paper-with-me

홈 › Papers

Confabulation: The Surprising Value of Large Language Model Hallucinations

2024-06-06 · Peiqi Sui, Eamon Duede, Sophie Wu, Richard Jean So

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.

📄 PDF Abstract BibTeX arXiv:2406.04175

Code (0)

등록된 구현이 없습니다.

Tasks

HallucinationLanguage ModelingLanguage ModellingLarge Language ModelText Generation

Similar Papers 제목 키워드 기반

Critical Confabulation: Can LLMs Hallucinate for Social Good?

2025-11-11 · Peiqi Sui, Eamon Duede, Hoyt Long, Richard Jean So 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 hallucinatio…

Detecting hallucinations in large language models using semantic entropy

2024-06-19 · Nature 2024 6 · Sebastian Farquhar, Jannik Kossen, Lorenz Kuhn, Yarin Gal

Large language model (LLM) systems, such as ChatGPT1 or Gemini2, can show impressive reasoning and question-answering capabilities but often ‘hallucinate’ false outputs and unsubstantiated answers3,4. Answering unreliabl…

Large Language ModelQuestion Answering

Synthetic Fluency: Hallucinations, Confabulations, and the Creation of Irish Words in LLM-Generated Translations

2025-04-10 · Sheila Castilho, Zoe Fitzsimmons, Claire Holton, Aoife Mc Donagh

This study examines hallucinations in Large Language Model (LLM) translations into Irish, specifically focusing on instances where the models generate novel, non-existent words. We classify these hallucinations within ve…

Language ModelingLanguage ModellingLarge Language Model

Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection

2025-10-25 · Federica Gamba, Aman Sinha, Timothee Mickus, Raul Vazquez 외 arxiv

We introduce the CAP (Confabulations from ACL Publications) dataset, a multilingual resource for studying hallucinations in large language models (LLMs) within scientific text generation. CAP focuses on the scientific do…

Text Generation

Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation

2025-10-02 · Mykyta Ielanskyi, Kajetan Schweighofer, Lukas Aichberger, Sepp Hochreiter arxiv

Hallucinations are a common issue that undermine the reliability of large language models (LLMs). Recent studies have identified a specific subset of hallucinations, known as confabulations, which arise due to predictive…