# Uncertainty Quantification for In-Context Learning of Large Language Models

arXiv: https://arxiv.org/abs/2402.10189 · HTML: https://mlsanity.com/paper/2402.10189/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges](https://mlsanity.com/paper/2011.06225/) (2020)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Texts](https://mlsanity.com/paper/1307.5336/) (2013)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey](https://mlsanity.com/paper/2305.18703/) (2023)
- [LM-Polygraph: Uncertainty Estimation for Language Models](https://mlsanity.com/paper/2311.07383/) (2023)
- [Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?](https://mlsanity.com/paper/2209.03302/) (2022)
- [Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis](https://mlsanity.com/paper/2210.04714/) (2022)
- [Uncertainty Aware Semi-Supervised Learning on Graph Data](https://mlsanity.com/paper/2010.12783/) (2020)
- [Quantifying Uncertainties in Natural Language Processing Tasks](https://mlsanity.com/paper/1811.07253/) (2018)
- [Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models](https://mlsanity.com/paper/2401.00625/) (2024)
- [HYTREL: Hypergraph-enhanced Tabular Data Representation Learning](https://mlsanity.com/paper/2307.08623/) (2023)
- [Source Localization of Graph Diffusion via Variational Autoencoders for Graph Inverse Problems](https://mlsanity.com/paper/2206.12327/) (2022)
- [Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables](https://mlsanity.com/paper/1706.08495/) (2017)
- [Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty](https://mlsanity.com/paper/2309.03433/) (2023)

## Built on by (most cited first, 30 of 45)

- [A Survey of Uncertainty Estimation Methods on Large Language Models](https://mlsanity.com/paper/2503.00172/) (2025)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving](https://mlsanity.com/paper/2404.17729/) (2024)
- [TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning](https://mlsanity.com/paper/2505.11737/) (2025)
- [HonestLLM: Toward an Honest and Helpful Large Language Model](https://mlsanity.com/paper/2406.00380/) (2024)
- [Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers](https://mlsanity.com/paper/2504.19254/) (2025)
- [Language Model Uncertainty Quantification with Attention Chain](https://mlsanity.com/paper/2503.19168/) (2025)
- [Uncertainty Quantification and Decomposition for LLM-based Recommendation](https://mlsanity.com/paper/2501.17630/) (2025)
- [Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems](https://mlsanity.com/paper/2506.10060/) (2025)
- [MAP: Multi-user Personalization with Collaborative LLM-powered Agents](https://mlsanity.com/paper/2503.12757/) (2025)
- [Conformal Information Pursuit for Interactively Guiding Large Language Models](https://mlsanity.com/paper/2507.03279/) (2025)
- [Shifting Uncertainty to Critical Moments: Towards Reliable Uncertainty Quantification for VLA Model](https://mlsanity.com/paper/2603.18342/) (2026)
- [LLM Confidence Evaluation Measures in Zero-Shot CSS Classification](https://mlsanity.com/paper/2410.13047/) (2024)
- [Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?](https://mlsanity.com/paper/2505.21003/) (2025)
- [UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models](https://mlsanity.com/paper/2602.18020/) (2026)
- [Comparing Uncertainty Measurement and Mitigation Methods for Large Language Models: A Systematic Review](https://mlsanity.com/paper/2504.18346/) (2025)
- [Uncertainty Profiles for LLMs: Uncertainty Source Decomposition and Adaptive Model-Metric Selection](https://mlsanity.com/paper/2505.07309/) (2025)
- [The Geometry of Creative Variability: How Credal Sets Expose Calibration Gaps in Language Models](https://mlsanity.com/paper/2509.23088/) (2025)
- [Uncertainty Quantification for Flow-Based Vision-Language-Action Models](https://mlsanity.com/paper/2606.18043/) (2026)
- [Robust Instant Policy: Leveraging Student's t-Regression Model for Robust In-context Imitation Learning of Robot Manipulation](https://mlsanity.com/paper/2506.15157/) (2025)
- [INSIGHT: INference-time Sequence Introspection for Generating Help Triggers in Vision-Language-Action Models](https://mlsanity.com/paper/2510.01389/) (2025)
- [Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting](https://mlsanity.com/paper/2605.27668/) (2026)
- [From predictions to confidence intervals: an empirical study of conformal prediction methods for in-context learning](https://mlsanity.com/paper/2504.15722/) (2025)
- [ALARM: Automated MLLM-Based Anomaly Detection in Complex-EnviRonment Monitoring with Uncertainty Quantification](https://mlsanity.com/paper/2512.03101/) (2025)
- [A Geometric Analysis of Small-sized Language Model Hallucinations](https://mlsanity.com/paper/2602.14778/) (2026)
- [LaMsS: When Large Language Models Meet Self-Skepticism](https://mlsanity.com/paper/2409.06601/) (2024)
- [Plausibility as Failure: How LLMs and Humans Co-Construct Epistemic Error](https://mlsanity.com/paper/2512.16750/) (2025)
- [Towards Effective In-context Cross-domain Knowledge Transfer via Domain-invariant-neurons-based Retrieval](https://mlsanity.com/paper/2604.05383/) (2026)
- [Reason Analogically via Cross-domain Prior Knowledge: An Empirical Study of Cross-domain Knowledge Transfer for In-Context Learning](https://mlsanity.com/paper/2604.05396/) (2026)
- [AGSC: Adaptive Granularity and Semantic Clustering for Uncertainty Quantification in Long-text Generation](https://mlsanity.com/paper/2604.06812/) (2026)

## Abstract (arXiv)

In-context learning has emerged as a groundbreaking ability of Large Language Models (LLMs) and revolutionized various fields by providing a few task-relevant demonstrations in the prompt. However, trustworthy issues with LLM's response, such as hallucination, have also been actively discussed. Existing works have been devoted to quantifying the uncertainty in LLM's response, but they often overlook the complex nature of LLMs and the uniqueness of in-context learning. In this work, we delve into the predictive uncertainty of LLMs associated with in-context learning, highlighting that such uncertainties may stem from both the provided demonstrations (aleatoric uncertainty) and ambiguities tied to the model's configurations (epistemic uncertainty). We propose a novel formulation and corresponding estimation method to quantify both types of uncertainties. The proposed method offers an unsupervised way to understand the prediction of in-context learning in a plug-and-play fashion. Extensive experiments are conducted to demonstrate the effectiveness of the decomposition. The code and data are available at: https://github.com/lingchen0331/UQ_ICL.