arXiv AI By Yujia Tong, Yuxi Wang, Yunyang Wan, Tian Zhang, Junhao Dong, Jingling Yuan

Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction

Read the original on arXiv AI →

arXiv:2606. 01850v1 Announce Type: new Abstract: Model compression techniques such as quantization and pruning are widely used to reduce the deployment cost of large language models (LLMs), with existing evaluations focusing almost exclusively on accuracy preservation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning
Aug 4

Conformalized Large Language Models under Configuration Shift

arXiv:2608. 01460v1 Announce Type: new Abstract: Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets with finite-sample coverage guarantees under exchangeability.

By Yuqicheng Zhu, Jialin Yu, Lin Li, Gengyuan Zhang, Zhen Yang, Steffen Staab, Puneet Dokania, Philip Torr, Jie Tang, Evgeny Kharlamov
arXiv AI
Jun 3

SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory

arXiv:2511. 16275v4 Announce Type: replace-cross Abstract: Reliable uncertainty quantification (UQ) is essential for deploying large language models (LLMs) in safety-critical scenarios, as it enables them to abstain from responding when uncertain, thereby avoiding hallucinations, i.

By Xingtao Zhao, Hao Peng, Dingli Su, Xianghua Zeng, Chunyang Liu, Jinzhi Liao, Philip S. Yu
Hugging Face Trending Papers
Jun 22

The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models

Recent advancements in Large Language Models (LLMs) have enabled sophisticated reasoning and content generation, yet their inherent stochasticity poses significant challenges for ensuring predictive credibility. While traditional uncertainty taxonomy paradigms, such as the dichotomy of aleatoric and epistemic uncertainties, provide conceptual foundations, they often fail to capture the multi-component and multi-stage nature of LLM generation and struggle to evaluate the effectiveness of various Uncertainty Quantification (UQ) methods.