AI safety and alignment

Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.

9,195 stories · RSS feed

arXiv Machine Learning

Jul 27

Interpretable EEG biomarkers with bag-of-waves: Spatial and temporal waveform dictionaries for low-data regimes

arXiv:2607. 22508v1 Announce Type: new Abstract: Electroencephalography (EEG) is widely used to diagnose neurological conditions, but its analysis usually relies on either predefined spectral features or deep neural networks.

By Athanasios Papastathopoulos-Katsaros, Steven T. Lee, Lin Yao, Ajay Thomas, Junseok Park, Matthew J. McGinley, Zhandong Liu

benchmarks safety

arXiv Machine Learning

Jul 27

FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs

arXiv:2607. 21624v1 Announce Type: cross Abstract: Transformer-based models have enabled unprecedented capabilities across language, vision, and multimodal tasks.

By Kahou Tam, Wei Niu, Yu Bao, Xiaomin Ouyang, Chengzhong Xu, Li Li

llms fine-tuning efficiency multimodal safety

arXiv Machine Learning

Jul 27

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems

arXiv:2607. 21627v1 Announce Type: cross Abstract: End-to-end reinforcement learning can improve the accuracy of compound LLM systems, but it does not constrain how modules divide labor internally.

By Xiaoyang Cao, Siddarth Srinivasan, Michiel A. Bakker

llms reinforcement-learning safety

arXiv Machine Learning

Jul 27

Deep Sigma Point Processes for RCS Modeling in Spaceborne SAR Imagery

arXiv:2607. 21745v1 Announce Type: cross Abstract: Radar cross-section (RCS) modeling is foundational to advancing the utility and sensitivity of spaceborne radar systems.

By Khalid El-Darymli, Christoph H. Gierull, Katerina Biron, Weimin Huang

safety

arXiv Machine Learning

Jul 27

Replacing Tunable Parameters in Weather and Climate Models with State-Dependent Functions using Reinforcement Learning

arXiv:2601. 04268v3 Announce Type: replace Abstract: Weather and climate models rely on parametrisations to represent unresolved sub-grid processes.

By Pritthijit Nath, Sebastian Schemm, Henry Moss, Peter Haynes, Emily Shuckburgh, Mark J. Webb

agents reinforcement-learning safety

arXiv Machine Learning

Jul 27

A Comparative Benchmark of Federated Learning Strategies for Mortality Prediction on Heterogeneous and Imbalanced Clinical Data

arXiv:2509. 10517v3 Announce Type: replace Abstract: Machine learning can predict in-hospital mortality, but data privacy and the statistical heterogeneity of clinical data hamper its use.

By Rodrigo Tertulino

benchmarks safety

arXiv Machine Learning

Jul 27

The Coordination Gap: Multi-Agent Alternation Metrics for Temporal Fairness in Repeated Games

arXiv:2603. 05789v5 Announce Type: replace-cross Abstract: Repeated multi-agent interactions require evaluation metrics that capture not only payoff distributions but also their temporal organization.

By Nikolaos Al. Papadopoulos, Ismael Tito Freire, Marti Sanchez-Fibla, Konstantinos E. Psannis

agents reinforcement-learning benchmarks safety

arXiv Machine Learning

Jul 27

LLAMA LIMA: A Living Meta-Analysis on the Effects of Generative AI on Learning Mathematics

arXiv:2601. 18685v4 Announce Type: replace-cross Abstract: The capabilities of generative AI in mathematics education are rapidly evolving, posing significant challenges for research to keep pace.

By Anselm Strohmaier, Samira B\"odefeld, Oliver Straser, Frank Reinhold

llms safety

arXiv Machine Learning

Jul 27

Minimum Norm Interpolation via the Local Theory of Banach Spaces: The Role of $2$-Uniform Convexity

arXiv:2603. 28956v2 Announce Type: replace-cross Abstract: The minimum-norm interpolator (MNI) framework has recently attracted considerable attention as a tool for understanding generalization in overparameterized models, such as neural networks.

By Gil Kur, Pierre Bizeul

safety

arXiv Machine Learning

Jul 27

Quantifying Political Partisanship for Cross-Platform Analyses

arXiv:2607. 21842v1 Announce Type: cross Abstract: Research on political polarization on social media depends on the ability to reliably measure partisanship in user-generated content.

By Fathima Ameen, Christopher G. Healey

llms rag safety

arXiv Machine Learning

Jul 27

The pretraining domain outweighs the training objective in setting the privacy-utility trade-off of differentially private medical image analysis

arXiv:2601. 19618v2 Announce Type: replace-cross Abstract: Differential privacy protects the patients whose images train medical imaging models, but it lowers diagnostic accuracy, and the initialization is the strongest known remedy.

By Soroosh Tayebi Arasteh, Mina Farajiamiri, Mahshad Lotfinia, Behrus Hinrichs-Puladi, Jonas Bienzeisler, Mohamed Alhaskir, Mirabela Rusu, Christiane Kuhl, Sven Nebelung, Daniel Truhn

safety

arXiv Machine Learning

Jul 27

Simpson's Paradox in Behavioral Curves: How Aggregation Distorts Parametric Models of User Dynamics

arXiv:2605. 11017v2 Announce Type: replace Abstract: Behavioral curve modeling -- fitting parametric functions to engagement-versus-exposure data -- is standard practice in recommendation, advertising, and clinical dosing.

By Chao Zhou

safety

arXiv Machine Learning

Jul 27

Certified in Theory, Broken in Practice: Assumption Gaps in Cryptographic Model Certification

arXiv:2607. 21839v1 Announce Type: cross Abstract: Privacy-preserving machine learning auditing protocols allow auditors to assess models for properties such as accuracy or fairness, without revealing their internals or training data.

By Carter Luck, Olive Franzese-McLaughlin, Elisaweta Masserova, Akira Takahashi, Antigoni Polychroniadou, Nicolas Papernot

safety

arXiv Machine Learning

Jul 27

A Robust Pipeline for Differentially Private Federated Learning on Imbalanced Clinical Data using SMOTETomek and FedProx

arXiv:2508. 10017v2 Announce Type: replace-cross Abstract: Federated Learning (FL) presents a groundbreaking approach for collaborative health research, allowing model training on decentralized data while safeguarding patient privacy.

By Rodrigo Tertulino

safety

arXiv Machine Learning

Jul 27

Automatic Stability and Recovery for Neural Network Training

arXiv:2601. 17483v2 Announce Type: replace Abstract: Training modern neural networks is increasingly fragile, with rare but severe destabilizing updates often causing irreversible divergence or silent performance degradation.

By Barak Or

safety

arXiv Machine Learning

Jul 27

Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models

arXiv:2607. 22098v1 Announce Type: cross Abstract: Large reasoning models (LRMs) generate long reasoning traces before producing final answers.

By Junlin Fang, Do Nguyen-Thanh, Xiaogang Xu, Zhen Fang, Sean Du

rag benchmarks safety

arXiv Machine Learning

Jul 27

Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions

arXiv:2607. 21635v1 Announce Type: new Abstract: Personal agents maintain memories, learned skills, tool configurations, and policy state that evolve with each user.

By Pin Qian, Su Wang, Yihang Chen, Qiaolin Yu, Xiaoyuan Wang, Zhitong Guo, Zhicheng Wang, Junxian You

llms agents benchmarks safety

arXiv Machine Learning

Jul 27

Safe In-Context Reinforcement Learning

arXiv:2509. 25582v4 Announce Type: replace Abstract: In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, instead relying on an expanding context of interaction history.

By Amir Moeini, Minjae Kwon, Alper Kamil Bozkurt, Yuichi Motai, Rohan Chandra, Lu Feng, Shangtong Zhang

agents reinforcement-learning benchmarks safety

arXiv Machine Learning

Jul 27

Industrial Tokenization for LLM-Based Health Intelligence: A Federated Architecture for Industrial Evidence Integration

arXiv:2607. 22153v1 Announce Type: cross Abstract: Industrial health management increasingly relies on heterogeneous information sources, including condition monitoring systems, supervisory control and data acquisition systems, maintenance records, inspection results, and prognostic models.

By Deshui Li, Xiao-Ming Yuan, Zishun Wang

llms agents nlp safety

arXiv Machine Learning

Jul 27

MA-DAR: Manifold-Aligned Dynamic Adaptive Routing for Continual Temporal Knowledge Graph Reasoning

arXiv:2607. 21949v1 Announce Type: new Abstract: Continual temporal knowledge graph (TKG) reasoning aims to continuously incorporate newly emerging facts while preserving previously acquired knowledge.

By Xiangjun Shi, Chong Mu, Jinchuan Zhang, Lizong Zhang, Yuefeng He, Shang Liu

benchmarks safety

Get the daily briefing