# HALT: Hallucination Assessment via Log-probs as Time series

arXiv: https://arxiv.org/abs/2602.02888 · HTML: https://mlsanity.com/paper/2602.02888/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 30 of 31)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Revisiting the Calibration of Modern Neural Networks](https://mlsanity.com/paper/2106.07998/) (2021)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation](https://mlsanity.com/paper/2307.03987/) (2023)
- [Fine-grained Hallucination Detection and Editing for Language Models](https://mlsanity.com/paper/2401.06855/) (2024)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [Self-Evaluation Improves Selective Generation in Large Language Models](https://mlsanity.com/paper/2312.09300/) (2023)
- [Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach](https://mlsanity.com/paper/2405.19648/) (2024)
- [Contrastive Learning Reduces Hallucination in Conversations](https://mlsanity.com/paper/2212.10400/) (2022)
- [LettuceDetect: A Hallucination Detection Framework for RAG Applications](https://mlsanity.com/paper/2502.17125/) (2025)
- [ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs](https://mlsanity.com/paper/2507.16488/) (2025)
- [Hallucination Detection in Large Language Models with Metamorphic Relations](https://mlsanity.com/paper/2502.15844/) (2025)
- [Hallucination Detection in LLMs with Topological Divergence on Attention Graphs](https://mlsanity.com/paper/2504.10063/) (2025)
- [Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection](https://mlsanity.com/paper/2502.15845/) (2025)
- [Beyond Token Probes: Hallucination Detection via Activation Tensors with ACT-ViT](https://mlsanity.com/paper/2510.00296/) (2025)
- [FactSelfCheck: Fact-Level Black-Box Hallucination Detection for LLMs](https://mlsanity.com/paper/2503.17229/) (2025)
- [Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions](https://mlsanity.com/paper/2503.14043/) (2025)
- [Semantic Uncertainty Quantification of Hallucinations in LLMs: A Quantum Tensor Network Based Method](https://mlsanity.com/paper/2601.20026/) (2026)
- [Neural Message-Passing on Attention Graphs for Hallucination Detection](https://mlsanity.com/paper/2509.24770/) (2025)
- [DecoPrompt : Decoding Prompts Reduces Hallucinations when Large Language Models Meet False Premises](https://mlsanity.com/paper/2411.07457/) (2024)
- [Black-Box Hallucination Detection via Consistency Under the Uncertain Expression](https://mlsanity.com/paper/2509.21999/) (2025)

## Built on by (most cited first, 8 of 8)

- [The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation](https://mlsanity.com/paper/2603.24124/) (2026)
- [HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language Models](https://mlsanity.com/paper/2604.26139/) (2026)
- [TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection](https://mlsanity.com/paper/2606.01033/) (2026)
- [Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics](https://mlsanity.com/paper/2606.12476/) (2026)
- [Temporal Multi-Signal Fusion for Token-Level Hallucination Detection](https://mlsanity.com/paper/2608.18115/) (2026)
- [Prediction of Prediction (PoP): Inter-Layer Activation Fusion for Single-Pass Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2608.27165/) (2026)
- [From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs](https://mlsanity.com/paper/2609.02679/) (2026)
- [TRACE: Single-Pass Decoding-Trace Risk Localization for Generation Calibration](https://mlsanity.com/paper/2609.35387/) (2026)

## Abstract (arXiv)

Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination Assessment via Log-probs as Time series), a lightweight hallucination detector that leverages only the top-20 token log-probabilities from LLM generations as a time series. HALT uses a gated recurrent unit model combined with entropy-based features to learn model calibration bias, providing an extremely efficient alternative to large encoders. Unlike white-box approaches, HALT does not require access to hidden states or attention maps, relying only on output log-probabilities. Unlike black-box approaches, it operates on log-probs rather than surface-form text, which enables stronger domain generalization and compatibility with proprietary LLMs without requiring access to internal weights. To benchmark performance, we introduce HUB (Hallucination detection Unified Benchmark), which consolidates prior datasets into ten capabilities covering both reasoning tasks (Algorithmic, Commonsense, Mathematical, Symbolic, Code Generation) and general purpose skills (Chat, Data-to-Text, Question Answering, Summarization, World Knowledge). While being 30x smaller, HALT outperforms Lettuce, a fine-tuned modernBERT-base encoder, achieving a 60x speedup gain on HUB. HALT and HUB together establish an effective framework for hallucination detection across diverse LLM capabilities.