# Calibrating Verbal Uncertainty as a Linear Feature to Reduce Hallucinations

arXiv: https://arxiv.org/abs/2503.14477 · HTML: https://mlsanity.com/paper/2503.14477/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 80 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 30 of 64)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models](https://mlsanity.com/paper/2309.03883/) (2023)
- [HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2305.11747/) (2023)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs](https://mlsanity.com/paper/2406.15927/) (2024)

## Built on by (most cited first, 30 of 48)

- [AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions](https://mlsanity.com/paper/2506.09038/) (2025)
- [Embodied AI Agents: Modeling the World](https://mlsanity.com/paper/2506.22355/) (2025)
- [LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions](https://mlsanity.com/paper/2509.18970/) (2025)
- [Revisiting Uncertainty Estimation and Calibration of Large Language Models](https://mlsanity.com/paper/2505.23854/) (2025)
- [SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models](https://mlsanity.com/paper/2601.03555/) (2026)
- [Verifying Chain-of-Thought Reasoning via Its Computational Graph](https://mlsanity.com/paper/2510.09312/) (2025)
- [AgentAbstain: Do LLM Agents Know When Not to Act?](https://mlsanity.com/paper/2607.10059/) (2026)
- [MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs](https://mlsanity.com/paper/2505.24858/) (2025)
- [Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing](https://mlsanity.com/paper/2507.10587/) (2025)
- [Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation](https://mlsanity.com/paper/2512.22245/) (2025)
- [Teaching Language Models to Faithfully Express their Uncertainty](https://mlsanity.com/paper/2510.12587/) (2025)
- [The Value Axis: Language Models Encode Whether They're on the Right Track](https://mlsanity.com/paper/2606.17056/) (2026)
- [Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning](https://mlsanity.com/paper/2510.02324/) (2025)
- [HACK: Hallucinations Along Certainty and Knowledge Axes](https://mlsanity.com/paper/2510.24222/) (2025)
- [Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration](https://mlsanity.com/paper/2605.27752/) (2026)
- [Can Large Language Models Express Uncertainty Like Human?](https://mlsanity.com/paper/2509.24202/) (2025)
- [Honesty over Accuracy: Trustworthy Language Models through Reinforced Hesitation](https://mlsanity.com/paper/2511.11500/) (2025)
- [Hallucinations Undermine Trust; Metacognition is a Way Forward](https://mlsanity.com/paper/2605.01428/) (2026)
- [Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots](https://mlsanity.com/paper/2504.03735/) (2025)
- [Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs](https://mlsanity.com/paper/2604.01457/) (2026)
- [Steering the Verifiability of Multimodal AI Hallucinations](https://mlsanity.com/paper/2604.06714/) (2026)
- [Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs](https://mlsanity.com/paper/2606.32032/) (2026)
- [A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation](https://mlsanity.com/paper/2608.24419/) (2026)
- [SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention](https://mlsanity.com/paper/2506.14387/) (2025)
- [GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models](https://mlsanity.com/paper/2509.09438/) (2025)
- [Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes](https://mlsanity.com/paper/2512.14177/) (2025)
- [Linking Perception, Confidence and Accuracy in MLLMs](https://mlsanity.com/paper/2603.12149/) (2026)
- [Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models](https://mlsanity.com/paper/2603.15557/) (2026)
- [Retrieval-Augmented Linguistic Calibration](https://mlsanity.com/paper/2605.19344/) (2026)
- [Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?](https://mlsanity.com/paper/2605.28778/) (2026)

## Abstract (arXiv)

LLMs often adopt an assertive language style also when making false claims. Such ``overconfident hallucinations'' mislead users and erode trust. Achieving the ability to express in language the actual degree of uncertainty around a claim is therefore of great importance. We find that ``verbal uncertainty'' is governed by a single linear feature in the representation space of LLMs, and show that this has only moderate correlation with the actual ``semantic uncertainty'' of the model. We apply this insight and show that (1) the mismatch between semantic and verbal uncertainty is a better predictor of hallucinations than semantic uncertainty alone and (2) we can intervene on verbal uncertainty at inference time and reduce confident hallucinations on short-form answers, achieving an average relative reduction of ~30%.