English
Related papers

Related papers: Subversion Strategy Eval: Can language models stat…

200 papers

Recent advancements in large language models have demonstrated that extended inference through techniques can markedly improve performance, yet these gains come with increased computational costs and the propagation of inherent biases found…

Computation and Language · Computer Science 2025-02-10 Edward Hong Wang , Cynthia Xin Wen

Adjustable autonomy refers to entities dynamically varying their own autonomy, transferring decision-making control to other entities (typically agents transferring control to human users) in key situations. Determining whether and when…

Artificial Intelligence · Computer Science 2011-06-24 D. V. Pynadath , P. Scerri , M. Tambe

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows…

For an AI's training process to successfully impart a desired goal, it is important that the AI does not attempt to resist the training. However, partially learned goals will often incentivize an AI to avoid further goal updates, as most…

Artificial Intelligence · Computer Science 2025-10-20 Rubi Hudson

Interest in the concept of AI-driven harmful manipulation is growing, yet current approaches to evaluating it are limited. This paper introduces a framework for evaluating harmful AI manipulation via context-specific human-AI interaction…

Artificial Intelligence (AI) planning is a flourishing research and development discipline that provides powerful tools for searching a course of action that achieves some user goal. While these planning tools show excellent performance on…

Artificial Intelligence · Computer Science 2021-02-23 Sebastian Graef , Ilche Georgievski

We present two categories of model-agnostic adversarial strategies that reveal the weaknesses of several generative, task-oriented dialogue models: Should-Not-Change strategies that evaluate over-sensitivity to small and…

Computation and Language · Computer Science 2018-09-07 Tong Niu , Mohit Bansal

This paper introduces a methodological framework for empirically testing AI alignment strategies through structured multi-model dialogue. Drawing on Peace Studies traditions - particularly interest-based negotiation, conflict…

Artificial Intelligence · Computer Science 2026-01-29 Gray Cox

Strategic adaptation -- the ability to adjust interaction behavior in response to changing constraints and leverage -- is a central goal of negotiation training and an emerging target for AI coaching systems. However, adaptation is…

Human-Computer Interaction · Computer Science 2026-02-05 Mobasshira Akter Urmi , Raiyan Abdul Baten

State-of-the-art conversational AI systems raise concerns due to their potential risks of generating unsafe, toxic, unethical, or dangerous content. Previous works have developed datasets to teach conversational agents the appropriate…

Computation and Language · Computer Science 2024-02-02 Souvik Das , Rohini K. Srihari

Active inference (AI) is a persuasive theoretical framework from computational neuroscience that seeks to describe action and perception as inference-based computation. However, this framework has yet to provide practical sensorimotor…

Machine Learning · Computer Science 2020-10-02 Joe Watson , Abraham Imohiosen , Jan Peters

As large language models (LLMs) are increasingly deployed as interactive agents, open-ended human-AI interactions can involve deceptive behaviors with serious real-world consequences, yet existing evaluations remain largely…

Artificial Intelligence · Computer Science 2026-02-09 Yichen Wu , Qianqian Gao , Xudong Pan , Geng Hong , Min Yang

Prominent AI companies are producing 'safety frameworks' as a type of voluntary self-governance. These statements purport to establish risk thresholds and safety procedures for the development and deployment of highly capable AI.…

Computers and Society · Computer Science 2025-10-14 Sam Coggins , Alexander K. Saeri , Katherine A. Daniell , Lorenn P. Ruster , Jessie Liu , Jenny L. Davis

Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that…

Cryptography and Security · Computer Science 2024-07-03 Erik Jones , Anca Dragan , Jacob Steinhardt

Transfer learning is a popular method for tuning pretrained (upstream) models for different downstream tasks using limited data and computational resources. We study how an adversary with control over an upstream model used in transfer…

Machine Learning · Computer Science 2023-03-22 Yulong Tian , Fnu Suya , Anshuman Suri , Fengyuan Xu , David Evans

Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…

Multiagent Systems · Computer Science 2021-12-22 Jiachen Yang , Ethan Wang , Rakshit Trivedi , Tuo Zhao , Hongyuan Zha

Agentic AI systems - systems that can pursue goals through multi-step planning and tool-mediated action with limited direct supervision - are moving from experimental prototypes to enterprise deployments. This transition introduces tensions…

Computers and Society · Computer Science 2026-05-21 Nelly Dux , Cristina Alaimo , Philippe Roussiere , Abhishek Kumar Mishra

Human-AI collaboration has the potential to transform various domains by leveraging the complementary strengths of human experts and Artificial Intelligence (AI) systems. However, unobserved confounding can undermine the effectiveness of…

Human-Computer Interaction · Computer Science 2025-02-27 Ruijiang Gao , Mingzhang Yin