English
Related papers

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

200 papers

Large language models are often not just wrong, but \emph{confidently wrong}: when they produce factually incorrect answers, they tend to verbalize overly high confidence rather than signal uncertainty. Such verbalized overconfidence can…

Computation and Language · Computer Science 2026-04-03 Tianyi Zhao , Yinhan He , Wendy Zheng , Yujie Zhang , Chen Chen

The increased use of Large Language Models (LLMs) in sensitive domains leads to growing interest in how their confidence scores correspond to fairness and bias. This study examines the alignment between LLM-predicted confidence and…

Computation and Language · Computer Science 2026-01-13 Ahmed Sabir , Markus Kängsepp , Rajesh Sharma

Large language models (LLMs) tend to verbalize confidence scores that are largely detached from their actual accuracy, yet the geometric relationship governing this behavior remain poorly understood. In this work, we present a mechanistic…

Computation and Language · Computer Science 2026-04-02 Miranda Muqing Miao , Lyle Ungar

Large language models (LLMs) are increasingly used as automated judges and synthetic labelers, especially in low-label settings. Yet these systems are stochastic and often overconfident, which makes deployment decisions difficult when…

Machine Learning · Computer Science 2026-03-19 Maxim Khomiakov , Jes Frellsen

Multiple Choice Question (MCQ) tests are among the most used methods for evaluating large language models (LLMs). Besides checking the correctness of the selected answer, evaluations often consider the model's confidence through the…

Computation and Language · Computer Science 2026-05-05 Tairan Fu , Javier Conde , Gonzalo Martínez , María Grandury , Pedro Reviriego

Safety benchmarks are routinely treated as evidence about how a language model will behave once deployed, but this inference is fragile if behavior depends on whether a prompt looks like an evaluation. We define evaluation-context…

Computation and Language · Computer Science 2026-05-08 Florian A. D. Burnat , Brittany I. Davidson

Pre-trained language models (PLMs) may fail in giving reliable estimates of their predictive uncertainty. We take a close look into this problem, aiming to answer two questions: (1) Do PLMs learn to become calibrated in the training…

Computation and Language · Computer Science 2023-05-09 Yangyi Chen , Lifan Yuan , Ganqu Cui , Zhiyuan Liu , Heng Ji

Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We study whether post-training can make a model's self-assessment explicit: when the model is…

Machine Learning · Computer Science 2026-05-15 Junyu Guo , Shangding Gu , Ming Jin , Costas Spanos , Javad Lavaei

Vision-Language Models (VLMs) have achieved remarkable progress in complex visual understanding across scientific and reasoning tasks. While performance benchmarking has advanced our understanding of these capabilities, the critical…

Artificial Intelligence · Computer Science 2026-01-27 Asif Azad , Mohammad Sadat Hossain , MD Sadik Hossain Shanto , M Saifur Rahman , Md Rizwan Parvez

Large language models, LLMs, are increasingly deployed in multiturn settings where earlier responses shape later ones, making reliability dependent on whether a conversation remains consistent over time. When this consistency degrades…

Computation and Language · Computer Science 2026-04-20 Wael Hafez , Amir Nazeri

As large language models (LLMs) are increasingly used in high-stakes domains, accurately assessing their confidence is crucial. Humans typically express confidence through epistemic markers (e.g., "fairly confident") instead of numerical…

Computation and Language · Computer Science 2026-04-14 Jiayu Liu , Qing Zong , Weiqi Wang , Yangqiu Song

Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context. In this work, we…

Computation and Language · Computer Science 2026-03-18 Tianyi Zhou , Johanne Medina , Sanjay Chawla

Large Language Models (LLMs) increasingly rely on long-form, multi-step reasoning to solve complex tasks such as mathematical problem solving and scientific question answering. Despite strong performance, existing confidence estimation…

Computation and Language · Computer Science 2026-01-21 Zhenjiang Mao , Anirudhh Venkat , Artem Bisliouk , Akshat Kothiyal , Sindhura Kumbakonam Subramanian , Saithej Singhu , Ivan Ruchkin

Large language models (LLMs) often present answers with high apparent confidence despite lacking an explicit mechanism for reasoning about certainty or truth. While existing benchmarks primarily evaluate single-turn accuracy, truthfulness…

Computation and Language · Computer Science 2026-03-05 Mohammadreza Saadat , Steve Nemzer

Confidence estimation (CE) indicates how reliable the answers of large language models are and impacts user trust and decision-making. Existing evaluations mainly concern the alignment between confidence and correctness, but ignore the…

Computation and Language · Computer Science 2026-05-29 Yuxi Xia , Dennis Ulmer , Terra Blevins , Yihong Liu , Hinrich Schütze , Benjamin Roth

Knowledge probing quantifies how much relational knowledge a language model (LM) has acquired during pre-training. Existing knowledge probes evaluate model capabilities through metrics like prediction accuracy and precision. Such…

Computation and Language · Computer Science 2026-01-28 Christopher Kissling , Elena Merdjanovska , Alan Akbik

Verbalized confidence, in which LLMs report a numerical certainty score, is widely used to estimate uncertainty in black-box settings, yet the confidence scale itself (typically 0--100) is rarely examined. We show that this design choice is…

Artificial Intelligence · Computer Science 2026-03-11 Yuyang Dai

Large language models (LLMs) are increasingly used as automatic judges for summarization and dialogue evaluation. Prior work has documented biases such as position, verbosity, and style preferences, but largely focuses on outcomes, leaving…

Computation and Language · Computer Science 2026-05-26 Riya Tapwal , Abhishek Kumar , Carsten Maple

Large language models (LLMs) are increasingly deployed in agentic and multi-turn workflows where they are tasked to perform actions of significant consequence. In order to deploy them reliably and manage risky outcomes in these settings, it…

Machine Learning · Computer Science 2026-02-10 Arka Pal , Teo Kitanovski , Arthur Liang , Akilesh Potti , Micah Goldblum

Large vision-language models (LVLMs) demonstrate strong visual question answering (VQA) capabilities but are shown to hallucinate. A reliable model should perceive its knowledge boundaries-knowing what it knows and what it does not. This…

Computation and Language · Computer Science 2025-08-27 Zhikai Ding , Shiyu Ni , Keping Bi