English
Related papers

Related papers: How Well Do Models Follow Their Constitutions?

200 papers

Safety cases, structured arguments that a system is acceptably safe, are becoming central to the governance of AI systems. Yet, traditional safety-case practices from aviation or nuclear engineering rely on well-specified system boundaries,…

Software Engineering · Computer Science 2026-03-09 Sung Une Lee , Liming Zhu , Md Shamsujjoha , Liming Dong , Qinghua Lu , Jieshan Chen , Lionel Briand

Over the past year, artificial intelligence (AI) companies have been increasingly adopting AI safety frameworks. These frameworks outline how companies intend to keep the potential risks associated with developing and deploying frontier AI…

Computers and Society · Computer Science 2024-09-16 Jide Alaga , Jonas Schuett , Markus Anderljung

Frontier AI safety claims - published assertions that a highly capable general-purpose model is below a threshold of concern, adequately mitigated, or suitable for release - increasingly shape model deployment, governance, and public trust.…

Computers and Society · Computer Science 2026-05-12 Varad Vishwarupe , Nigel Shadbolt , Marina Jirotka , Ivan Flechais

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

Artificial Intelligence · Computer Science 2025-05-20 Lili Zhang , Haomiaomiao Wang , Long Cheng , Libao Deng , Tomas Ward

Pre-deployment evaluations inspect only a limited sample of model actions. A malicious model seeking to evade oversight could exploit this by randomizing when to "defect": misbehaving so rarely that no malicious actions are observed during…

Machine Learning · Computer Science 2026-03-03 Alex Serrano , Wen Xing , David Lindner , Erik Jenner

Many have observed that the development and deployment of generative machine learning (ML) and artificial intelligence (AI) models follow a distinctive pattern in which pre-trained models are adapted and fine-tuned for specific downstream…

Social and Information Networks · Computer Science 2025-08-12 Benjamin Laufer , Hamidah Oderinwale , Jon Kleinberg

Artificial intelligence (AI) is increasingly being considered to assist human decision-making in high-stake domains (e.g. health). However, researchers have discussed an issue that humans can over-rely on wrong suggestions of the AI model…

Human-Computer Interaction · Computer Science 2023-08-09 Min Hun Lee , Chong Jun Chew

Do expert personas improve language model performance? The Wharton Generative AI Lab reports that they do not, broadcasting to millions via social media the recommendation that practitioners abandon a technique recommended by Anthropic,…

Computers and Society · Computer Science 2026-03-24 Drake Mullens , Stella Shen

The proliferation of AI-assisted "vibe coding" enables rapid software development but introduces significant security risks, as Large Language Models (LLMs) prioritize functional correctness over security. We present Constitutional…

Software Engineering · Computer Science 2026-02-04 Srinivas Rao Marri

Despite widespread deployment of Large Language Models, systematic evaluation of instruction-following capabilities remains challenging. While comprehensive benchmarks exist, focused assessments that quickly diagnose specific instruction…

Computation and Language · Computer Science 2025-10-23 Richard J. Young , Brandon Gillins , Alice M. Matthews

In this paper, we conduct an empirical analysis of how large language models (LLMs), specifically GPT-4, interpret constitutional principles in complex decision-making scenarios. We examine rulings from the Italian Constitutional Court on…

Computation and Language · Computer Science 2024-08-12 Camilla Bignotti , Carolina Camassa

Large language models make it easy for students to delegate writing, analysis, and problem-solving to automated systems, bypassing the effortful engagement that produces lasting understanding. We introduce a practical framework that helps…

Software Engineering · Computer Science 2026-05-26 Philipp Haindl , Oliver Eigner , Peter Kieseberg

Readers of applied-domain LLM capability evaluations want to know what AI systems can currently do. That literature answers a related, but consequentially different, question: what older, cheaper, less-elicited models could do months or…

Computers and Society · Computer Science 2026-05-07 David Gringras , Misha Salahshoor

Many promising-looking ideas in AI research fail to deliver, but their validation takes substantial human labor and compute. Predicting an idea's chance of success is thus crucial for accelerating empirical AI research, a skill that even…

Artificial Intelligence · Computer Science 2025-06-03 Jiaxin Wen , Chenglei Si , Yueh-han Chen , He He , Shi Feng

We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from…

Machine Learning · Computer Science 2026-05-12 Rohit Agarwal , Joshua Lin , Mark Braverman , Elad Hazan

For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent…

Computation and Language · Computer Science 2023-05-29 Kundan Krishna , Saurabh Garg , Jeffrey P. Bigham , Zachary C. Lipton

Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations where social influence may override individual alignment. Here…

Physics and Society · Physics 2026-05-12 Giordano De Marzo , Alessandro Bellina , Claudio Castellano , Viola Priesemann , David Garcia

This paper presents the first systematic measurement of educational alignment in Large Language Models. Using a Delphi-validated instrument comprising 48 items across eight educational-theoretical dimensions, the study reveals that GPT-5.1…

Computers and Society · Computer Science 2026-03-24 Daniel Autenrieth

Although AI drafting tools have gained prominence in patent writing, the systematic evaluation of AI-generated patent content quality represents a significant research gap. To address this gap, We propose to evaluate patents using…

Information Retrieval · Computer Science 2025-10-31 Yuqian Chai , Chaochao Wang , Weilei Wang

Contemporary AI governance frameworks rely heavily on post hoc oversight, policy guidance, and behavioral alignment techniques, yet these mechanisms become fragile as systems gain autonomy, speed, and operational opacity. This paper…

Cryptography and Security · Computer Science 2026-03-19 Adam Massimo Mazzocchetti
‹ Prev 1 4 5 6 7 8 10 Next ›