Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space

2024-05-22 · Xin Qiu, Risto Miikkulainen

With the widespread application of Large Language Models (LLMs) to various domains, concerns regarding the trustworthiness of LLMs in safety-critical scenarios have been raised, due to their unpredictable tendency to hallucinate and generate misinformation. Existing LLMs do not have an inherent functionality to provide the users with an uncertainty/confidence metric for each response it generates, making it difficult to evaluate trustworthiness. Although several studies aim to develop uncertainty quantification methods for LLMs, they have fundamental limitations, such as being restricted to classification tasks, requiring additional training and data, considering only lexical instead of semantic information, and being prompt-wise but not response-wise. A new framework is proposed in this paper to address these issues. Semantic density extracts uncertainty/confidence information for each response from a probability distribution perspective in semantic space. It has no restriction on task types and is "off-the-shelf" for new models and tasks. Experiments on seven state-of-the-art LLMs, including the latest Llama 3 and Mixtral-8x22B models, on four free-form question-answering benchmarks demonstrate the superior performance and robustness of semantic density compared to prior approaches.

📄 PDF Abstract BibTeX arXiv:2405.13845

Code (1)

cognizant-ai-labs/semantic-density-paper 공식 구현 pytorch

Tasks

Misinformation Question AnsweringUncertainty Quantification

Methods 이 논문이 사용한 방법론

LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…

Eigenvalue Calibration for Semantic Embeddings of Large Language Models

2026-07-09 · Sebastian G. Gruber, Nassim Walha, Francis Bach, Florian Buettner arxiv

Uncertainty quantification is central to the reliable deployment of large language models (LLMs), and eigenvalues of semantic embeddings have recently emerged as a key tool in state-of-the-art methods. However, conventio…

Semantic Self-Distillation for Language Model Uncertainty

2026-02-04 · Edward Phillips, Sean Wu, Fredrik K. Gustafsson, Boyan Gao 외 arxiv

Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answe…

Answer Selection

ESI: Epistemic Uncertainty Quantification via Semantic-preserving Intervention for Large Language Models

2025-10-15 · Mingda Li, Xinyu Li, Weinan Zhang, Longxuan Ma arxiv

Uncertainty Quantification (UQ) is a promising approach to improve model reliability, yet quantifying the uncertainty of Large Language Models (LLMs) is non-trivial. In this work, we establish a connection between the un…

Computational Efficiency

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

2024-05-30 · Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen

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 detectin…

Text Generation Uncertainty Quantification

Uncertainty Quantification in Large Language Models Through Convex Hull Analysis

2024-06-28 · Ferhat Ozgur Catak, Murat Kuzlu

Uncertainty quantification approaches have been more critical in large language models (LLMs), particularly high-risk applications requiring reliable outputs. However, traditional methods for uncertainty quantification, …

Uncertainty Quantification