English
Related papers

Related papers: Are LLM Uncertainty and Correctness Encoded by the…

200 papers

In many applications of LLMs, natural language responses often have an underlying structure such as representing discrete labels, numerical values, or graphs. Yet, existing decoding and uncertainty estimation methods operate only in…

Machine Learning · Computer Science 2026-05-25 Tim Tomov , Dominik Fuchsgruber , Stephan Günnemann

There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…

Computation and Language · Computer Science 2021-12-14 Nicola De Cao , Leon Schmid , Dieuwke Hupkes , Ivan Titov

Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhance trust and task accuracy. Yet existing methods face…

Computation and Language · Computer Science 2025-09-30 Linwei Tao , Yi-Fan Yeh , Bo Kai , Minjing Dong , Tao Huang , Tom A. Lamb , Jialin Yu , Philip H. S. Torr , Chang Xu

Large language models are increasingly relied upon as sources of information, but their propensity for generating false or misleading statements with high confidence poses risks for users and society. In this paper, we confront the critical…

Large language models (LLMs) often exhibit deficient reasoning or generate hallucinations. To address these, studies prefixed with "Self-" such as Self-Consistency, Self-Improve, and Self-Refine have been initiated. They share a…

Computation and Language · Computer Science 2024-09-19 Xun Liang , Shichao Song , Zifan Zheng , Hanyu Wang , Qingchen Yu , Xunkai Li , Rong-Hua Li , Yi Wang , Zhonghao Wang , Feiyu Xiong , Zhiyu Li

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Machine Learning · Computer Science 2024-08-22 Samyak Jain , Ekdeep Singh Lubana , Kemal Oksuz , Tom Joy , Philip H. S. Torr , Amartya Sanyal , Puneet K. Dokania

Homogeneity bias in Large Language Models (LLMs) refers to their tendency to homogenize the representations of some groups compared to others. Previous studies documenting this bias have predominantly used encoder models, which may have…

Computation and Language · Computer Science 2024-12-13 Messi H. J. Lee , Calvin K. Lai

In this paper, we address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. Specifically, we identify a critical issue of ''$\textbf{reconstruction error…

Machine Learning · Computer Science 2025-02-21 Weizhong Huang , Yuxin Zhang , Xiawu Zheng , Fei Chao , Rongrong Ji

Multimodal large language models (MLLMs) combine visual and textual data for tasks such as image captioning and visual question answering. Proper uncertainty calibration is crucial, yet challenging, for reliable use in areas like healthcare…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Zijun Chen , Wenbo Hu , Guande He , Zhijie Deng , Zheng Zhang , Richang Hong

Feature attribution is widely used in interpretable machine learning to explain how influential each measured input feature value is for an output inference. However, measurements can be uncertain, and it is unclear how the awareness of…

Machine Learning · Computer Science 2021-01-26 Danding Wang , Wencan Zhang , Brian Y. Lim

The Universality Hypothesis in large language models (LLMs) claims that different models converge towards similar concept representations in their latent spaces. Providing evidence for this hypothesis would enable researchers to exploit…

Machine Learning · Computer Science 2025-05-22 Michael Lan , Philip Torr , Austin Meek , Ashkan Khakzar , David Krueger , Fazl Barez

Large language models (LLMs) often miscommunicate their uncertainty: repeated queries can produce divergent answers, yet generated responses are typically unhedged or hedged in ways that do not reflect this variability. This conveys…

Computation and Language · Computer Science 2025-10-15 Bryan Eikema , Evgenia Ilia , José G. C. de Souza , Chrysoula Zerva , Wilker Aziz

As large language models (LLMs) are increasingly deployed in critical decision-making systems, the lack of reliable methods to measure their uncertainty presents a fundamental trustworthiness risk. We introduce a normalized confidence score…

Machine Learning · Computer Science 2026-03-10 Xie Xiaohu , Liu Xiaohu , Yao Benjamin

Large language models (LLMs) demonstrate remarkable capabilities but face challenges from hallucinations, which typically arise from insufficient knowledge or context. While instructing LLMs to acknowledge knowledge limitations by…

Computation and Language · Computer Science 2025-08-08 Jiaqi Li , Yixuan Tang , Yi Yang

Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the…

Computation and Language · Computer Science 2024-03-13 Shiqi Chen , Miao Xiong , Junteng Liu , Zhengxuan Wu , Teng Xiao , Siyang Gao , Junxian He

Sparse Autoencoders (SAEs) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number of features in the SAE, hierarchical features tend to split…

Computation and Language · Computer Science 2025-11-18 David Chanin , James Wilken-Smith , Tomáš Dulka , Hardik Bhatnagar , Satvik Golechha , Joseph Bloom

Intrinsic self-correction was proposed to improve LLMs' responses via feedback prompts solely based on their inherent capability. However, recent works show that LLMs' intrinsic self-correction fails without oracle labels as feedback…

Computation and Language · Computer Science 2025-07-16 Qingjie Zhang , Di Wang , Haoting Qian , Yiming Li , Tianwei Zhang , Minlie Huang , Ke Xu , Hewu Li , Yan Liu , Han Qiu

LLMs can estimate Hospital Anxiety and Depression Scale (HADS) scores from speech in a zero-shot manner, but clinical deployment requires reliability across three dimensions: intra-model consistency, ASR robustness, and evidence…

Computation and Language · Computer Science 2026-05-12 Erfan Loweimi , Sofia de la Fuente Garcia , Samira Loveymi , Hadi Daneshvar , Saturnino Luz

This study introduces a framework for evaluating consistency in large language model (LLM) binary text classification, addressing the lack of established reliability assessment methods. Adapting psychometric principles, we determine sample…

Computation and Language · Computer Science 2025-12-23 Fadel M. Megahed , Ying-Ju Chen , L. Allision Jones-Farmer , Younghwa Lee , Jiawei Brooke Wang , Inez M. Zwetsloot

Despite their widespread use, the mechanisms by which large language models (LLMs) represent and regulate uncertainty in next-token predictions remain largely unexplored. This study investigates two critical components believed to influence…

Machine Learning · Computer Science 2024-11-11 Alessandro Stolfo , Ben Wu , Wes Gurnee , Yonatan Belinkov , Xingyi Song , Mrinmaya Sachan , Neel Nanda