Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?

• URL: http://arxiv.org/abs/2505.24778v2
• Date: Tue, 01 Jul 2025 05:53:22 GMT
• Title: Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?
• Abstract summary: Large language models (LLMs) are increasingly used in high-stakes domains.<n>It remains unclear whether LLMs consistently use these markers to reflect their intrinsic confidence.<n>We first define marker confidence as the observed accuracy when a model employs an epistemic marker.<n>Our results show that while markers generalize well within the same distribution, their confidence is inconsistent in out-of-distribution scenarios.
• Score: 46.28794610965004
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As large language models (LLMs) are increasingly used in high-stakes domains, accurately assessing their confidence is crucial. Humans typically express confidence through epistemic markers (e.g., "fairly confident") instead of numerical values. However, it remains unclear whether LLMs consistently use these markers to reflect their intrinsic confidence due to the difficulty of quantifying uncertainty associated with various markers. To address this gap, we first define marker confidence as the observed accuracy when a model employs an epistemic marker. We evaluate its stability across multiple question-answering datasets in both in-distribution and out-of-distribution settings for open-source and proprietary LLMs. Our results show that while markers generalize well within the same distribution, their confidence is inconsistent in out-of-distribution scenarios. These findings raise significant concerns about the reliability of epistemic markers for confidence estimation, underscoring the need for improved alignment between marker based confidence and actual model uncertainty. Our code is available at https://github.com/HKUST-KnowComp/MarCon.

Related papers

• Post-Calibration Reliability Reranking of Relevance Decisions via Label-wise Monotone Projection [35.67041829703622]
  Web search, product search, and question-answering retrieval systems often assign a relevance label and confidence score to each query-candidate pair.<n>Post-hoc calibration is needed because misaligned confidence can make systems over-trust wrong predictions or unnecessarily defer correct ones.<n>We address this gap with Label-wise Monotone Reliability Projection (MRP), which learns label-wise monotone functions that map calibrated confidence to correctness reliability.
  arXiv  Detail & Related papers  (2026-08-11T02:51:35Z)
• Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence? [50.17126900886782]
  It remains unclear whether models can apply their own linguistic confidence framework to associate markers with specific confidence levels in a stable and generalizable way.<n>We formalize _marker internal confidence_ (MIC) as the estimated intrinsic confidence a model associates with a specific epistemic marker in a given task domain.<n>Applying our analysis framework to diverse models and tasks, we find that LLMs remain faithfully miscalibrated even under model-centric interpretation of marker meanings.
  arXiv  Detail & Related papers  (2026-05-27T17:38:00Z)
• Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models [11.878003218072765]
  Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in various perception and reasoning tasks.<n>We propose a monotone confidence fusion framework to merge dual-channel signals and cross-channel consistency to estimate correctness.<n>Experiments on diverse open-source and closed-source MLLMs show that our method consistently yields more reliable confidence estimates.
  arXiv  Detail & Related papers  (2026-04-19T06:07:39Z)
• BAS: A Decision-Theoretic Approach to Evaluating Large Language Model Confidence [22.382291859991472]
  We introduce the Behavioral Alignment Score (BAS), a decision-theoretic metric for evaluating how well large language models support abstention-aware decision making.<n>BAS is derived from an explicit answer-or-abstain utility model and aggregates realized utility across a continuum of risk thresholds.<n>We show theoretically that truthful confidence estimates uniquely maximize expected BAS utility, linking calibration to decision-optimal behavior.
  arXiv  Detail & Related papers  (2026-04-03T17:44:32Z)
• A Confidence-Variance Theory for Pseudo-Label Selection in Semi-Supervised Learning [15.149171763610662]
  This paper introduces a Confidence-Variance (CoVar) theory framework that provides a principled joint reliability criterion for pseudo-label selection.<n>We show that reliable pseudo-labels should have both high MC and low RCV, and that the influence of RCV increases as confidence grows.<n>We integrate CoVar as a plug-in module into representative semi-supervised semantic segmentation and image classification methods.
  arXiv  Detail & Related papers  (2026-01-16T02:51:59Z)
• BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents [58.05949210993854]
  We investigate whether search agents have the ability to communicate their own confidence through verbalized confidence scores after long sequences of actions.<n>We propose Test-Time Scaling (TTS) methods that use confidence scores to determine answer quality, encourage the model to try again until reaching a satisfactory confidence level.
  arXiv  Detail & Related papers  (2025-10-27T15:58:51Z)
• ConfTuner: Training Large Language Models to Express Their Confidence Verbally [58.63318088243125]
  Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as science, law, and healthcare.<n>LLMs are often observed to generate incorrect answers with high confidence, a phenomenon known as "overconfidence"
  arXiv  Detail & Related papers  (2025-08-26T09:25:32Z)
• Mind the Generation Process: Fine-Grained Confidence Estimation During LLM Generation [63.49409574310576]
  Large language models (LLMs) exhibit overconfidence, assigning high confidence scores to incorrect predictions.<n>We introduce FineCE, a novel confidence estimation method that delivers accurate, fine-grained confidence scores during text generation.<n>Our code and all baselines used in the paper are available on GitHub.
  arXiv  Detail & Related papers  (2025-08-16T13:29:35Z)
• Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence [16.311538811237536]
  Large language models (LLMs) are increasingly used for factual question-answering.<n>For these verbalized expressions of uncertainty to be meaningful, they should reflect the error rates at the expressed level of confidence.<n>We propose a simple procedure, uncertainty distillation, to teach an LLM to calibrated semantic confidences.
  arXiv  Detail & Related papers  (2025-03-18T21:29:29Z)
• On Verbalized Confidence Scores for LLMs [25.160810008907397]
  Uncertainty quantification for large language models (LLMs) can establish more human trust into their responses.<n>This work focuses on asking the LLM itself to verbalize its uncertainty with a confidence score as part of its output tokens.<n>We assess the reliability of verbalized confidence scores with respect to different datasets, models, and prompt methods.
  arXiv  Detail & Related papers  (2024-12-19T11:10:36Z)
• Confidence in the Reasoning of Large Language Models [0.0]
  Confidence is measured in terms of persistence in keeping their answer when prompted to reconsider.<n> Confidence is only partially explained by the underlying token-level probability.
  arXiv  Detail & Related papers  (2024-12-19T10:04:29Z)
• Label-Confidence-Aware Uncertainty Estimation in Natural Language Generation [8.635811152610604]
  Uncertainty Quantification (UQ) is crucial for ensuring the safety and robustness of AI systems.<n>We propose a label-confidence-aware (LCA) uncertainty estimation based on Kullback-Leibler divergence bridging between samples and label source.
  arXiv  Detail & Related papers  (2024-12-10T07:35:23Z)
• Mirror-Consistency: Harnessing Inconsistency in Majority Voting [54.30719306011487]
  We present Mirror-Consistency, an enhancement of the standard Self-Consistency approach. Mirror-Consistency incorporates a'reflective mirror' into the self-ensemble decoding process. We show that Mirror-Consistency yields superior performance in both reasoning accuracy and confidence calibration compared to Self-Consistency.
  arXiv  Detail & Related papers  (2024-10-07T03:41:08Z)
• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models [79.76293901420146]
  Large Language Models (LLMs) are employed across various high-stakes domains, where the reliability of their outputs is crucial. Our research investigates the fragility of uncertainty estimation and explores potential attacks. We demonstrate that an attacker can embed a backdoor in LLMs, which, when activated by a specific trigger in the input, manipulates the model's uncertainty without affecting the final output.
  arXiv  Detail & Related papers  (2024-07-15T23:41:11Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Revisiting Confidence Estimation: Towards Reliable Failure Prediction [53.79160907725975]
  We find a general, widely existing but actually-neglected phenomenon that most confidence estimation methods are harmful for detecting misclassification errors. We propose to enlarge the confidence gap by finding flat minima, which yields state-of-the-art failure prediction performance.
  arXiv  Detail & Related papers  (2024-03-05T11:44:14Z)
• TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness [58.721012475577716]
  Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, prompting a surge in their practical applications. This paper introduces TrustScore, a framework based on the concept of Behavioral Consistency, which evaluates whether an LLMs response aligns with its intrinsic knowledge.
  arXiv  Detail & Related papers  (2024-02-19T21:12:14Z)
• MACEst: The reliable and trustworthy Model Agnostic Confidence Estimator [0.17188280334580192]
  We argue that any confidence estimates based upon standard machine learning point prediction algorithms are fundamentally flawed. We present MACEst, a Model Agnostic Confidence Estimator, which provides reliable and trustworthy confidence estimates.
  arXiv  Detail & Related papers  (2021-09-02T14:34:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.