AI safety and alignment

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

10,657 stories · RSS feed

arXiv AI

Jun 16

BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios

arXiv:2605. 00873v2 Announce Type: replace-cross Abstract: The rapid advancement of photorealistic Text-to-Video (T2V) generation brings in an urgent need for up-to-date evaluation methods.

By Advait Tilak, Jiwon Choi, Nazifa Mouli, Wei Le

llms diffusion multimodal benchmarks safety

arXiv AI

Jun 16

Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphs

arXiv:2606. 15656v1 Announce Type: new Abstract: Modern artificial intelligence remains fundamentally divided between the continuous, probabilistic spaces of Foundation Models and the discrete, deterministic structures of Knowledge Graphs.

By Sahil Rajesh Dhayalkar

rag safety

arXiv AI

Jun 16

FORTIS: Benchmarking Over-Privilege in Agent Skills

arXiv:2605. 09163v3 Announce Type: replace Abstract: Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution.

By Shawn Li, Chenxiao Yu, Han Wang, Wei Yang, Ryan Rossi, Franck Dernoncourt, Xiyang Hu, Philip Yu, Chaowei Xiao, Huan Zhang, Yue Zhao

llms agents benchmarks safety

arXiv AI

Jun 16

Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call

arXiv:2606. 15225v1 Announce Type: cross Abstract: Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement.

By Weibo Gao, Qi Liu, Linan Yue, Zheng Zhang, Yichao Du, Fangzhou Yao, Ao Yu, Zhenya Huang, Shijin Wang

llms agents safety

arXiv Machine Learning

Jun 16

Latent space mapping of interpretable structural coordinates from stochastic single-molecule signals

arXiv:2606. 16950v1 Announce Type: cross Abstract: Nanopores are versatile single-molecular sensors, but their utility is fundamentally constrained by stochastic translocation dynamics warping any encoded information.

By Matteo Cartiglia, Sandro Kuppel, Wouter Botermans Wannes Peeters, Natan Biesmans, Liam Vandekerckhove, Eric Beamish, Koen Ongena, Wouter Renckens, Pol Van Dorpe, Sanjin Marion

diffusion safety

arXiv AI

Jun 16

Unifying Post-hoc Explanations of Knowledge Graph Completions

arXiv:2507. 22951v2 Announce Type: replace Abstract: Knowledge Graphs organize information as entity-relation-entity triples, enabling machine learning models to predict plausible missing triples in a task known as Knowledge Graph Completion (KGC).

By Alessandro Lonardi, Samy Badreddine, Tarek R. Besold, Pablo Sanchez Martin

safety

arXiv Machine Learning

Jun 16

GRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science

arXiv:2606. 16000v1 Announce Type: cross Abstract: We introduce GRACE-DS, a Guarded Reward-guided Agent Correction Environment in Data Science for pre-deployment evaluation of LLM-powered AutoML agents.

By Aleksandr Tsymbalov, Danis Zaripov, Artem Epifanov, Anastasya Palienko

llms agents safety

arXiv AI

Jun 16

Teacher-Student Structure for Domain Adaptation in Ensemble Audio-Visual Video Deepfake Detection

arXiv:2606. 15117v1 Announce Type: cross Abstract: The rapid advancement of generative AI models is leading to more realistic deepfake media, encompassing the manipulation of audio, video, or both.

By Elham Abolhasani, Maryam Ramezani, Hamid R. Rabiee

robotics fine-tuning multimodal safety

arXiv AI

Jun 16

JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks

arXiv:2602. 06486v2 Announce Type: replace Abstract: Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility.

By Lanbo Lin, Jiayao Liu, Tianyuan Yang, Li Cai, Yuanwu Xu, Lei Wei, Sicong Xie, Guannan Zhang

llms agents safety

arXiv Machine Learning

Jun 16

Rethinking Structural Anomaly Detection: From Decision Boundaries to Projection Operators

arXiv:2606. 15280v1 Announce Type: new Abstract: Most existing anomaly detection methods rely on estimating a probability density or learning an enclosing decision boundary, implicitly assuming that normal data occupies a region of non-zero volume in the ambient space.

By Alexander Bauer

safety

arXiv Machine Learning

Jun 16

Repeated Bilateral Trade: The Quest for Fairness

arXiv:2606. 15369v1 Announce Type: new Abstract: We study repeated bilateral trade from a fairness perspective.

By Fran\c{c}ois Bachoc, Roberto Colomboni, Emilie Kaufmann

agents safety

arXiv AI

Jun 16

Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints

arXiv:2504. 11320v4 Announce Type: replace-cross Abstract: Large language models now serve millions of users daily, with providers incurring costs exceeding $700,000 per day.

By Ruicheng Ao, Gan Luo, David Simchi-Levi, Xinshang Wang

llms benchmarks safety

arXiv Machine Learning

Jun 16

To forget is to preserve: Machine Unlearning for 3D medical image segmentation

arXiv:2606. 16180v1 Announce Type: cross Abstract: With new data privacy laws such as the General Data Protection Regulation (GDPR) [1] that allow individuals to ask that any of their personal information be erased from trained machine learning models, there has been a push to investigate the unlearning of data from models as a way to comply with these laws.

By Nitesh Kumar Singh, Akhilesh Singh, Arjun Arora

computer-vision safety

arXiv Machine Learning

Jun 16

Diversity-Driven Offline Multi-Objective Optimization via Nested Pareto Set Learning

arXiv:2606. 15115v1 Announce Type: new Abstract: Multi-objective optimization (MOO) has emerged as a powerful approach to solving complex optimization problems involving multiple objectives.

By Yiyi Zhu, Yaolin Wen, Xiang Xia, Xin An, Hanyi Si, Xiang Shu, Yangde Fu, Liang Dou, Hong Qian

benchmarks safety

arXiv AI

Jun 16

Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: A Mechanistic Interpretability Audit of Ethical Reasoning

arXiv:2606. 15507v1 Announce Type: new Abstract: Behavioral audits of Large Language Models on moral prompts measure what the model says, not the internal computation producing it.

By Ali Dasdan, Manan Shah, W. Russell Neuman, Chad Coleman, Kund Meghani, Safinah Ali

llms reinforcement-learning safety

arXiv AI

Jun 16

Critically Engaged Pragmatism: Scientific Norm and Social, Pragmatist Epistemology for AI Science Evaluation Tools

arXiv:2601. 09753v2 Announce Type: replace-cross Abstract: AI science evaluation tools aim to assess research credibility.

By Carole J. Lee

benchmarks safety

arXiv Machine Learning

Jun 16

Spatial Priors via Space Filling Curves for Small and Limited Data Vision Transformers

arXiv:2606. 14757v1 Announce Type: cross Abstract: Though Vision Transformers (ViTs) have become the dominant backbone in many computer vision tasks, due to permutation equivariance, their attention mechanism lacks explicit spatial inductive biases.

By Leyla Naz Candogan, Arshia Afzal, Pol Puigdemont, Volkan Cevher

llms computer-vision fine-tuning safety

arXiv Machine Learning

Jun 16

From Tokens to Policy: Causal and Interpretable Heterogeneous Treatment Effects Identification

arXiv:2606. 17010v1 Announce Type: new Abstract: Heterogeneous Treatment Effect (HTE) identification is crucial to explain the impact of an intervention and optimize our policies accordingly.

By Riccardo Cadei, Frank Otchere, Nyasha Tirivayi, Gustavo Angeles Tagliaferro, Falco J. Bargagli-Stoffi, Francesco Locatello

multimodal safety

arXiv AI

Jun 16

Are Neuro-Inspired Multi-Modal Vision-Language Models Resilient to Membership Inference Privacy Leakage?

arXiv:2511. 20710v2 Announce Type: replace-cross Abstract: In the age of agentic AI, the growing deployment of multi-modal models (MMs) has introduced new attack vectors that can leak sensitive training data in MMs, causing privacy leakage.

By David Amebley, Sayanton Dibbo

llms agents multimodal benchmarks safety

arXiv AI

Jun 16

Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents

arXiv:2606. 16769v1 Announce Type: new Abstract: Agent skills are commonly distributed as SKILL.

By Tianyi Zhang, Zhonghao Qi

llms agents fine-tuning safety

Get the daily briefing