Instant research discovery
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
PreviousNext
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Search and browse arXiv CS/AI/ML papers, enriched with AI-generated insights.
Generate novel research ideas grounded in real arXiv papers with Brainstorm.
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
Showing 1-30 of 199 papers (page 1 of 7)路 78 ms
| Paper | Published | Area | Tags | Intel | Citations |
|---|---|---|---|---|---|
| Optimal Policies Tend to Seek Power Alexander Matt Turner, Andrew Critch, Logan Smith, Prasad Tadepalli Published: 2019-12-03Area: Formal/TheoreticalCitations: 97 Tags: ai-safety, formaltheoretical, theoretical | 2019-12-03 | Formal/Theoretical | ai-safety, formaltheoretical, theoretical | E5 / R3 (93%) | 97 |
| Deep Learning is Singular, and That's Good Daniel Murfet, Hui Li, Jesse Gell-Redman, Mingming Gong Published: 2020-10-22Area: Formal/TheoreticalCitations: 38 Tags: ai-safety, formaltheoretical, theoretical | 2020-10-22 | Formal/Theoretical | ai-safety, formaltheoretical, theoretical | E5 / R3 (95%) | 38 |
| Agent Incentives: A Causal Perspective Eric D. Langlois, Pedro A. Ortega, Ryan Carey, Shane Legg Published: 2021-02-02Area: Formal/TheoreticalCitations: 61 Tags: ai-safety, formaltheoretical, theoretical | 2021-02-02 | Formal/Theoretical | ai-safety, formaltheoretical, theoretical | E6 / R3 (96%) | 61 |
| Consequences of Misaligned AI Dylan Hadfield-Menell, Simon Zhuang Published: 2021-02-07Area: Formal/TheoreticalCitations: 95 Tags: ai-safety, formaltheoretical, theoretical | 2021-02-07 | Formal/Theoretical | ai-safety, formaltheoretical, theoretical | E6 / R3 (96%) | 95 |
| Towards Understanding Grokking: An Effective Theory of Representation Learning Eric J. Michaud, Max Tegmark, Mike Williams, Niklas Nolte Published: 2022-05-20Area: Training DynamicsCitations: 217 Tags: ai-safety, theoretical, training-dynamics | 2022-05-20 | Training Dynamics | ai-safety, theoretical, training-dynamics | E5 / R4 (94%) | 217 |
| Is Power-Seeking AI an Existential Risk? Joseph Carlsmith Published: 2022-06-16Area: Deception & FailureCitations: 129 Tags: ai-safety, alignment-training, deception-failure, theoretical | 2022-06-16 | Deception & Failure | ai-safety, alignment-training, deception-failure, theoretical | E4 / R3 (94%) | 129 |
| Parametrically Retargetable Decision-Makers Tend to Seek Power Alexander Matt Turner, Prasad Tadepalli Published: 2022-06-27Area: Formal/TheoreticalCitations: 21 Tags: ai-safety, formaltheoretical, theoretical | 2022-06-27 | Formal/Theoretical | ai-safety, formaltheoretical, theoretical | E6 / R3 (96%) | 21 |
| The Alignment Problem from a Deep Learning Perspective Lawrence Chan, Richard Ngo, S枚ren Mindermann Published: 2022-08-30Area: Deception & FailureCitations: 263 Tags: ai-safety, alignment-training, deception-failure, theoretical | 2022-08-30 | Deception & Failure | ai-safety, alignment-training, deception-failure, theoretical | E5 / R3 (93%) | 263 |
| Defining and Characterizing Reward Hacking David Krueger, Dmitrii Krasheninnikov, Joar Skalse, Nikolaus H. R. Howe Published: 2022-09-27Area: Deception & FailureCitations: 96 Tags: ai-safety, deception-failure, theoretical | 2022-09-27 | Deception & Failure | ai-safety, deception-failure, theoretical | E5 / R3 (97%) | 96 |
| On the Impossible Safety of Large AI Models El-Mahdi El-Mhamdi, John Stephan, L锚-Nguy锚n Hoang, Nirupam Gupta Published: 2022-09-30Area: Formal/TheoreticalCitations: 37 Tags: ai-safety, formaltheoretical, theoretical | 2022-09-30 | Formal/Theoretical | ai-safety, formaltheoretical, theoretical | E5 / R4 (94%) | 37 |
| Polysemanticity and Capacity in Neural Networks Adam Scherlis, Adam S. Jermyn, Buck Shlegeris, Joe Benton Published: 2022-10-04Area: Mechanistic Interp.Citations: 52 Tags: ai-safety, mechanistic-interp, theoretical | 2022-10-04 | Mechanistic Interp. | ai-safety, mechanistic-interp, theoretical | E5 / R3 (92%) | 52 |
| Interpreting Neural Networks through the Polytope Lens Beren Millidge, Carlos Ram贸n Guevara, Connor Leahy, Dan Braun Published: 2022-11-22Area: Mechanistic Interp.Citations: 36 Tags: ai-safety, interpretability, mechanistic-interp, theoretical | 2022-11-22 | Mechanistic Interp. | ai-safety, interpretability, mechanistic-interp, theoretical | E5 / R3 (95%) | 36 |
| Transformers Learn In-Context by Gradient Descent Alexander Mordvintsev, Andrey Zhmoginov, Ettore Randazzo, Eyvind Niklasson Published: 2022-12-15Area: Training DynamicsCitations: 677 Tags: ai-safety, theoretical, training-dynamics | 2022-12-15 | Training Dynamics | ai-safety, theoretical, training-dynamics | E5 / R3 (95%) | 677 |
| Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability Amir Zur, Aryaman Arora, Atticus Geiger, Christopher Potts Published: 2023-01-11Area: Mechanistic Interp.Citations: 118 Tags: ai-safety, interpretability, mechanistic-interp, theoretical | 2023-01-11 | Mechanistic Interp. | ai-safety, interpretability, mechanistic-interp, theoretical | E6 / R3 (95%) | 118 |
| Conditioning Predictive Models: Risks and Strategies Adam S. Jermyn, Evan Hubinger, Johannes Treutlein, Kate Woolverton Published: 2023-02-02Area: Deception & FailureCitations: 8 Tags: ai-safety, alignment-training, deception-failure, theoretical | 2023-02-02 | Deception & Failure | ai-safety, alignment-training, deception-failure, theoretical | E5 / R3 (94%) | 8 |
| Characterizing Manipulation from AI Systems Alan Chan, David Krueger, Henry Ashton, Micah Carroll Published: 2023-03-16Area: Deception & FailureCitations: 66 Tags: ai-safety, deception-failure, theoretical | 2023-03-16 | Deception & Failure | ai-safety, deception-failure, theoretical | E5 / R4 (93%) | 66 |
| Power-seeking can be probable and predictive for trained agents Janos Kramar, Victoria Krakovna Published: 2023-04-13Area: Formal/TheoreticalCitations: 22 Tags: ai-safety, formaltheoretical, theoretical | 2023-04-13 | Formal/Theoretical | ai-safety, formaltheoretical, theoretical | E6 / R3 (96%) | 22 |
| Fundamental Limitations of Alignment in Large Language Models Amnon Shashua, Noam Wies, Oshri Avnery, Yoav Levine Published: 2023-04-19Area: Formal/TheoreticalCitations: 178 Tags: adversarial-robustness, ai-safety, alignment-training, formaltheoretical, theoretical | 2023-04-19 | Formal/Theoretical | adversarial-robustness, ai-safety, alignment-training, formaltheoretical, theoretical | E4 / R2 (94%) | 178 |
| A Technical Note on Bilinear Layers for Interpretability Lee Sharkey Published: 2023-05-05Area: Mechanistic Interp.Citations: 10 Tags: ai-safety, interpretability, mechanistic-interp, theoretical | 2023-05-05 | Mechanistic Interp. | ai-safety, interpretability, mechanistic-interp, theoretical | E5 / R3 (92%) | 10 |
| Intent-aligned AI systems deplete human agency: the need for agency foundations research in AI safety Ben Smith, Catalin Mitelut, Peter Vamplew Published: 2023-05-30Area: Formal/TheoreticalCitations: 7 Tags: ai-safety, formaltheoretical, theoretical | 2023-05-30 | Formal/Theoretical | ai-safety, formaltheoretical, theoretical | E5 / R3 (96%) | 7 |
| LLM Censorship: A Machine Learning Challenge or a Computer Security Problem? David Glukhov, Ilia Shumailov, Nicolas Papernot, Vardan Papyan Published: 2023-07-20Area: Adversarial RobustnessCitations: 72 Tags: adversarial-robustness, ai-safety, theoretical | 2023-07-20 | Adversarial Robustness | adversarial-robustness, ai-safety, theoretical | E5 / R3 (94%) | 72 |
| A Geometric Notion of Causal Probing Alexander Warstadt, Anej Svete, Cl茅ment Guerner, Ryan Cotterell Published: 2023-07-27Area: Representation AnalysisCitations: 25 Tags: ai-safety, representation-analysis, theoretical | 2023-07-27 | Representation Analysis | ai-safety, representation-analysis, theoretical | E5 / R3 (92%) | 25 |
| The Local Learning Coefficient: A Singularity-Aware Complexity Measure Daniel Murfet, Edmund Lau, George Wang, Susan Wei Published: 2023-08-23Area: Training DynamicsCitations: 34 Tags: ai-safety, theoretical, training-dynamics | 2023-08-23 | Training Dynamics | ai-safety, theoretical, training-dynamics | E5 / R3 (96%) | 34 |
| Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition Daniel Murfet, Edmund Lau, Jake Mendel, Susan Wei Published: 2023-10-10Area: Training DynamicsCitations: 22 Tags: ai-safety, theoretical, training-dynamics | 2023-10-10 | Training Dynamics | ai-safety, theoretical, training-dynamics | E5 / R3 (95%) | 22 |
| A General Theoretical Paradigm to Understand Learning from Human Feedback Bilal Piot, Daniele Calandriello, Daniel Guo, Mark Rowland Published: 2023-10-18Area: Alignment TrainingCitations: 894 Tags: ai-safety, alignment-training, theoretical | 2023-10-18 | Alignment Training | ai-safety, alignment-training, theoretical | E5 / R3 (97%) | 894 |
| The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback Nathan Lambert, Roberto Calandra Published: 2023-10-31Area: Alignment TrainingCitations: 42 Tags: ai-safety, alignment-training, safety-evaluation, theoretical | 2023-10-31 | Alignment Training | ai-safety, alignment-training, safety-evaluation, theoretical | E5 / R3 (95%) | 42 |
| The Linear Representation Hypothesis and the Geometry of Large Language Models Kiho Park, Victor Veitch, Yo Joong Choe Published: 2023-11-07Area: Representation AnalysisCitations: 371 Tags: ai-safety, representation-analysis, theoretical | 2023-11-07 | Representation Analysis | ai-safety, representation-analysis, theoretical | E5 / R3 (95%) | 371 |
| Scheming AIs: Will AIs Fake Alignment During Training in Order to Get Power? Joe Carlsmith Published: 2023-11-14Area: Deception & FailureCitations: 59 Tags: ai-safety, alignment-training, deception-failure, theoretical | 2023-11-14 | Deception & Failure | ai-safety, alignment-training, deception-failure, theoretical | E6 / R3 (94%) | 59 |
| Scalable AI Safety via Doubly-Efficient Debate Geoffrey Irving, Georgios Piliouras, Jonah Brown-Cohen Published: 2023-11-23Area: Scalable OversightCitations: 40 Tags: ai-safety, scalable-oversight, theoretical | 2023-11-23 | Scalable Oversight | ai-safety, scalable-oversight, theoretical | E5 / R3 (94%) | 40 |
| Hashmarks: Privacy-Preserving Benchmarks for High-Stakes AI Evaluation Paul Bricman Published: 2023-12-01Area: Safety EvaluationCitations: - Tags: ai-safety, safety-evaluation, theoretical | 2023-12-01 | Safety Evaluation | ai-safety, safety-evaluation, theoretical | E5 / R3 (95%) | - |