AI safety and alignment

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

11,365 stories · RSS feed

arXiv Machine Learning

Jun 5

SHALA-LLM: Smartly Handling Ambiguous Labels in Aligning LLMs

arXiv:2606. 05376v1 Announce Type: new Abstract: Many human-centered tasks, including natural language inference (NLI) and emotion recognition (ER), have multiple plausible interpretations, leading to label ambiguity and challenging disagreements across human annotators.

By Jingyao Wu, Ashley Wang, Keane Ong, Paul Pu Liang, Rosalind Picard

llms reinforcement-learning benchmarks safety

arXiv Machine Learning

Jun 5

Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models

arXiv:2606. 05737v1 Announce Type: cross Abstract: Diffusion-based vision-language-action (VLA) models often inherit the image-generation view: actions are generated by iterative denoising.

By Yitong Chen, Shiduo Zhang, Jingjing Gong, Xipeng Qiu

diffusion robotics efficiency multimodal safety

arXiv Machine Learning

Jun 5

Towards AI epidemiology: a measurement standardisation framework for prospective risk detection

arXiv:2512. 15783v3 Announce Type: replace-cross Abstract: This paper proposes a measurement standardisation framework that compresses expert-AI interactions into structured, comparable fields for prospective risk detection in deployed AI systems, without access to model internals.

By Kit Tempest-Walters

llms safety

arXiv Machine Learning

Jun 5

PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis

arXiv:2606. 06293v1 Announce Type: new Abstract: Whilst the vulnerability of graph neural networks (GNNs) to adversarial attacks poses a critical threat to graph representation learning, the understanding of the robust generalization behavior remains a fundamental challenge in the adversarial setting.

By Ziling Liang, Xinping Yi, Qingsong Wen, Shi Jin

safety

arXiv Machine Learning

Jun 5

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

arXiv:2606. 05680v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip design.

By Mohammad Akyash, Nowfel Mashnoor, Kimia Azar, Hadi Kamali

llms rag agents fine-tuning safety

arXiv Machine Learning

Jun 5

FATE: Focal-modulated Attention Encoder for Multivariate Time-series Forecasting

arXiv:2408. 11336v3 Announce Type: replace Abstract: Climate change stands as one of the most pressing global challenges of the twenty-first century, with far-reaching consequences such as rising sea levels, melting glaciers, and increasingly extreme weather patterns.

By Tajamul Ashraf, Janibul Bashir

llms benchmarks safety

arXiv Machine Learning

Jun 5

Learning to model pediatric asthma exacerbation from multiple risk factors: a case study in coastal Virginia

arXiv:2606. 06174v1 Announce Type: new Abstract: Childhood asthma is a common illness exacerbated by air pollution as well as meteorological and neighborhood-level socioeconomic factors.

By Jonathan Colen, Eric Werner, Maryam Golbazi, Heather Richter, Diana McSpadden, Amy Quinn, Jocel Santos, Mary Jane Darling, Mary Margaret Gleason

safety

arXiv Machine Learning

Jun 5

Domain-Adapted Small Language Models with Hybrid Post-Processing: Achieving Cost-Efficient, Low-Latency Multi-Label Structured Prediction via LoRA Fine-Tuning on Scarce Data

arXiv:2606. 05781v1 Announce Type: new Abstract: Deploying frontier large language models (LLMs) for domain-specific structured evaluation tasks often incurs substantial latency, cost, and data privacy overhead.

By Srinivasan Manoharan, Dilipkumar Nallusamy, Sachin Kumar, Haifeng Wu

llms fine-tuning safety

arXiv Machine Learning

Jun 5

Non-Negative Matrix Factorization for Event Data

arXiv:2606. 06205v1 Announce Type: new Abstract: Continuous-time event data, in which entities emit instantaneous events over time, arises naturally across many domains such as neuroscience, seismology, and social networks.

By Rapha\"el Romero

safety

arXiv Machine Learning

Jun 5

Topology-Aware Differential Privacy in Federated Learning

arXiv:2506. 19260v2 Announce Type: replace-cross Abstract: Federated learning transmits only model updates to protect client data, and differentially private SGD (DP-SGD) bounds content-level leakage through those updates.

By Murtaza Rangwala, Richard O. Sinnott, Rajkumar Buyya

safety

arXiv Machine Learning

Jun 5

High-Dimensional Theory of LoRA Fine-Tuning in a Solvable Attention Model

arXiv:2606. 05899v1 Announce Type: new Abstract: We develop a high-dimensional statistical theory of low-rank adaptation (LoRA) in attention models, capturing the interplay between pre-training and fine-tuning.

By O. Duranthon, F. Boncoraglio, L. Zdeborov\'a

fine-tuning safety

arXiv Machine Learning

Jun 5

Soft Sequence Policy Optimization

arXiv:2602. 19327v3 Announce Type: replace Abstract: A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO).

By Svetlana Glazyrina, Maksim Kryzhanovskiy, Roman Ischenko

llms reinforcement-learning safety

arXiv Machine Learning

Jun 5

Vision Hopfield Memory Networks

arXiv:2603. 25157v2 Announce Type: replace Abstract: Recent vision and multimodal foundation backbones, such as Transformer families and state-space models like Mamba, have achieved remarkable progress, enabling unified modeling across images, text, and beyond.

By Jianfeng Wang, Amine M'Charrak, Luk Koska, Xiangtao Wang, Daniel Petriceanu, Ruizhi Wang, Michael Bumbar, Luca Pinchetti, Thomas Lukasiewicz

llms computer-vision multimodal benchmarks safety

arXiv Machine Learning

Jun 5

GenAutoML: An Agentic Framework for Dynamic Architecture Generation and Optimization in Time-Series Analysis

arXiv:2606. 05860v1 Announce Type: new Abstract: Designing neural architectures for time-series forecasting and anomaly detection remains a resource-intensive task that often requires substantial domain expertise.

By Oleeviya Babu Poikarayil, C\'edric Schockaert, Abdulrahman Nahhas, Christian Daase, Mursal Dawodi, Jawid Ahmad Baktash

llms agents efficiency benchmarks safety

arXiv Machine Learning

Jun 5

Short paper: Models in the dark -- Rectification and erasure under GDPR in ML supply chains

arXiv:2606. 05946v1 Announce Type: new Abstract: The rights to rectification and erasure, as established under the General Data Protection Regulation (GDPR), are central to protecting individuals' privacy.

By Henrik Gra{\ss}hoff, Malte Hansen, Meiko Jensen, Sara Ramezanian

safety

arXiv Machine Learning

Jun 5

Uncovering Model Processing Strategies with Non-Negative Per-Example Fisher Factorization

arXiv:2310. 04649v3 Announce Type: replace Abstract: We introduce NPEFF (Non-Negative Per-Example Fisher Factorization), an interpretability method that aims to uncover strategies used by a model to generate its predictions.

By Michael Matena, Colin Raffel

llms benchmarks safety

arXiv Machine Learning

Jun 5

Expand Neurons, Not Parameters

arXiv:2510. 04500v3 Announce Type: replace Abstract: This work demonstrates how increasing the number of neurons in a network without increasing its total number of non-zero parameters improves performance.

By Linghao Kong, Inimai Subramanian, Yonadav Shavit, Micah Adler, Dan Alistarh, Nir Shavit

rag safety

arXiv Machine Learning

Jun 5

Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models

arXiv:2511. 21338v2 Announce Type: replace Abstract: Masked Diffusion Language Models (MDLMs) have recently emerged as a promising alternative to Autoregressive Language Models (ARLMs), leveraging a denoising objective that, in principle, should enable more uniform context utilisation.

By Julianna Piskorz, Cristina Pinneri, Alvaro Correia, Motasem Alfarra, Risheek Garrepalli, Christos Louizos

llms diffusion fine-tuning safety

arXiv Machine Learning

Jun 5

Electricity price forecasting across Norway's five bidding zones in the post-crisis era

arXiv:2604. 26634v2 Announce Type: replace Abstract: Norway's electricity market is heavily dominated by hydropower, but the 2021-2022 energy crisis and stronger integration with Continental Europe have fundamentally altered price formation, reducing the reliability of forecasting models calibrated on historical data.

By My Thi Diem Phan, Trung Tuyen Truong, Hoai Phuong Ha, Dat Thanh Nguyen

multimodal benchmarks safety

arXiv Machine Learning

Jun 5

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

arXiv:2606. 06333v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) are widely used for mechanistic interpretability in large language models, yet their formulation assigns each latent feature a single decoder direction, implicitly assuming features to be one-dimensional.

By Seyed Arshan Dalili, Mehrdad Mahdavi

llms efficiency safety

Get the daily briefing