Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:2RYEBC6Irecord.jsonopen to challenge →
read the original abstract
Large Language Models (LLMs) excel in text generation, reasoning, and decision-making, enabling their adoption in high-stakes domains such as healthcare, law, and transportation. However, their reliability is a major concern, as they often produce plausible but incorrect responses. Uncertainty quantification (UQ) enhances trustworthiness by estimating confidence in outputs, enabling risk mitigation and selective prediction. However, traditional UQ methods struggle with LLMs due to computational constraints and decoding inconsistencies. Moreover, LLMs introduce unique uncertainty sources, such as input ambiguity, reasoning path divergence, and decoding stochasticity, that extend beyond classical aleatoric and epistemic uncertainty. To address this, we introduce a new taxonomy that categorizes UQ methods based on computational efficiency and uncertainty dimensions (input, reasoning, parameter, and prediction uncertainty). We evaluate existing techniques, assess their real-world applicability, and identify open challenges, emphasizing the need for scalable, interpretable, and robust UQ approaches to enhance LLM reliability.
This paper has not been read by Pith yet.
Forward citations
Cited by 10 Pith papers
-
MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
MARGIN is an online per-agent per-band calibration method using symmetric exponentially weighted moving averages with Bayesian shrinkage that reduces calibration error 3-6x under distribution shift and improves multi-...
-
Inducing Artificial Uncertainty in Language Models
Inducing artificial uncertainty on trivial tasks allows training probes that achieve higher calibration on hard data than standard approaches while retaining performance on easy data.
-
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
A large-scale multilingual evaluation of LLM uncertainty estimation methods across 22 languages and 9 models finds that English reasoning closes the UE gap for low-resource languages and that optimal UE method choice ...
-
MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
MARGIN is an online calibration technique using symmetric EWMA and Bayesian shrinkage that learns per-agent per-band factors from the task stream, cutting calibration error 3-6x versus design-time baselines and liftin...
-
Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning
METIS internalizes curriculum judgment in LLM reinforcement fine-tuning by predicting within-prompt reward variance via in-context learning and jointly optimizing with a self-judgment reward, yielding superior perform...
-
Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training
Average token log-probability provides a zero-shot confidence signal for small LLMs that matches supervised baselines in-distribution and outperforms them out-of-distribution, with a new retrieval-conditional variant ...
-
TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
TokUR estimates token-level uncertainty via low-rank weight perturbations in LLMs, aggregates signals to correlate with correctness, and uses them to improve reasoning performance on math tasks.
-
Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective
Reliable AI needs structured Knowledge Objects to externalize and enable human validation of implicit knowledge that current methods cannot verify.
-
SocialLM: Social Signal Processing of Patient-Provider Communication using LLMs and Contextual Aggregation
LLMs detect social signals in clinical transcripts across model families, with an agreement-weighted ensemble using group-level agreement patterns improving accuracy and stability over individual models.
-
Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective
Proposes Knowledge Objects to externalize implicit AI knowledge for human verification, addressing a gap in current reliability methods.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.