paper-with-me

홈 › Papers

Complementing Self-Consistency with Cross-Model Disagreement for Uncertainty Quantification

2026-04-18 · Kimia Hamidieh, Veronika Thost, Walter Gerych, Mikhail Yurochkin, Marzyeh Ghassemi arxiv

Large language models (LLMs) often produce confident yet incorrect responses, and uncertainty quantification is one potential solution to more robust usage. Recent works routinely rely on self-consistency to estimate aleatoric uncertainty (AU), yet this proxy collapses when models are overconfident and produce the same incorrect answer across samples. We analyze this regime and show that cross-model semantic disagreement is higher on incorrect answers precisely when AU is low. Motivated by this, we introduce an epistemic uncertainty (EU) term that operates in the black-box access setting: EU uses only generated text from a small, scale-matched ensemble and is computed as the gap between inter-model and intra-model sequence-semantic similarity. We then define total uncertainty (TU) as the sum of AU and EU. In a comprehensive study across five 7-9B instruction-tuned models and ten long-form tasks, TU improves ranking calibration and selective abstention relative to AU, and EU reliably flags confident failures where AU is low. We further characterize when EU is most useful via agreement and complementarity diagnostics.

📄 PDF Abstract BibTeX arXiv:2604.17112

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Similarity

Similar Papers 제목 키워드 기반

Co-training with High-Confidence Pseudo Labels for Semi-supervised Medical Image Segmentation

2023-01-11 · Zhiqiang Shen, Peng Cao, Hua Yang, Xiaoli Liu 외

Consistency regularization and pseudo labeling-based semi-supervised methods perform co-training using the pseudo labels from multi-view inputs. However, such co-training models tend to converge early to a consensus, deg…

Image SegmentationLeft Atrium SegmentationMedical Image SegmentationSegmentation+3

Deep Ensemble as a Gaussian Process Approximate Posterior

2022-04-30 · Zhijie Deng, Feng Zhou, Jianfei Chen, Guoqiang Wu 외

Deep Ensemble (DE) is an effective alternative to Bayesian neural networks for uncertainty quantification in deep learning. The uncertainty of DE is usually conveyed by the functional inconsistency among the ensemble mem…

Bayesian InferenceUncertainty Quantification

UfM*: Uncertainty from Motion* for DNN Depth Estimation Using Gaussians

2026-05-21 · Soumya Sudhakar, Sertac Karaman, Vivienne Sze arxiv

Reliable uncertainty estimation is critical for deploying monocular depth deep neural networks (DNNs) in safety-critical robotic systems. Conventional uncertainty methods such as ensembles and sampling-based approaches r…

Depth Estimation

Complementing Semi-Supervised Learning with Uncertainty Quantification

2022-07-22 · Ehsan Kazemi

The problem of fully supervised classification is that it requires a tremendous amount of annotated data, however, in many datasets a large portion of data is unlabeled. To alleviate this problem semi-supervised learning…

Uncertainty Quantification

Aligning LLM Uncertainty with Human Disagreement in Subjectivity Analysis

2026-05-11 · Junyu Lu, Deyi Ji, Xuanyi Liu, Lanyun Zhu 외 arxiv

Large language models for subjectivity analysis are typically trained with aggregated labels, which compress variations in human judgment into a single supervision signal. This paradigm overlooks the intrinsic uncertaint…

Subjectivity Analysis