AI safety and alignment

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

17,884 stories · RSS feed

arXiv Machine Learning

Sep 1

Partially Linear Autoencoders for Manifold Learning and Dimensionality Reduction

arXiv:2608.29867v1 Announce Type: new Abstract: Autoencoders are widely used for nonlinear dimensionality reduction and manifold learning. While most common implementations rely on both nonlinear enc...

By Louen Pottier, Louis Lesueur, Anders Thorin

safety

arXiv Machine Learning

Sep 1

On the Recoverability of Private Information Unlearning in Large Language Models

arXiv:2608.29943v1 Announce Type: new Abstract: Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to re...

By Shicheng Hu, Runzhi Tian, Ziqiao Wang, Yongyi Mao

llms safety

arXiv Machine Learning

Sep 1

Multiclass Linear Perceptrons with Multiplicative Margins

arXiv:2608.30028v1 Announce Type: new Abstract: This paper introduces a family of multiclass linear Perceptron classifiers with a multiplicative margin mechanism (MMPerc), as an alternative to standa...

By Dmitri Rachkovskij, Evgeny Osipov, Olexander Volkov, Daswin De Silva, Denis Kleyko

safety

arXiv Machine Learning

Sep 1

Certified Safety Radii in Forecast-Error Space for Wasserstein Distributionally Robust Small Signal Stability-Constrained AC Optimal Power Flow via Lifted Spectrahedral Containment

arXiv:2608.30201v1 Announce Type: new Abstract: Directly robustifying small-signal stability in AC optimal power flow is challenging since the stability boundary in the original uncertainty space is...

By Ziqi Zhang, Xi Chen

safety

arXiv Machine Learning

Sep 1

Context Staircase: Signature-Aligned Dynamics of Token Embeddings under Small Initialization

arXiv:2608.30315v1 Announce Type: new Abstract: Token embeddings are the basic representational units that connect discrete tokens with continuous computation in language models. Although modern lang...

By Junjie Yao, Liangkai Hang, Zhi-Qin John Xu

llms rag safety

arXiv Machine Learning

Sep 1

Generative multi-domain transfer learning for fault detection in data-scarce wind turbines

arXiv:2608.30323v1 Announce Type: new Abstract: Normal behavior models have shown promise for reliable fault detection in wind turbines. However, these unsupervised anomaly detection models require s...

By Stefan Jonas, Angela Meyer

fine-tuning safety

arXiv Machine Learning

Sep 1

RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search

arXiv:2608.30384v1 Announce Type: new Abstract: By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension,...

By Rastislav Lenhardt, Teodora Dobos, Thomas Vecchiato, Jiri Isa, Igor Ginzburg

rag efficiency benchmarks safety

arXiv Machine Learning

Sep 1

VisER: Visual Evidence and Reliance for Object Hallucination Detection in LVLMs

arXiv:2608.30480v1 Announce Type: cross Abstract: Object hallucination remains a persistent reliability issue in large vision-language models, where generated object mentions may sound plausible but...

By Afsaneh Hasanebrahimi, Hanxun Huang, Christopher Leckie, Sarah Erfani

llms multimodal benchmarks safety

arXiv Machine Learning

Sep 1

Expected flow networks in stochastic environments and two-player zero-sum games

arXiv:2310.02779v3 Announce Type: replace Abstract: Generative flow networks (GFlowNets) are sequential sampling models trained to match a given distribution. GFlowNets have been successfully applied...

By Marco Jiralerspong, Bilun Sun, Danilo Vucetic, Tianyu Zhang, Yoshua Bengio, Gauthier Gidel, Esmeralda S. Whitammer

reinforcement-learning safety

arXiv Machine Learning

Sep 1

H-FedSN: Personalized Sparse Networks for Efficient and Accurate Hierarchical Federated Learning for IoT Applications

arXiv:2412.06210v3 Announce Type: replace Abstract: With the rapid development of the Internet of Things (IoT), federated learning (FL) has gained increasing attention for its privacy-preserving use...

By Jiechao Gao, Yuangang Li, Jie Wang, Yue Zhao, Michael Lepech, Brad Campbell

safety

arXiv Machine Learning

Sep 1

Constrained Group Relative Policy Optimization

arXiv:2602.05863v3 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) remains the dominant critic-free approach for fine-tuning LLMs and VLMs, but its compatibility with const...

By Roger Girgis, Rodrigue de Schaetzen, Luke Rowe, Azal\'ee Robitaille, Christopher Pal, Liam Paull

llms agents robotics fine-tuning benchmarks safety

arXiv Machine Learning

Sep 1

PairAlign: A Framework for Autoregressive Tokenization via Self-Alignment with Applications to Audio Tokenization

arXiv:2605.06582v4 Announce Type: replace Abstract: Modern learning systems represent perceptual signals with continuous vectors, but comparison, retrieval, memory, alignment, and reasoning are often...

By Adhiraj Banerjee, Vipul Arora

nlp efficiency safety

arXiv Machine Learning

Sep 1

Generalist Graph Anomaly Detection via Prototype-Based Distillation

arXiv:2605.26857v2 Announce Type: replace Abstract: Driven by the pressing demand for graph anomaly detection (GAD) in high-stakes domains, the generalist GAD paradigm, which trains a single detector...

By Yiming Xu, Zihan Chen, Zhen Peng, Song Wang, Bin Shi, Bo Dong, Chao Shen

efficiency safety

arXiv Machine Learning

Sep 1

Classification Drives Geographic Bias in Street Scene Segmentation

arXiv:2412.11061v2 Announce Type: replace-cross Abstract: Previous studies showed that image datasets lacking geographic diversity can lead to biased performance in models trained on them. While earl...

By Rahul Nair, Gabriel Tseng, Esther Rolf, Bhanu Tokas, Hannah Kerner

computer-vision safety

arXiv Machine Learning

Sep 1

Mirror Descent Linearized Augmented Lagrangian Methods for Nonconvex Constrained Stochastic Zeroth-Order Optimization

arXiv:2504.09409v3 Announce Type: replace-cross Abstract: In this paper, we study nonconvex constrained stochastic zeroth-order optimization problems with exact constraints and stochastic objective e...

By Qiankun Shi, Han Yuan, Xiao Wang, Hao Wang

safety

arXiv Machine Learning

Sep 1

Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues

arXiv:2601.12868v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly operate in high-stakes settings where demographic attributes such as race and ethnicity may be expl...

By Shiyue Hu, Ruizhe Li, Yanjun Gao

llms nlp safety

arXiv Machine Learning

Sep 1

Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion

arXiv:2601.21670v4 Announce Type: replace-cross Abstract: Multimodal fusion is often treated as an optimization-balancing problem, where training signals are adjusted to prevent one modality from dom...

By Zixuan Xia, Hao Wang, Pengcheng Weng, Yanyu Qian, Yangxin Xu, William Dan, Fei Wang

rag multimodal benchmarks safety

arXiv Machine Learning

Sep 1

NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval

arXiv:2603.12824v3 Announce Type: replace-cross Abstract: Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi...

By Zhuchenyang Liu, Yao Zhang, Yu Xiao

llms rag efficiency multimodal benchmarks safety

arXiv Computation and Language

Sep 1

ReVA: A Region-Aware Visual Assistant for Visually Grounded Question Answering

arXiv:2608.28707v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with quest...

By Anoop Senthil

llms rag computer-vision nlp multimodal safety

arXiv Computation and Language

Sep 1

Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops

arXiv:2608.28860v1 Announce Type: new Abstract: Large Language Models (LLMs) often answer the same factual question differently across languages. We study whether cross-lingual latent-space intervent...

By Faeze Ghorbanpour, Constanza Fierro, Alexander Fraser, Anders Sogaard

llms safety

Get the daily briefing