# Estimating LLM Uncertainty with Evidence

arXiv: https://arxiv.org/abs/2502.00290 · HTML: https://mlsanity.com/paper/2502.00290/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 1 Feb 2025.

## Builds on (most cited first, 25 of 25)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models](https://mlsanity.com/paper/2305.19187/) (2023)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models](https://mlsanity.com/paper/2307.01379/) (2023)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [Language Model Cascades: Token-level uncertainty and beyond](https://mlsanity.com/paper/2404.10136/) (2024)
- [GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations](https://mlsanity.com/paper/2402.12348/) (2024)
- [Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code](https://mlsanity.com/paper/2404.00971/) (2024)
- [Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus](https://mlsanity.com/paper/2311.13230/) (2023)
- [SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency](https://mlsanity.com/paper/2311.01740/) (2023)
- [Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability](https://mlsanity.com/paper/2411.19943/) (2024)
- [Types of Out-of-Distribution Texts and How to Detect Them](https://mlsanity.com/paper/2109.06827/) (2021)
- [LLMs Will Always Hallucinate, and We Need to Live With This](https://mlsanity.com/paper/2409.05746/) (2024)
- [Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation](https://mlsanity.com/paper/2110.03051/) (2021)
- [Selectively Answering Ambiguous Questions](https://mlsanity.com/paper/2305.14613/) (2023)
- [A Survey of Uncertainty Estimation in LLMs: Theory Meets Practice](https://mlsanity.com/paper/2410.15326/) (2024)
- [Forking Paths in Neural Text Generation](https://mlsanity.com/paper/2412.07961/) (2024)

## Built on by (most cited first, 26 of 26)

- [Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models](https://mlsanity.com/paper/2503.15888/) (2025)
- [R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing](https://mlsanity.com/paper/2505.21600/) (2025)
- [Semantic Energy: Detecting LLM Hallucination Beyond Entropy](https://mlsanity.com/paper/2508.14496/) (2025)
- [Learned Hallucination Detection in Black-Box LLMs using Token-level Entropy Production Rate](https://mlsanity.com/paper/2509.04492/) (2025)
- [Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty Quantification](https://mlsanity.com/paper/2602.05535/) (2026)
- [Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models](https://mlsanity.com/paper/2508.08139/) (2025)
- [The Alignment Tax: Response Homogenization in Aligned LLMs and Its Implications for Uncertainty Estimation](https://mlsanity.com/paper/2603.24124/) (2026)
- [Uncertainty Quantification for Flow-Based Vision-Language-Action Models](https://mlsanity.com/paper/2606.18043/) (2026)
- [INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models](https://mlsanity.com/paper/2510.01389/) (2025)
- [ProgRAG: Hallucination-Resistant Progressive Retrieval and Reasoning over Knowledge Graphs](https://mlsanity.com/paper/2511.10240/) (2025)
- [REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation](https://mlsanity.com/paper/2508.08149/) (2025)
- [WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent](https://mlsanity.com/paper/2604.17821/) (2026)
- [Towards Generation-Efficient Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2605.06053/) (2026)
- [Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty](https://mlsanity.com/paper/2606.17312/) (2026)
- [DND: Boosting Large Language Models with Dynamic Nested Depth](https://mlsanity.com/paper/2510.11001/) (2025)
- [Calibrating Uncertainty for Zero-Shot Adversarial CLIP](https://mlsanity.com/paper/2512.12997/) (2025)
- [VIHD: Visual Intervention-based Hallucination Detection for Medical Visual Question Answering](https://mlsanity.com/paper/2605.20772/) (2026)
- [Adaptive Nucleus Truncation for Long-Form Reasoning](https://mlsanity.com/paper/2606.13982/) (2026)
- [Beyond Confidence: The Rhythms of Reasoning in Generative Models](https://mlsanity.com/paper/2602.10816/) (2026)
- [Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models](https://mlsanity.com/paper/2605.04874/) (2026)
- [Integrating Local and Global Entropy for Uncertainty Quantification in LLMs](https://mlsanity.com/paper/2606.09875/) (2026)
- [LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data](https://mlsanity.com/paper/2606.19509/) (2026)
- [TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors](https://mlsanity.com/paper/2607.12571/) (2026)
- [ProbPlug: A Plugin Uncertainty Network for Reliable Confidence in LLM Binary Classification](https://mlsanity.com/paper/2609.10122/) (2026)
- [Rethinking Correctness for Uncertainty Estimation in Clinical Prediction with Vision-Language Models](https://mlsanity.com/paper/2609.15180/) (2026)
- [Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs](https://mlsanity.com/paper/2610.01428/) (2026)

## Abstract (arXiv)

Over the past few years, Large Language Models (LLMs) have developed rapidly and are widely applied in various domains. However, LLMs face the issue of hallucinations, generating responses that may be unreliable when the models lack relevant knowledge. To be aware of potential hallucinations, uncertainty estimation methods have been introduced, and most of them have confirmed that reliability lies in critical tokens. However, probability-based methods perform poorly in identifying token reliability, limiting their practical utility. In this paper, we reveal that the probability-based method fails to estimate token reliability due to the loss of evidence strength information which is accumulated in the training stage. Therefore, we present Logits-induced token uncertainty (LogTokU), a framework for estimating decoupled token uncertainty in LLMs, enabling real-time uncertainty estimation without requiring multiple sampling processes. We employ evidence modeling to implement LogTokU and use the estimated uncertainty to guide downstream tasks. The experimental results demonstrate that LogTokU has significant effectiveness and promise.