# Valuable Hallucinations: Realizable Non-realistic Propositions

arXiv: https://arxiv.org/abs/2502.11113 · HTML: https://mlsanity.com/paper/2502.11113/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 56 references that are in the map.
- First posted on arXiv 16 Feb 2025.

## Builds on (most cited first, 30 of 32)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models](https://mlsanity.com/paper/2305.08322/) (2023)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation](https://mlsanity.com/paper/2310.03214/) (2023)
- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework](https://mlsanity.com/paper/2305.03268/) (2023)
- [Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding](https://mlsanity.com/paper/2104.08455/) (2021)
- [Assessing The Factual Accuracy of Generated Text](https://mlsanity.com/paper/1905.13322/) (2019)
- [The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey](https://mlsanity.com/paper/2104.14839/) (2021)
- [LLMs Will Always Hallucinate, and We Need to Live With This](https://mlsanity.com/paper/2409.05746/) (2024)
- [Induction Networks for Few-Shot Text Classification](https://mlsanity.com/paper/1902.10482/) (2019)
- [Diverse Few-Shot Text Classification with Multiple Metrics](https://mlsanity.com/paper/1805.07513/) (2018)
- [Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks](https://mlsanity.com/paper/1911.03863/) (2019)
- [Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks](https://mlsanity.com/paper/1908.10423/) (2019)
- [Confabulation: The Surprising Value of Large Language Model Hallucinations](https://mlsanity.com/paper/2406.04175/) (2024)
- [Deficiency of Large Language Models in Finance: An Empirical Examination of Hallucination](https://mlsanity.com/paper/2311.15548/) (2023)
- [Out-of-Domain Detection for Low-Resource Text Classification Tasks](https://mlsanity.com/paper/1909.05357/) (2019)
- [Hallucination is the last thing you need](https://mlsanity.com/paper/2306.11520/) (2023)
- [Looking Beyond Sentence-Level Natural Language Inference for Downstream Tasks](https://mlsanity.com/paper/2009.09099/) (2020)

## Abstract (arXiv)

This paper introduces the first formal definition of valuable hallucinations in large language models (LLMs), addressing a gap in the existing literature. We provide a systematic definition and analysis of hallucination value, proposing methods for enhancing the value of hallucinations. In contrast to previous works, which often treat hallucinations as a broad flaw, we focus on the potential value that certain types of hallucinations can offer in specific contexts. Hallucinations in LLMs generally refer to the generation of unfaithful, fabricated, inconsistent, or nonsensical content. Rather than viewing all hallucinations negatively, this paper gives formal representations and manual judgments of "valuable hallucinations" and explores how realizable non-realistic propositions--ideas that are not currently true but could be achievable under certain conditions--can have constructive value. We present experiments using the Qwen2.5 model and HalluQA dataset, employing ReAct prompting (which involves reasoning, confidence assessment, and answer verification) to control and optimize hallucinations. Our findings show that ReAct prompting results in a 5.12% reduction in overall hallucinations and an increase in the proportion of valuable hallucinations from 6.45% to 7.92%. These results demonstrate that systematically controlling hallucinations can improve their usefulness without compromising factual reliability.