English
Related papers

Related papers: Uncertainty-Aware Transformers: Conformal Predicti…

200 papers

Multimodal foundation models offer promising advancements for enhancing driving perception systems, but their high computational and financial costs pose challenges. We develop a method that leverages foundation models to refine predictions…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Yunhao Yang , Yuxin Hu , Mao Ye , Zaiwei Zhang , Zhichao Lu , Yi Xu , Ufuk Topcu , Ben Snyder

Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these traces often fail to faithfully represent the computations behind a model's predictions.…

Computation and Language · Computer Science 2026-05-26 Yoav Gur-Arieh , Ana Marasović , Mor Geva

Recent progress in large language models (LLMs) has enabled them to communicate their confidence in natural language, improving transparency and reliability. However, this expressiveness is often accompanied by systematic overconfidence,…

Computation and Language · Computer Science 2026-05-04 Ki Jung Seo , Sehun Lim , Taeuk Kim

Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks. However, they can be easily misled by unfaithful arguments during conversations, even when their original statements are correct. To this…

Computation and Language · Computer Science 2025-01-03 Yong Zhao , Yang Deng , See-Kiong Ng , Tat-Seng Chua

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 present a significant…

Robotics · Computer Science 2025-10-10 Shiyuan Yin , Chenjia Bai , Zihao Zhang , Junwei Jin , Xinxin Zhang , Chi Zhang , Xuelong Li

Transformer-based language models have been shown to be highly effective for several NLP tasks. In this paper, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large versions, and investigate how faithful…

Computation and Language · Computer Science 2023-12-01 Akshay Chaturvedi , Swarnadeep Bhar , Soumadeep Saha , Utpal Garain , Nicholas Asher

Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…

Artificial Intelligence · Computer Science 2026-01-13 Pranav Kallem

While pre-trained language models (PLMs) have become a de-facto standard promoting the accuracy of text classification tasks, recent studies find that PLMs often predict over-confidently. Although various calibration methods have been…

Computation and Language · Computer Science 2023-02-15 Jaeyoung Kim , Dongbin Na , Sungchul Choi , Sungbin Lim

Ambiguity is ubiquitous in natural language. Resolving ambiguous meanings is especially important in information retrieval tasks. While word embeddings carry semantic information, they fail to handle ambiguity well. Transformer models have…

Computation and Language · Computer Science 2023-07-26 Matthias Thurnbauer , Johannes Reisinger , Christoph Goller , Andreas Fischer

Pretrained transformers achieve the state of the art across tasks in natural language processing, motivating researchers to investigate their inner mechanisms. One common direction is to understand what features are important for…

Computation and Language · Computer Science 2021-08-06 Zhiying Jiang , Raphael Tang , Ji Xin , Jimmy Lin

Deep neural networks (DNNs) have become integral to a wide range of scientific and practical applications due to their flexibility and strong predictive performance. Despite their accuracy, however, DNNs frequently exhibit poor calibration,…

Machine Learning · Computer Science 2026-03-12 Sanne Ruijs , Alina Kosiakova , Farrukh Javed

Despite their impressive capabilities, Large Language Models (LLMs) exhibit unwanted uncertainty, a phenomenon where a model changes a previously correct answer into an incorrect one when re-prompted. This behavior undermines trust and…

Computation and Language · Computer Science 2025-10-28 Tiasa Singha Roy , Ayush Rajesh Jhaveri , Ilias Triantafyllopoulos

Confidence calibration is central to providing accurate and interpretable uncertainty estimates, especially under safety-critical scenarios. However, we find that existing calibration algorithms often overlook the issue of *proximity bias*,…

Machine Learning · Computer Science 2024-03-19 Miao Xiong , Ailin Deng , Pang Wei Koh , Jiaying Wu , Shen Li , Jianqing Xu , Bryan Hooi

When a machine learning model is deployed, its predictions can alter its environment, as better informed agents strategize to suit their own interests. With such alterations in mind, existing approaches to uncertainty quantification break.…

Machine Learning · Statistics 2024-11-05 Daniel Csillag , Claudio José Struchiner , Guilherme Tegoni Goedert

Machine learning classification tasks often benefit from predicting a set of possible labels with confidence scores to capture uncertainty. However, existing methods struggle with the high-dimensional nature of the data and the lack of…

Machine Learning · Computer Science 2024-07-08 Rui Luo , Zhixin Zhou

Federated learning has significantly advanced distributed training of machine learning models across decentralized data sources. However, existing frameworks often lack comprehensive solutions that combine uncertainty quantification,…

Machine Learning · Computer Science 2025-07-01 Sree Bhargavi Balija , Amitash Nanda , Debashis Sahoo

Predictions of uncertainty-aware models are diverse, ranging from single point estimates (often averaged over prediction samples) to predictive distributions, to set-valued or credal-set representations. We propose a novel unified…

Machine Learning · Computer Science 2025-02-18 Shireen Kudukkil Manchingal , Muhammad Mubashar , Kaizheng Wang , Fabio Cuzzolin

Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…

Machine Learning · Computer Science 2023-08-08 Shuang Ao , Stefan Rueger , Advaith Siddharthan

Unreliable predictions can occur when using artificial intelligence (AI) systems with negative consequences for downstream applications, particularly when employed for decision-making. Conformal prediction provides a model-agnostic…

Machine Learning · Computer Science 2024-01-15 Geethen Singh , Glenn Moncrieff , Zander Venter , Kerry Cawse-Nicholson , Jasper Slingsby , Tamara B Robinson

As large language models (LLMs) are increasingly used for factual question-answering, it becomes more important for LLMs to have the capability to communicate the likelihood that their answer is correct. For these verbalized expressions of…

Computation and Language · Computer Science 2025-12-15 Sophia Hager , David Mueller , Kevin Duh , Nicholas Andrews