English
Related papers

Related papers: How Well Do Models Follow Their Constitutions?

200 papers

Background: When using deep learning models, there are many possible vulnerabilities and some of the most worrying are the adversarial inputs, which can cause wrong decisions with minor perturbations. Therefore, it becomes necessary to…

Software Engineering · Computer Science 2024-01-12 Francisco Durán López , Silverio Martínez-Fernández , Michael Felderer , Xavier Franch

Large language models (LLMs) such as ChatGPT are increasingly integrated into high-stakes decision-making, yet little is known about their susceptibility to social influence. We conducted three preregistered conformity experiments with…

Artificial Intelligence · Computer Science 2025-10-31 Clarissa Sabrina Arlinghaus , Tristan Kenneweg , Barbara Hammer , Günter W. Maier

Self-replication with no human intervention is broadly recognized as one of the principal red lines associated with frontier AI systems. While leading corporations such as OpenAI and Google DeepMind have assessed GPT-o3-mini and Gemini on…

Artificial Intelligence · Computer Science 2025-03-26 Xudong Pan , Jiarun Dai , Yihe Fan , Minyuan Luo , Changyi Li , Min Yang

The Abstraction and Reasoning Corpus (ARC-AGI) has become a key benchmark for fluid intelligence in AI. This survey presents the first cross-generation analysis of 82 approaches across three benchmark versions and the ARC Prize 2024-2025…

Artificial Intelligence · Computer Science 2026-03-17 Sahar Vahdati , Andrei Aioanei , Haridhra Suresh , Jens Lehmann

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…

Cryptography and Security · Computer Science 2026-04-28 Richard Joseph Mitchell

Legal practice requires careful adherence to procedural rules. In the United States, few are more complex than those found in The Bluebook: A Uniform System of Citation. Compliance with this system's 500+ pages of byzantine formatting…

Computation and Language · Computer Science 2025-05-06 Matthew Dahl

Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning. Variants of this method have been used as regularization mechanisms to achieve SOTA results on NLP benchmarks, and…

Computation and Language · Computer Science 2021-09-30 Javid Ebrahimi , Hao Yang , Wei Zhang

We introduce a framework called LAPITHS (Language model Analysis through Paradigm grounded Interpretations of Theses about Human likenesS) and use it to show that several major claims advanced by models such as CENTAUR, proposed as an…

Artificial Intelligence · Computer Science 2026-05-01 Matteo Da Pelo , Alessio Donvito , Claudio Frongia , Pietro Salis , Antonio Lieto

As language models are deployed as autonomous agents that negotiate, cooperate, and compete on behalf of human principals, their strategic dispositions acquire direct economic consequences. Here we show, across 51,906 game-theoretic trials…

Physics and Society · Physics 2026-04-23 Felipe M. Affonso

This work establishes a foundational framework for standardizing AI evaluation RCTs (sometimes called human uplift studies). Drawing on established experimental practices from disciplines with established RCT traditions, including software…

Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors. To study these risks, researchers develop model organisms: models finetuned to exhibit specific known behaviors…

Computation and Language · Computer Science 2026-05-05 Mohammed Abu Baker , Luca Baroni , Dan Wilhelm

Data teams at frontier AI companies routinely train small proxy models to make critical decisions about pretraining data recipes for full-scale training runs. However, the community has a limited understanding of whether and when…

Machine Learning · Computer Science 2026-04-14 Jiachen T. Wang , Tong Wu , Kaifeng Lyu , James Zou , Dawn Song , Ruoxi Jia , Prateek Mittal

Constitution-conditioned post-training can be analysed as a structured perturbation of a model's learned representational geometry. We introduce ATLAS, a geometry-first program that traces constitution-induced hidden-state structure across…

Machine Learning · Computer Science 2026-04-21 Gareth Seneque , Lap-Hang Ho , Nafise Erfanian Saeedi , Jeffrey Molendijk , Tim Elson

Self-recognition is a crucial metacognitive capability for AI systems, relevant not only for psychological analysis but also for safety, particularly in evaluative scenarios. Motivated by contradictory interpretations of whether models…

Artificial Intelligence · Computer Science 2025-10-07 Xiaoyan Bai , Aryan Shrivastava , Ari Holtzman , Chenhao Tan

The release of large natural language inference (NLI) datasets like SNLI and MNLI have led to rapid development and improvement of completely neural systems for the task. Most recently, heavily pre-trained, Transformer-based models like…

Computation and Language · Computer Science 2019-12-10 Tiffany Chien , Jugal Kalita

AI models of equivalent capability can exhibit fundamentally different behavioral patterns, yet no standardized instrument exists to measure these dispositional differences. Existing approaches either borrow human personality dimensions and…

Artificial Intelligence · Computer Science 2026-04-03 Jihoon Jeong

AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks. We call these models foundation models to underscore their…

Machine Learning · Computer Science 2022-07-14 Rishi Bommasani , Drew A. Hudson , Ehsan Adeli , Russ Altman , Simran Arora , Sydney von Arx , Michael S. Bernstein , Jeannette Bohg , Antoine Bosselut , Emma Brunskill , Erik Brynjolfsson , Shyamal Buch , Dallas Card , Rodrigo Castellon , Niladri Chatterji , Annie Chen , Kathleen Creel , Jared Quincy Davis , Dora Demszky , Chris Donahue , Moussa Doumbouya , Esin Durmus , Stefano Ermon , John Etchemendy , Kawin Ethayarajh , Li Fei-Fei , Chelsea Finn , Trevor Gale , Lauren Gillespie , Karan Goel , Noah Goodman , Shelby Grossman , Neel Guha , Tatsunori Hashimoto , Peter Henderson , John Hewitt , Daniel E. Ho , Jenny Hong , Kyle Hsu , Jing Huang , Thomas Icard , Saahil Jain , Dan Jurafsky , Pratyusha Kalluri , Siddharth Karamcheti , Geoff Keeling , Fereshte Khani , Omar Khattab , Pang Wei Koh , Mark Krass , Ranjay Krishna , Rohith Kuditipudi , Ananya Kumar , Faisal Ladhak , Mina Lee , Tony Lee , Jure Leskovec , Isabelle Levent , Xiang Lisa Li , Xuechen Li , Tengyu Ma , Ali Malik , Christopher D. Manning , Suvir Mirchandani , Eric Mitchell , Zanele Munyikwa , Suraj Nair , Avanika Narayan , Deepak Narayanan , Ben Newman , Allen Nie , Juan Carlos Niebles , Hamed Nilforoshan , Julian Nyarko , Giray Ogut , Laurel Orr , Isabel Papadimitriou , Joon Sung Park , Chris Piech , Eva Portelance , Christopher Potts , Aditi Raghunathan , Rob Reich , Hongyu Ren , Frieda Rong , Yusuf Roohani , Camilo Ruiz , Jack Ryan , Christopher Ré , Dorsa Sadigh , Shiori Sagawa , Keshav Santhanam , Andy Shih , Krishnan Srinivasan , Alex Tamkin , Rohan Taori , Armin W. Thomas , Florian Tramèr , Rose E. Wang , William Wang , Bohan Wu , Jiajun Wu , Yuhuai Wu , Sang Michael Xie , Michihiro Yasunaga , Jiaxuan You , Matei Zaharia , Michael Zhang , Tianyi Zhang , Xikun Zhang , Yuhui Zhang , Lucia Zheng , Kaitlyn Zhou , Percy Liang

The widespread use of generative AI systems is coupled with significant ethical and social challenges. As a result, policymakers, academic researchers, and social advocacy groups have all called for such systems to be audited. However,…

Computers and Society · Computer Science 2024-07-09 Jakob Mokander , Justin Curl , Mihir Kshirsagar

As ChatGPT et al. conquer the world, the optimal liability framework for AI systems remains an unsolved problem across the globe. In a much-anticipated move, the European Commission advanced two proposals outlining the European approach to…

Computers and Society · Computer Science 2023-08-01 Philipp Hacker

Generative pretraining (the "GPT" in ChatGPT) enables language models to learn from vast amounts of internet text without human supervision. This approach has driven breakthroughs across AI by allowing deep neural networks to learn from…

Neurons and Cognition · Quantitative Biology 2025-09-23 Thomas Serre , Ellie Pavlick
‹ Prev 1 8 9 10 Next ›