mlsanityData to 14 Oct 2026

Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge

arXiv 2311.09731 ↗First posted 16 Nov 2023cs.CL cs.AI cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Can large language models (LLMs) express their uncertainty in situations where they lack sufficient parametric knowledge to generate reasonable responses? This work aims to systematically investigate LLMs' behaviors in such situations, emphasizing the trade-off between honesty and helpfulness. To tackle the challenge of precisely determining LLMs' knowledge gaps, we diagnostically create unanswerable questions containing non-existent concepts or false premises, ensuring that they are outside the LLMs' vast training data. By compiling a benchmark, UnknownBench, which consists of both unanswerable and answerable questions, we quantitatively evaluate the LLMs' performance in maintaining honesty while being helpful. Using a model-agnostic unified confidence elicitation approach, we observe that most LLMs fail to consistently refuse or express uncertainty towards questions outside their parametric knowledge, although instruction fine-tuning and alignment techniques can provide marginal enhancements. Moreover, LLMs' uncertainty expression does not always stay consistent with the perceived confidence of their textual outputs.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

28 of 43 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  5. 2017On Calibration of Modern Neural Networkscited by 4,960
  6. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  7. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  8. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  9. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  10. 2022Teaching Models to Express Their Uncertainty in Wordscited by 751
  11. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 439
  12. 2023A Survey of Hallucination in Large Foundation Modelscited by 368
16 more
  1. 2023FreshLLMs: Refreshing Large Language Models with Search Engine Augmentationcited by 318
  2. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 246
  3. 2020Reducing conversational agents' overconfidence through linguistic calibrationcited by 210
  4. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 206
  5. 2022Language models show human-like content effects on reasoning taskscited by 173
  6. 2023Sources of Hallucination by Large Language Models on Inference Taskscited by 169
  7. 2022On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?cited by 138
  8. 2022Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysiscited by 104
  9. 2023Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examplescited by 84
  10. 2022CREPE: Open-Domain Question Answering with False Presuppositionscited by 72
  11. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  12. 2023From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuningcited by 56
  13. 2023Won't Get Fooled Again: Answering Questions with False Premisescited by 48
  14. 2023Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learningcited by 29
  15. 2023Counterfactual reasoning: Testing language models' understanding of hypothetical scenarioscited by 27
  16. 2023Augmenting LLMs with Knowledge: A survey on hallucination preventioncited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 11; 2025: 11; 2026: 10.

32 papers.

Sort:

By area:

  1. 2025X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agentscited by 125
  2. 2024Knowledge Boundary of Large Language Models: A Surveycited by 40
  3. 2025Generalization Bias in Large Language Model Summarization of Scientific Researchcited by 30
  4. 2025MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulationscited by 27
  5. 2024BeHonest: Benchmarking Honesty in Large Language Modelscited by 24
  6. 2024A Survey on the Honesty of Large Language Modelscited by 23
  7. 2024Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrappingcited by 14
  8. 2024UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Modelscited by 13
  9. 2024LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statementscited by 12
  10. 2024Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMscited by 11
  11. 2025MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence Calibrationcited by 11
  12. 2025MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questionscited by 11
20 more
  1. 2025Uncertainty Quantification in Retrieval Augmented Question Answeringcited by 8
  2. 2025SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialoguescited by 7
  3. 2024LLMs can learn self-restraint through iterative self-reflectioncited by 6
  4. 2025A Unified Definition of Hallucination: It's The World Model, Stupid!cited by 6
  5. 2024Recognizing Limits: Investigating Infeasibility in Large Language Modelscited by 4
  6. 2026Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQAcited by 4
  7. 2025Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honestycited by 3
  8. 2026SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?cited by 3
  9. 2024Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledgecited by 2
  10. 2024Knowledge Graph Guided Evaluation of Abstention Techniquescited by 2
  11. 2025Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Trainingcited by 2
  12. 2026PhantomBench: Benchmarking the Non-existential Threat of Language Modelscited by 2
  13. 2026Knowledge Boundary Discovery for Large Language Modelscited by 1
  14. 2026Learning from AVA: Early Lessons from a Curated and Trustworthy Generative AI for Policy and Development Researchcited by 1
  15. 2026Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearningcited by 1
  16. 2025PCS: Perceived Confidence Scoring of Black Box LLMs with Metamorphic Relationscited by 0
  17. 2026What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"cited by 0
  18. 2026Automatic Hard Example Synthesis with Multi-Level Agentic Data Curationcited by 0
  19. 2026What Makes Agent Memory Useful for Reliable Unanswerable Question Handling?cited by 0
  20. 2026Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuningcited by 0