# Distinguishing the Knowable from the Unknowable with Language Models

arXiv: https://arxiv.org/abs/2402.03563 · HTML: https://mlsanity.com/paper/2402.03563/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 70 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Memory-Based Model Editing at Scale](https://mlsanity.com/paper/2206.06520/) (2022)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [Can We Edit Factual Knowledge by In-Context Learning?](https://mlsanity.com/paper/2305.12740/) (2023)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [Selective Question Answering under Domain Shift](https://mlsanity.com/paper/2006.09462/) (2020)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Epistemic Neural Networks](https://mlsanity.com/paper/2107.08924/) (2021)
- [Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling](https://mlsanity.com/paper/2311.08718/) (2023)
- [Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settings](https://mlsanity.com/paper/2203.00211/) (2022)
- [Bootstrapped Thompson Sampling and Deep Exploration](https://mlsanity.com/paper/1507.00300/) (2015)
- [Fine-Tuning Language Models via Epistemic Neural Networks](https://mlsanity.com/paper/2211.01568/) (2022)
- [Measuring and Modifying Factual Knowledge in Large Language Models](https://mlsanity.com/paper/2306.06264/) (2023)

## Built on by (most cited first, 30 of 47)

- [Know Your Limits: A Survey of Abstention in Large Language Models](https://mlsanity.com/paper/2407.18418/) (2024)
- [A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions](https://mlsanity.com/paper/2412.05563/) (2024)
- [To Believe or Not to Believe Your LLM](https://mlsanity.com/paper/2406.02543/) (2024)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [LLM Internal States Reveal Hallucination Risk Faced With a Query](https://mlsanity.com/paper/2407.03282/) (2024)
- [Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach](https://mlsanity.com/paper/2404.15993/) (2024)
- [A Survey of Uncertainty Estimation Methods on Large Language Models](https://mlsanity.com/paper/2503.00172/) (2025)
- [Efficiently Scaling LLM Reasoning with Certaindex](https://mlsanity.com/paper/2412.20993/) (2024)
- [Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era](https://mlsanity.com/paper/2403.08946/) (2024)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty](https://mlsanity.com/paper/2408.06816/) (2024)
- [Do LLMs "know" internally when they follow instructions?](https://mlsanity.com/paper/2410.14516/) (2024)
- [Do LLMs estimate uncertainty well in instruction-following?](https://mlsanity.com/paper/2410.14582/) (2024)
- [Estimating the Hallucination Rate of Generative AI](https://mlsanity.com/paper/2406.07457/) (2024)
- [MUR: Momentum Uncertainty guided Reasoning for Large Language Models](https://mlsanity.com/paper/2507.14958/) (2025)
- [On Subjective Uncertainty Quantification and Calibration in Natural Language Generation](https://mlsanity.com/paper/2406.05213/) (2024)
- [Conformal Language Model Reasoning with Coherent Factuality](https://mlsanity.com/paper/2505.17126/) (2025)
- [Calibrating Verbalized Confidence with Self-Generated Distractors](https://mlsanity.com/paper/2509.25532/) (2025)
- [Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy](https://mlsanity.com/paper/2410.17234/) (2024)
- [When to Speak, When to Abstain: Contrastive Decoding with Abstention](https://mlsanity.com/paper/2412.12527/) (2024)
- [Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities](https://mlsanity.com/paper/2603.10396/) (2026)
- [Uncertainty Profiles for LLMs: Uncertainty Source Decomposition and Adaptive Model-Metric Selection](https://mlsanity.com/paper/2505.07309/) (2025)
- [LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs](https://mlsanity.com/paper/2505.24451/) (2025)
- [Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems](https://mlsanity.com/paper/2506.20209/) (2025)
- [Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings](https://mlsanity.com/paper/2508.06030/) (2025)
- [Disentangling Ambiguity from Instability in Large Language Models: A Clinical Text-to-SQL Case Study](https://mlsanity.com/paper/2602.12015/) (2026)
- [Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space](https://mlsanity.com/paper/2605.12412/) (2026)
- [Automatic Layer Selection for Hallucination Detection](https://mlsanity.com/paper/2605.26366/) (2026)
- [Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification](https://mlsanity.com/paper/2405.15115/) (2024)
- [Efficient semantic uncertainty quantification in language models via diversity-steered sampling](https://mlsanity.com/paper/2510.21310/) (2025)

## Abstract (arXiv)

We study the feasibility of identifying epistemic uncertainty (reflecting a lack of knowledge), as opposed to aleatoric uncertainty (reflecting entropy in the underlying distribution), in the outputs of large language models (LLMs) over free-form text. In the absence of ground-truth probabilities, we explore a setting where, in order to (approximately) disentangle a given LLM's uncertainty, a significantly larger model stands in as a proxy for the ground truth. We show that small linear probes trained on the embeddings of frozen, pretrained models accurately predict when larger models will be more confident at the token level and that probes trained on one text domain generalize to others. Going further, we propose a fully unsupervised method that achieves non-trivial accuracy on the same task. Taken together, we interpret these results as evidence that LLMs naturally contain internal representations of different types of uncertainty that could potentially be leveraged to devise more informative indicators of model confidence in diverse practical settings.