English
Related papers

Related papers: Asking Is Not Enough: Protocol Sensitivity in LLM …

200 papers

Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deployment. Existing calibration methods usually depend on labels or repeated sampling at…

Machine Learning · Computer Science 2026-04-22 Thomas Zollo , Jimmy Wang , Richard Zemel

In real-world task-oriented dialogue (TOD) settings, agents are required to strictly adhere to complex instructions while conducting multi-turn conversations with customers. These instructions are typically presented in natural language…

Computation and Language · Computer Science 2025-11-21 Sarik Ghazarian , Abhinav Gullapalli , Swair Shah , Anurag Beniwal , Nanyun Peng , Narayanan Sadagopan , Zhou Yu

Large language models (LLMs) are increasingly deployed in domains where errors carry high social, scientific, or safety costs. Yet standard confidence estimators, such as token likelihood, semantic similarity and multi-sample consistency,…

Computation and Language · Computer Science 2026-02-03 Pengyue Yang , Jiawen Wen , Haolin Jin , Linghan Huang , Huaming Chen , Ling Chen

A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated…

Computation and Language · Computer Science 2026-03-03 David Bani-Harouni , Chantal Pellegrini , Paul Stangel , Ege Özsoy , Kamilia Zaripova , Nassir Navab , Matthias Keicher

Large Language Models (LLMs) are increasingly applied to complex telecommunications tasks, including 3GPP specification analysis and O-RAN network troubleshooting. However, a critical limitation remains: LLM-generated confidence scores are…

Machine Learning · Computer Science 2026-04-16 Anton Saenko , Pranshav Gajjar , Abiodun Ganiyu , Vijay K. Shah

Large Language Models (LLMs) are widely used as automated judges, where practical value depends on both accuracy and trustworthy, risk-aware judgments. Existing approaches predominantly focus on accuracy, overlooking the necessity of…

Artificial Intelligence · Computer Science 2025-08-19 Zailong Tian , Zhuoheng Han , Yanzhe Chen , Haozhe Xu , Xi Yang , Richeng Xuan , Houfeng Wang , Lizi Liao

LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool results, retrieved evidence, artifacts, and safety boundaries that future responses must…

Machine Learning · Computer Science 2026-05-19 Natalia Trukhina , Vadim Vashkelis

Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of…

Current question-answering benchmarks predominantly focus on accuracy in realizable prediction tasks. Conditioned on a question and answer-key, does the most likely token match the ground truth? Such benchmarks necessarily fail to evaluate…

Machine Learning · Computer Science 2024-12-02 André F. Cruz , Moritz Hardt , Celestine Mendler-Dünner

People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are trained to predict the next token solely from text input, not underlying intent. Because written…

Computation and Language · Computer Science 2026-03-13 Nadav Kunievsky , James A. Evans

Language model calibration refers to the alignment between the confidence of the model and the actual performance of its responses. While previous studies point out the overconfidence phenomenon in Large Language Models (LLMs) and show that…

Computation and Language · Computer Science 2025-03-04 Jixuan Leng , Chengsong Huang , Banghua Zhu , Jiaxin Huang

Overconfidence and underconfidence in machine learning classifiers is measured by calibration: the degree to which the probabilities predicted for each class match the accuracy of the classifier on that prediction. How one measures…

Machine Learning · Computer Science 2020-08-11 Jeremy Nixon , Mike Dusenberry , Ghassen Jerfel , Timothy Nguyen , Jeremiah Liu , Linchuan Zhang , Dustin Tran

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks in various domains. Despite their impressive performance, they can be unreliable due to factual errors in their generations. Assessing their…

Computation and Language · Computer Science 2024-03-26 Jiahui Geng , Fengyu Cai , Yuxia Wang , Heinz Koeppl , Preslav Nakov , Iryna Gurevych

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

Machine Learning · Computer Science 2025-02-11 Brian Formento , Chuan Sheng Foo , See-Kiong Ng

Calibration, the alignment between model confidence and prediction accuracy, is critical for the reliable deployment of large language models (LLMs). Existing works neglect to measure the generalization of their methods to other prompt…

Computation and Language · Computer Science 2025-01-08 Yuxi Xia , Pedro Henrique Luz de Araujo , Klim Zaporojets , Benjamin Roth

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in various perception and reasoning tasks. Despite this success, ensuring their reliability in practical deployment necessitates robust confidence…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Yunkai Dang , Yifan Jiang , Yizhu Jiang , Anqi Chen , Wenbin Li , Yang Gao

Reliable uncertainty quantification (UQ) is essential for ensuring trustworthy downstream use of large language models, especially when they are deployed in decision-support and other knowledge-intensive applications. Model certainty can be…

Computation and Language · Computer Science 2025-11-04 Autumn Toney-Wails , Ryan Wails

The text produced by language models (LMs) can exhibit specific `behaviors,' such as a failure to follow alignment training, that we hope to detect and react to during deployment. Identifying these behaviors can often only be done post…

Computation and Language · Computer Science 2025-09-24 Dhananjay Ashok , Jonathan May

Large language models are increasingly deployed in settings where reliability matters, yet output-level uncertainty signals such as token probabilities, entropy, and self-consistency can become brittle under calibration--deployment…

Computation and Language · Computer Science 2026-04-20 Yanli Wang , Peng Kuang , Xiaoyu Han , Kaidi Xu , Haohan Wang

Many constructs that characterize language, like its complexity or emotionality, have a naturally continuous semantic structure; a public speech is not just "simple" or "complex," but exists on a continuum between extremes. Although large…

Computation and Language · Computer Science 2025-09-23 Hauke Licht , Rupak Sarkar , Patrick Y. Wu , Pranav Goel , Niklas Stoehr , Elliott Ash , Alexander Miserlis Hoyle