# DecoPrompt : Decoding Prompts Reduces Hallucinations when Large Language Models Meet False Premises

arXiv: https://arxiv.org/abs/2411.07457 · HTML: https://mlsanity.com/paper/2411.07457/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2024.

## Built on by (most cited first, 5 of 5)

- [Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning](https://mlsanity.com/paper/2504.06438/) (2025)
- [HALT: Hallucination Assessment via Log-probs as Time series](https://mlsanity.com/paper/2602.02888/) (2026)
- [Judge Before Answer: Can MLLM Discern the False Premise in Question?](https://mlsanity.com/paper/2510.10965/) (2025)
- [Hallucination-Resistant, Domain-Specific Research Assistant with Self-Evaluation and Vector-Grounded Retrieval](https://mlsanity.com/paper/2510.02326/) (2025)
- [Verification Trap: Understanding Test-Time Selection Failures under False Premises in Code Generation](https://mlsanity.com/paper/2610.05170/) (2026)

## Abstract (arXiv)

While large language models (LLMs) have demonstrated increasing power, they have also called upon studies on their hallucinated outputs that deviate from factually correct statements. In this paper, we focus on one important scenario of false premises, where LLMs are distracted by misaligned claims although the model possesses the required factual knowledge to answer original questions accurately. Inspired by the observation that entropy of the false-premise prompt is closely related to its likelihood to elicit hallucination generation, we propose a new prompting algorithm, named DecoPrompt, to mitigate hallucination. DecoPrompt leverages LLMs to "decode" the false-premise prompts without really eliciting hallucination output from LLMs. We perform experiments on two datasets, demonstrating that DecoPrompt can reduce hallucinations effectively on outputs from different LLMs. Moreover, DecoPrompt exhibits cross-model transferability, which facilitates its applications to scenarios such as LLMs of large sizes or unavailable model logits.