# First Hallucination Tokens Are Different from Conditional Ones

arXiv: https://arxiv.org/abs/2507.20836 · HTML: https://mlsanity.com/paper/2507.20836/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Do Language Models Know When They're Hallucinating References?](https://mlsanity.com/paper/2305.18248/) (2023)
- [The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models](https://mlsanity.com/paper/2401.03205/) (2024)
- [On Early Detection of Hallucinations in Factual Question Answering](https://mlsanity.com/paper/2312.14183/) (2023)
- [On Large Language Models' Hallucination with Regard to Known Facts](https://mlsanity.com/paper/2403.20009/) (2024)
- [Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach](https://mlsanity.com/paper/2405.19648/) (2024)
- [Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models](https://mlsanity.com/paper/2411.00154/) (2024)
- [A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation](https://mlsanity.com/paper/2406.06950/) (2024)
- [Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models](https://mlsanity.com/paper/2502.14427/) (2025)
- [Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics](https://mlsanity.com/paper/2403.08904/) (2024)

## Built on by (most cited first, 4 of 4)

- [Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer](https://mlsanity.com/paper/2605.22007/) (2026)
- [How Confident Is the First Token? An Uncertainty-Calibrated Prompt Optimization Framework for Large Language Model Classification and Understanding](https://mlsanity.com/paper/2603.18009/) (2026)
- [Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics](https://mlsanity.com/paper/2606.12476/) (2026)
- [The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining](https://mlsanity.com/paper/2609.32964/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) hallucinate, and detecting these cases is key to ensuring trust. While many approaches address hallucination detection at the response or span level, recent work explores token-level detection, enabling more fine-grained intervention. However, the distribution of hallucination signal across sequences of hallucinated tokens remains unexplored. We leverage token-level annotations from the RAGTruth corpus and find that the first hallucinated token is far more detectable than later ones. This structural property holds across models, suggesting that first hallucination tokens play a key role in token-level hallucination detection. Our code is available at https://github.com/jakobsnl/RAGTruth_Xtended.