English
Related papers

Related papers: When Evaluation Becomes a Side Channel: Regime Lea…

200 papers

Early-warning models built from Learning Management System (LMS) logs aim to predict end-of-course outcomes early enough to enable timely learner support. However, reported "early" performance is often inflated by temporal leakage. This…

Artificial Intelligence · Computer Science 2026-05-26 Ngoc Luyen Le , Marie-Hélène Abel , Bertrand Laforge

The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are…

Computation and Language · Computer Science 2025-06-06 Raphaël Millière

Large Language Models (LLMs) increasingly prioritize user validation over epistemic accuracy - a phenomenon known as sycophancy. We present The Silicon Mirror, an orchestration framework that dynamically detects user persuasion tactics and…

Artificial Intelligence · Computer Science 2026-04-03 Harshee Jignesh Shah

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like sycophancy to…

This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended goals. Specifically, we evaluate whether frontier models sabotage safety research when…

Artificial Intelligence · Computer Science 2026-04-02 Alexandra Souly , Robert Kirk , Jacob Merizian , Abby D'Cruz , Xander Davies

Generative artificial intelligence is increasingly being integrated into complex business workflows, fundamentally shifting the boundaries of managerial decision-making. However, the reliability of its strategic advice in ambiguous business…

Artificial Intelligence · Computer Science 2026-03-05 Sule Ozturk Birim , Fabrizio Marozzo , Yigit Kazancoglu

Existing AI evaluation practices often fail to capture how systems actually perform in low-resource environments, where operational constraints shape usability as much as model quality. Through a structured analysis of existing benchmark…

Artificial Intelligence · Computer Science 2026-05-28 Aakash Pant , Kavya Shah , Apoorv Agnihotri , Sneha Nikam , Prasaanth Balraj , Nakul Jain

The rapid growth of the large language model (LLM) ecosystem raises a critical question: are seemingly diverse models truly independent? Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral…

Artificial Intelligence · Computer Science 2026-04-10 Chenchen Kuai , Jiwan Jiang , Zihao Zhu , Hao Wang , Keshu Wu , Zihao Li , Yunlong Zhang , Chenxi Liu , Zhengzhong Tu , Zhiwen Fan , Yang Zhou

We localize the policy routing mechanism in alignment-trained language models. An intermediate-layer attention gate reads detected content and triggers deeper amplifier heads that boost the signal toward refusal. In smaller models the gate…

Computation and Language · Computer Science 2026-05-04 Gregory N. Frank

Agentic systems increasingly rely on language models to monitor their own behavior. For example, coding agents may self critique generated code for pull request approval or assess the safety of tool-use actions. We show that this design…

Artificial Intelligence · Computer Science 2026-03-06 Dipika Khullar , Jack Hopkins , Rowan Wang , Fabien Roger

Effective human-machine collaboration requires machine learning models to externalize uncertainty, so users can reflect and intervene when necessary. For language models, these representations of uncertainty may be impacted by sycophancy…

Computation and Language · Computer Science 2024-10-22 Anthony Sicilia , Mert Inan , Malihe Alikhani

Pretraining corpora contain extensive discourse about AI systems, yet the causal influence of this discourse on downstream alignment remains poorly understood. If prevailing descriptions of AI behaviour are predominantly negative, LLMs may…

Computation and Language · Computer Science 2026-02-23 Cameron Tice , Puria Radmard , Samuel Ratnam , Andy Kim , David Africa , Kyle O'Brien

Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…

Computation and Language · Computer Science 2026-05-26 Yihao Hu , Zhihao Wen , Xiujin Liu , Pan Wang , Xin Zhang , Wei Wu

As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…

Behavior cloning provides strong imitation learning guarantees when training and test environments share the same dynamics. However, in many deployment settings the test environment's transitions differ from training, and classical offline…

Machine Learning · Computer Science 2026-05-19 Surbhi Goel , Jonathan Pei , James Wang

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…

Machine Learning · Computer Science 2021-10-22 Osvaldo Simeone , Sangwoo Park , Joonhyuk Kang

Large language models (LLMs) are reshaping how knowledge is produced, with increasing reliance on AI systems for generation, summarization, and reasoning. While prior work has studied cognitive offloading in humans and model collapse in…

Human-Computer Interaction · Computer Science 2026-05-08 Xuening Wu , Yanlan Kang , Qianya Xu , Kexuan Xie , Jiaqi Mi , Honggang Wang , Yubin Liu , Zeping Chen

Exposure bias describes the phenomenon that a language model trained under the teacher forcing schema may perform poorly at the inference stage when its predictions are conditioned on its previous predictions unseen from the training…

Computation and Language · Computer Science 2020-04-02 Yifan Xu , Kening Zhang , Haoyu Dong , Yuezhou Sun , Wenlong Zhao , Zhuowen Tu

Large language models are increasingly being used to support network operations (NetOps) and artificial intelligence for IT operations (AIOps), including incident investigation, root-cause analysis, configuration synthesis, and limited…

Networking and Internet Architecture · Computer Science 2026-05-14 Muhammad Bilal , Jon Crowcroft , Ruizhi Wang , Xiaolong Xu , Schahram Dustdar

The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…

Artificial Intelligence · Computer Science 2025-03-11 Dany Moshkovich , Hadar Mulian , Sergey Zeltyn , Natti Eder , Inna Skarbovsky , Roy Abitbol
‹ Prev 1 4 5 6 7 8 10 Next ›