paper-with-me

홈 › Papers

Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models

2026-04-01 · Ponhvoan Srey, Quang Minh Nguyen, Xiaobao Wu, Anh Tuan Luu arxiv

Uncertainty estimation (UE) aims to detect hallucinated outputs of large language models (LLMs) to improve their reliability. However, UE metrics often exhibit unstable performance across configurations, which significantly limits their applicability. In this work, we formalise this phenomenon as proxy failure, since most UE metrics originate from model behaviour, rather than being explicitly grounded in the factual correctness of LLM outputs. With this, we show that UE metrics become non-discriminative precisely in low-information regimes. To alleviate this, we propose Truth AnChoring (TAC), a post-hoc calibration method to remedy UE metrics, by mapping the raw scores to truth-aligned scores. Even with noisy and few-shot supervision, our TAC can support the learning of well-calibrated uncertainty estimates, and presents a practical calibration protocol. Our findings highlight the limitations of treating heuristic UE metrics as direct indicators of truth uncertainty, and position our TAC as a necessary step toward more reliable uncertainty estimation for LLMs. The code repository is available at https://github.com/ponhvoan/TruthAnchor/.

📄 PDF Abstract BibTeX arXiv:2604.00445

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Reliable Multimodal Trajectory Prediction via Error Aligned Uncertainty Optimization

2022-12-09 · Neslihan Kose, Ranganath Krishnan, Akash Dhamasia, Omesh Tickoo 외

Reliable uncertainty quantification in deep neural networks is very crucial in safety-critical applications such as automated driving for trustworthy and informed decision-making. Assessing the quality of uncertainty est…

Decision Makingmotion predictionPredictionStructured Prediction+2

Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation

2025-10-09 · Shiyuan Yin, Chenjia Bai, Zihao Zhang, Junwei Jin 외 arxiv

Large language models (LLMs) demonstrate advanced reasoning abilities, enabling robots to understand natural language instructions and generate high-level plans with appropriate grounding. However, LLM hallucinations pre…

U$^{2}$Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation

2026-04-11 · Xunpei Sun, Wenwei Lin, Yi Chang, Gang Chen arxiv

Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose U$^{2}$Flow, the first recurrent unsupervised framework that jointly estimates …

Optical Flow Estimation

On the Effect of Inter-observer Variability for a Reliable Estimation of Uncertainty of Medical Image Segmentation

2018-06-07 · Alain Jungo, Raphael Meier, Ekin Ermis, Marcela Blatti-Moreno 외

Uncertainty estimation methods are expected to improve the understanding and quality of computer-assisted methods used in medical applications (e.g., neurosurgical interventions, radiotherapy planning), where automated m…

Image SegmentationMedical Image SegmentationSegmentationSemantic Segmentation

Generalization of Fine-Tuned Uncertainty Communication and Metacognition in Large Language Models

2025-09-30 · Mark Steyvers, Catarina Belem, Padhraic Smyth arxiv

Background. Large language models are increasingly used in settings where confident but incorrect answers can mislead users. Reliable uncertainty communication requires a form of metacognition: monitoring when one's own …

General Knowledge