Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty

• URL: http://arxiv.org/abs/2604.17293v1
• Date: Sun, 19 Apr 2026 07:15:23 GMT
• Title: Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
• Abstract summary: We introduce UA-Bench, a benchmark of over 3,500 questions drawn from six datasets spanning knowledge-intensive and reasoning-intensive tasks.<n>An evaluation of 18 frontier LLMs shows that even state-of-the-art models struggle to reliably discriminate between data uncertainty and model uncertainty.<n> Experiments on both Qwen3-4B-Instruct-2507 and Qwen3-8B in thinking mode show that the proposed method improves uncertainty attribution while preserving answer accuracy.
• Score: 19.65441892575154
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reliable Large Language Models (LLMs) should abstain when confidence is insufficient. However, prior studies often treat refusal as a generic "I don't know'', failing to distinguish input-level ambiguity (data uncertainty) from capability limitations (model uncertainty). This lack of distinction limits downstream action decisions like requesting clarification or invoking external tools. In this work, we introduce UA-Bench, a benchmark of over 3,500 questions drawn from six datasets spanning knowledge-intensive and reasoning-intensive tasks, designed to evaluate explicit uncertainty attribution. An evaluation of 18 frontier LLMs shows that even state-of-the-art models struggle to reliably discriminate between data uncertainty and model uncertainty, and that high answer accuracy does not necessarily imply strong uncertainty attribution ability. To narrow this gap, we propose a lightweight data synthesis and reinforcement learning strategy. Experiments on both Qwen3-4B-Instruct-2507 and Qwen3-8B in thinking mode show that the proposed method improves uncertainty attribution while preserving answer accuracy. Our code and data are publicly available now.

Related papers

• Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models [24.72990207218907]
  Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation.<n>We investigate how in-context information influences model behavior and whether LLMs can identify their unreliable responses.
  arXiv  Detail & Related papers  (2025-08-11T16:12:36Z)
• LoGU: Long-form Generation with Uncertainty Expressions [49.76417603761989]
  We introduce the task of Long-form Generation with Uncertainty(LoGU)<n>We identify two key challenges: Uncertainty Suppression and Uncertainty Misalignment.<n>Our framework adopts a divide-and-conquer strategy, refining uncertainty based on atomic claims.<n>Experiments on three long-form instruction following datasets show that our method significantly improves accuracy, reduces hallucinations, and maintains the comprehensiveness of responses.
  arXiv  Detail & Related papers  (2024-10-18T09:15:35Z)
• MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty [10.154013836043816]
  We investigate previous uncertainty quantification methods under the presence of data uncertainty.<n>Our findings show that previous methods relatively struggle compared to single-answer settings.<n>We observe that entropy- and consistency-based methods effectively estimate model uncertainty, even in the presence of data uncertainty.
  arXiv  Detail & Related papers  (2024-08-13T11:17:31Z)
• Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations [63.330182403615886]
  A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness, hallucinations when given unanswerable questions, and safety. In all three cases, models should ideally abstain from responding, much like humans, whose ability to understand uncertainty makes us refrain from answering questions we don't know.
  arXiv  Detail & Related papers  (2024-04-16T23:56:38Z)
• Explainability through uncertainty: Trustworthy decision-making with neural networks [1.104960878651584]
  Uncertainty is a key feature of any machine learning model. It is particularly important in neural networks, which tend to be overconfident. Uncertainty as XAI improves the model's trustworthiness in downstream decision-making tasks.
  arXiv  Detail & Related papers  (2024-03-15T10:22:48Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning [76.98542249776257]
  Large-scale language models often face the challenge of "hallucination" We introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
  arXiv  Detail & Related papers  (2023-10-07T12:06:53Z)
• Ambiguity Meets Uncertainty: Investigating Uncertainty Estimation for Word Sense Disambiguation [5.55197751179213]
  Existing supervised methods treat WSD as a classification task and have achieved remarkable performance. This paper extensively studies uncertainty estimation (UE) on the benchmark designed for WSD. We examine the capability of capturing data and model uncertainties by the model with the selected UE score on well-designed test scenarios and discover that the model reflects data uncertainty satisfactorily but underestimates model uncertainty.
  arXiv  Detail & Related papers  (2023-05-22T15:18:15Z)
• Approaching Neural Network Uncertainty Realism [53.308409014122816]
  Quantifying or at least upper-bounding uncertainties is vital for safety-critical systems such as autonomous vehicles. We evaluate uncertainty realism -- a strict quality criterion -- with a Mahalanobis distance-based statistical test. We adopt it to the automotive domain and show that it significantly improves uncertainty realism compared to a plain encoder-decoder model.
  arXiv  Detail & Related papers  (2021-01-08T11:56:12Z)
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty [66.17147341354577]
  We argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. We describe how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness.
  arXiv  Detail & Related papers  (2020-11-15T17:26:14Z)

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.