- [On Classification with Large Language Models in Cultural Analytics](https://mlsanity.com/paper/2410.12029/) (2024)
- [CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges](https://mlsanity.com/paper/2603.11863/) (2026)
- [Why Slop Matters](https://mlsanity.com/paper/2601.06060/) (2025)
- [Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models](https://mlsanity.com/paper/2508.08139/) (2025)
- [Narrative Theory-Driven LLM Methods for Automatic Story Generation and Understanding: A Survey](https://mlsanity.com/paper/2602.15851/) (2026)
- [KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning](https://mlsanity.com/paper/2505.09825/) (2025)
- [ReFACT: A Benchmark for Scientific Confabulation Detection with Positional Error Annotations](https://mlsanity.com/paper/2509.25868/) (2025)
- [PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models](https://mlsanity.com/paper/2512.19350/) (2025)
- [Towards a Science Exocortex](https://mlsanity.com/paper/2406.17809/) (2024)
- [Memory Helps, but Confabulation Misleads: Understanding Streaming Events in Videos with MLLMs](https://mlsanity.com/paper/2502.15457/) (2025)
- [Semantic Calibration Prevails Where Token Confidence Fails: Benchmarking Long-Form Scientific QA](https://mlsanity.com/paper/2602.00279/) (2026)
- [The Dynamics of Delusion: Modeling Bidirectional False Belief Amplification in Human-Chatbot Dialogue](https://mlsanity.com/paper/2604.25096/) (2026)
- [Synthetic Fluency: Hallucinations, Confabulations, and the Creation of Irish Words in LLM-Generated Translations](https://mlsanity.com/paper/2504.07680/) (2025)
- [MetaRAG: Metamorphic Testing for Hallucination Detection in RAG Systems](https://mlsanity.com/paper/2509.09360/) (2025)
- [Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations](https://mlsanity.com/paper/2510.17256/) (2025)
- [Critical Confabulation: Can LLMs Hallucinate for Social Good?](https://mlsanity.com/paper/2511.07722/) (2025)
- [The Homogenization Problem in LLMs: Towards Meaningful Diversity in AI Safety](https://mlsanity.com/paper/2601.06116/) (2026)
- [Structure Guided Retrieval-Augmented Generation for Factual Queries](https://mlsanity.com/paper/2604.22843/) (2026)
- [AiBAT: Artificial Intelligence/Instructions for Build, Assembly, and Test](https://mlsanity.com/paper/2410.02955/) (2024)
- [OAEI-LLM-T: A TBox Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching](https://mlsanity.com/paper/2503.21813/) (2025)
- [Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values](https://mlsanity.com/paper/2506.13774/) (2025)
- [Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries](https://mlsanity.com/paper/2509.22202/) (2025)

## Abstract (arXiv)

This paper presents a systematic defense of large language model (LLM) hallucinations or 'confabulations' as a potential resource instead of a categorically negative pitfall. The standard view is that confabulations are inherently problematic and AI research should eliminate this flaw. In this paper, we argue and empirically demonstrate that measurable semantic characteristics of LLM confabulations mirror a human propensity to utilize increased narrativity as a cognitive resource for sense-making and communication. In other words, it has potential value. Specifically, we analyze popular hallucination benchmarks and reveal that hallucinated outputs display increased levels of narrativity and semantic coherence relative to veridical outputs. This finding reveals a tension in our usually dismissive understandings of confabulation. It suggests, counter-intuitively, that the tendency for LLMs to confabulate may be intimately associated with a positive capacity for coherent narrative-text generation.