English
Related papers

Related papers: Evaluation Awareness in Language Models Has Limite…

200 papers

Large language models (LLMs) can internally distinguish between evaluation and deployment contexts, a behaviour known as \emph{evaluation awareness}. This undermines AI safety evaluations, as models may conceal dangerous capabilities during…

Artificial Intelligence · Computer Science 2025-11-11 Maheep Chaudhary , Ian Su , Nikhil Hooda , Nishith Shankar , Julia Tan , Kevin Zhu , Ryan Lagasse , Vasu Sharma , Ashwinee Panda

Recent advances in vision language models (VLMs) offer reasoning capabilities, yet how these unfold and integrate visual and textual information remains unclear. We analyze reasoning dynamics in 18 VLMs covering instruction-tuned and…

Computation and Language · Computer Science 2026-04-28 Danae Sánchez Villegas , Samuel Lewis-Lim , Nikolaos Aletras , Desmond Elliott

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

Computation and Language · Computer Science 2025-11-04 Sriram Balasubramanian , Samyadeep Basu , Soheil Feizi

Uncertainty calibration is essential for the safe deployment of large language models (LLMs), particularly when users rely on verbalized confidence estimates. While prior work has focused on classifiers or short-form generation, confidence…

Computation and Language · Computer Science 2025-06-05 Chaeyun Jang , Moonseok Choi , Yegon Kim , Hyungi Lee , Juho Lee

Vision-language models (VLMs) often produce chain-of-thought (CoT) explanations that sound plausible yet fail to reflect the underlying decision process, undermining trust in high-stakes clinical use. Existing evaluations rarely catch this…

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) often exhibit significant behavioral shifts when they perceive a change from a real-world deployment context to a controlled evaluation setting, a phenomenon known as "evaluation awareness." This discrepancy…

Computation and Language · Computer Science 2025-12-05 Lang Xiong , Nishant Bhargava , Jianhang Hong , Jeremy Chang , Haihao Liu , Vasu Sharma , Kevin Zhu

Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…

Computation and Language · Computer Science 2026-03-03 Tim Tian Hua , Andrew Qin , Samuel Marks , Neel Nanda

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized…

Computation and Language · Computer Science 2026-05-28 Katharina Deckenbach , Haritz Puerto , Jonas Geiping , Sahar Abdelnabi

Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expressed confidence is tied to the reasoning, knowledge, or decision making of the…

Machine Learning · Computer Science 2026-01-13 Jiawei Wang , Yanfei Zhou , Siddartha Devic , Deqing Fu

Reasoning-focused LLMs sometimes alter their behavior when they detect that they are being evaluated, which can lead them to optimize for test-passing performance or to comply more readily with harmful prompts if real-world consequences…

Computation and Language · Computer Science 2025-10-29 Sahar Abdelnabi , Ahmed Salem

Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…

Artificial Intelligence · Computer Science 2026-04-14 Mengxuan Wang , Yuxin Chen , Gang Xu , Tao He , Hongjie Jiang , Ming Li

While Vision-Language Models (VLMs) have shown promise in textual understanding, they face significant challenges when handling long context and complex reasoning tasks. In this paper, we dissect the internal mechanisms governing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Rongcan Pei , Huan Li , Fang Guo , Qi Zhu

Vision-language models (VLMs) are increasingly deployed in high-stakes settings where reliable uncertainty quantification (UQ) is as important as predictive accuracy. Extended reasoning via chain-of-thought (CoT) prompting or…

Machine Learning · Computer Science 2026-03-18 Robert Welch , Emir Konuk , Kevin Smith

Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Weihao Xuan , Qingcheng Zeng , Heli Qi , Junjue Wang , Naoto Yokoya

Large reasoning models (LRMs) have recently demonstrated impressive capabilities in complex reasoning tasks by leveraging increased test-time computation and exhibiting behaviors reminiscent of human-like self-reflection. While LRMs show a…

Computation and Language · Computer Science 2025-10-21 Qingcheng Zeng , Weihao Xuan , Leyang Cui , Rob Voigt

As foundation models grow increasingly more intelligent, reliable and trustworthy safety evaluation becomes more indispensable than ever. However, an important question arises: Whether and how an advanced AI system would perceive the…

Artificial Intelligence · Computer Science 2026-03-16 Yihe Fan , Wenqi Zhang , Xudong Pan , Min Yang

Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT…

Computation and Language · Computer Science 2023-12-12 Miles Turpin , Julian Michael , Ethan Perez , Samuel R. Bowman

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising…

Computation and Language · Computer Science 2025-09-03 Xiaomin Li , Zhou Yu , Zhiwei Zhang , Xupeng Chen , Ziji Zhang , Yingying Zhuang , Narayanan Sadagopan , Anurag Beniwal

We investigate whether large language models (LLMs) display human-like cognitive biases, focusing on potential implications for assistance in judicial sentencing, a decision-making system where fairness is paramount. Two of the most…

Computers and Society · Computer Science 2026-03-12 Sierra S. Liu
‹ Prev 1 2 3 10 Next ›