Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
Uncertainty quantification in Large Language Models (LLMs) is crucial for applications where safety and reliability are important. In particular, uncertainty can be used to improve the trustworthiness of LLMs by detecting factually incorrect model responses, commonly called hallucinations. Critically, one should seek to capture the model's semantic uncertainty, i.e., the uncertainty over the meanings of LLM outputs, rather than uncertainty over lexical or syntactic variations that do not affect answer correctness. To address this problem, we propose Kernel Language Entropy (KLE), a novel method for uncertainty estimation in white- and black-box LLMs. KLE defines positive semidefinite unit trace kernels to encode the semantic similarities of LLM outputs and quantifies uncertainty using the von Neumann entropy. It considers pairwise semantic dependencies between answers (or semantic clusters), providing more fine-grained uncertainty estimates than previous methods based on hard clustering of answers. We theoretically prove that KLE generalizes the previous state-of-the-art method called semantic entropy and empirically demonstrate that it improves uncertainty quantification performance across multiple natural language generation datasets and LLM architectures.
Code (2)
Tasks
Text GenerationUncertainty QuantificationSimilar Papers 제목 키워드 기반
A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models
Generative models, like large language models, are becoming increasingly relevant in our daily lives, yet a theoretical framework to assess their generalization behavior and uncertainty does not exist. Particularly, the …
Image GenerationQuestion AnsweringText GenerationTriviaQAFine-Grained Uncertainty Decomposition in Large Language Models: A Spectral Approach
As Large Language Models (LLMs) are increasingly integrated in diverse applications, obtaining reliable measures of their predictive uncertainty has become critically important. A precise distinction between aleatoric un…
Semantic SimilarityNERVE: Neighbourhood & Entropy-guided Random-walk for training free open-Vocabulary sEgmentation
Despite recent advances in Open-Vocabulary Semantic Segmentation (OVSS), existing training-free methods face several limitations: use of computationally expensive affinity refinement strategies, ineffective fusion of tra…
Semantic SegmentationFrom Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
Large Language Models (LLMs) that can express interpretable and calibrated uncertainty are crucial in high-stakes domains. While methods to compute uncertainty post-hoc exist, they are often sampling-based and therefore …
Reinforcement LearningDifferent Questions, Different Models: Fine-Grained Evaluation of Uncertainty and Calibration in Clinical QA with LLMs
Accurate and well-calibrated uncertainty estimates are essential for deploying large language models (LLMs) in high-stakes domains such as clinical decision support. We present a fine-grained evaluation of uncertainty es…
Multiple-choiceQuestion Answering