English
Related papers

Related papers: When Prohibitions Become Permissions: Auditing Neg…

200 papers

As artificial intelligence (AI) systems play an increasingly prominent role in human decision-making, challenges surface in the realm of human-AI interactions. One challenge arises from the suboptimal AI policies due to the inadequate…

Machine Learning · Statistics 2024-03-22 Guanting Chen , Xiaocheng Li , Chunlin Sun , Hanzhao Wang

Most frameworks for assessing the openness of AI systems use narrow criteria such as availability of data, model, code, documentation, and licensing terms. However, to evaluate whether the intended effects of openness - such as…

Computers and Society · Computer Science 2025-10-14 Tamara Paris , Shalaleh Rismani

An auditor instructs an AI assistant: "open each file individually using the Read tool -- no scripts, no agents." The AI replies "Yes" -- then issues a single batched call summarizing all fifty files at once. We call this the Compliance…

Computation and Language · Computer Science 2026-05-05 Kwan Soo Shin

When AI systems explain their reasoning step-by-step, practitioners often assume these explanations reveal what actually influenced the AI's answer. We tested this assumption by embedding hints into questions and measuring whether models…

Artificial Intelligence · Computer Science 2026-01-06 Deep Pankajbhai Mehta

We examine two properties of AI systems: capability (what a system can do) and steerability (how reliably one can shift behavior toward intended outcomes). A central question is whether capability growth reduces steerability and risks…

Computation and Language · Computer Science 2026-01-07 Jakub Hoscilowicz

Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We…

Machine Learning · Computer Science 2026-05-04 Gregory N. Frank

Previous research on expert advice-taking shows that humans exhibit two contradictory behaviors: on the one hand, people tend to overvalue their own opinions undervaluing the expert opinion, and on the other, people often defer to other…

Computation and Language · Computer Science 2023-10-24 Elena Sergeeva , Anastasia Sergeeva , Huiyun Tang , Kerstin Bongard-Blanchy , Peter Szolovits

Large language models are trained to refuse harmful requests, but can they accurately predict when they will refuse before responding? We investigate this question through a systematic study where models first predict their refusal…

Computation and Language · Computer Science 2026-04-02 Tanay Gondil

As artificial intelligence systems become increasingly agentic, capable of general reasoning, planning, and value prioritization, current safety practices that treat obedience as a proxy for ethical behavior are becoming inadequate. This…

Artificial Intelligence · Computer Science 2025-07-04 Joseph Boland

In decision support applications of AI, the AI algorithm's output is framed as a suggestion to a human user. The user may ignore this advice or take it into consideration to modify their decision. With the increasing prevalence of such…

Artificial Intelligence · Computer Science 2022-06-03 Kailas Vodrahalli , Roxana Daneshjou , Tobias Gerstenberg , James Zou

Since the release of OpenAI's ChatGPT, generative language models have attracted extensive public attention. The increased usage has highlighted generative models' broad utility, but also revealed several forms of embedded bias. Some is…

Artificial Intelligence · Computer Science 2023-06-16 Max Reuter , William Schulze

Scalable oversight protocols aim to empower evaluators to accurately verify AI models more capable than themselves. However, human evaluators are subject to biases that can lead to systematic errors. We conduct two studies examining the…

Human-Computer Interaction · Computer Science 2025-07-29 Gabriel Recchia , Chatrik Singh Mangat , Jinu Nyachhyon , Mridul Sharma , Callum Canavan , Dylan Epstein-Gross , Muhammed Abdulbari

Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a…

Computation and Language · Computer Science 2025-12-22 Riad Ahmed Anonto , Md Labid Al Nahiyan , Md Tanvir Hassan

As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conventional permission…

Cryptography and Security · Computer Science 2025-11-25 Yuhao Wu , Ke Yang , Franziska Roesner , Tadayoshi Kohno , Ning Zhang , Umar Iqbal

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for…

Computation and Language · Computer Science 2025-07-17 Joe Needham , Giles Edkins , Govind Pimpale , Henning Bartsch , Marius Hobbhahn

Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless…

Computation and Language · Computer Science 2024-06-12 MohammadHossein Rezaei , Eduardo Blanco

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

Negation instructions such as 'do not mention $X$' can paradoxically increase the accessibility of $X$ in human thought, a phenomenon known as ironic rebound. Large language models (LLMs) face the same challenge: suppressing a concept…

Computation and Language · Computer Science 2025-11-18 Logan Mann , Nayan Saxena , Sarah Tandon , Chenhao Sun , Savar Toteja , Kevin Zhu

A key component of building safe and reliable language models is enabling the models to appropriately refuse to follow certain instructions or answer certain questions. We may want models to output refusal messages for various categories of…

Machine Learning · Computer Science 2025-09-01 Neel Jain , Aditya Shrivastava , Chenyang Zhu , Daben Liu , Alfy Samuel , Ashwinee Panda , Anoop Kumar , Micah Goldblum , Tom Goldstein

AI-assisted code review tools typically operate as generic "expert reviewer" agents, producing homogeneous findings regardless of the analysis type needed. We present a system that constrains AI reviewer behavior through philosophical…

Software Engineering · Computer Science 2026-05-25 Kaushal Bansal