AI safety and alignment

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

18,070 stories · RSS feed

arXiv AI

Jul 24

Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces

arXiv:2601. 07556v2 Announce Type: replace-cross Abstract: Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) face significant deployment challenges due to inter-subject variability, signal non-stationarity, and computational constraints.

By Siyang Li, Jiayi Ouyang, Zhenyao Cui, Ziwei Wang, Tianwang Jia, Feng Wan, Dongrui Wu

safety

arXiv AI

Jul 24

Knowledge-Guided Time-Varying Causal Inference for Arctic Sea Ice Dynamics

arXiv:2601. 17647v3 Announce Type: replace-cross Abstract: Quantifying the causal relationship between sea ice thickness and sea surface height (SSH) is essential for understanding the mechanisms driving polar climate dynamics.

By Akila Sampath, Vandana Janeja, Jianwu Wang

diffusion benchmarks safety

arXiv Machine Learning

Jul 24

Environment-Aware Channel Inference via Cross-Modal Flow: From Multimodal Sensing to Wireless Channels

arXiv:2512. 04966v2 Announce Type: replace-cross Abstract: Accurate channel state information (CSI) underpins reliable and efficient wireless communication.

By Guangming Liang, Mingjie Yang, Dongzhu Liu, Paul Henderson, Lajos Hanzo

diffusion multimodal benchmarks safety

arXiv Machine Learning

Jul 24

Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs

arXiv:2607. 20517v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) over heterogeneous PDF collections remains challenging due to multimodal content, domain-specific terminology, and the need for multi-hop reasoning across dispersed evidence.

By Takato Yasuno

llms rag computer-vision multimodal benchmarks safety

arXiv Machine Learning

Jul 24

Safety-oriented sidewalk and road segmentation for smartphone-based assistive navigation

arXiv:2607. 21137v1 Announce Type: cross Abstract: Independent sidewalk mobility is essential for blind and visually impaired pedestrians (BVIPs), yet smartphone-based assistive navigation requires perception models that distinguish walkable sidewalks from adjacent unsafe regions.

By Hakan Calim, Anamaria Dumitrescu, Adarsh Bhandary Panambur, Huzaifa Asif, Andreas Maier

computer-vision fine-tuning benchmarks safety

arXiv AI

Jul 24

Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models

arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.

By Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz

llms fine-tuning safety

arXiv Machine Learning

Jul 24

From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python

arXiv:2607. 21069v1 Announce Type: new Abstract: The original ALPHA benchmark introduced a taxonomy-aware penalty for evaluating CWE-level vulnerability prediction in Python and proposed that the penalty could theoretically also serve as a training signal.

By Muntasir Adnan, Manile Srun, Carlos C. N. Kuhn

reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jul 24

DataPrep-Bench: Benchmarking LLMs as Training Data Preparators

arXiv:2607. 20465v1 Announce Type: new Abstract: The quality of training data fundamentally determines the capabilities of large language models (LLMs), yet no unified benchmark exists to measure how well LLMs, agents, and data-centric workflows actually prepare training data end to end.

By Hao Liang, Qifeng Cai, Yibo Lin, Jianzhuo Du, Qifeng Xia, Sizhe Qiu, Linzhuang Sun, Meiyi Qiang, Zhaoyang Han, Xiaochen Ma, Bohan Zeng, Ruichuan An, Conghui He, Wentao Zhang

llms agents fine-tuning benchmarks safety data-engineering

arXiv AI

Jul 24

Generative Artificial Intelligence in Bioinformatics: A Systematic Review of Models, Applications, and Methodological Advances

arXiv:2511. 03354v2 Announce Type: replace-cross Abstract: Generative artificial intelligence (GenAI) is transforming bioinformatics by advancing genomics, proteomics, transcriptomics, structural biology, and drug discovery.

By Wasimul Karim, Riasad Alvi, Sayeem Been Zaman, Arefin Ittesafun Abian, Mohaimenul Azam Khan Raiaan, Saddam Mukta, Md Rafi Ur Rashid, Md Rafiqul Islam, Yakub Sebastian, Sami Azam

benchmarks safety

arXiv AI

Jul 24

When Are Reasoning-Based Guardrails Not Efficient? ResponseGuard: A Fast Vision-Language Guard for Real-Time Moderation

arXiv:2607. 21401v1 Announce Type: cross Abstract: A vision-language AI assistant returns its answer as a stream of generated tokens.

By Dongbin Na

llms multimodal benchmarks safety

arXiv AI

Jul 24

DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation

arXiv:2607. 21371v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) leverages textual semantics to segment objects beyond predefined categories.

By Sung-Hoon Yoon, Hoyong Kwon, Changgyoon Oh, Kuk-Jin Yoon

rag computer-vision multimodal benchmarks safety

arXiv Machine Learning

Jul 24

How Many Bits Can an Adapter Write? Measuring the Capacity and Memorization of Parameter-Efficient Fine-Tuning

arXiv:2607. 21351v1 Announce Type: new Abstract: A LoRA adapter is a few megabytes that almost everyone treats as a skill rather than a record of the data behind it.

By Kaizhen Tan, Heqing Du, Yang Feng

reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jul 24

Chronofy: A Temporal-Logical Decay Architecture for Information Validity in Time-Aware Retrieval-Augmented Generation

arXiv:2607. 20560v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs.

By Muntaser Syed, Marius Silaghi, Sheikh Abujar, Sharun Akter

llms rag benchmarks safety

arXiv AI

Jul 24

Directional Hallucinations: Ideological Drift in News-Grounded LLM Question Answering

arXiv:2607. 20487v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to answer questions about political information, including in election-adjacent information settings where factual errors and ideological distortions are high-stakes.

By Chendi Wang, Liam Cunningham, Tom Yishay, Jieying Chen

llms nlp fine-tuning safety

arXiv Machine Learning

Jul 24

Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs

arXiv:2607. 21291v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong generation and reasoning performance, but the Transformer architecture incurs high inference cost.

By Yidu Wu, Xiang Wang, Kejie Zhao, Zhangchi Wang, Qinghai Guo, Xiaoying Tang

llms fine-tuning efficiency safety

arXiv AI

Jul 24

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation

arXiv:2607. 21518v1 Announce Type: new Abstract: Even a current high-capability LLM can appear safer when shown a dangerous objective directly than when other agents transform and relay its direction.

By Linjun Li

llms agents robotics safety

arXiv AI

Jul 24

Evaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective

arXiv:2604. 25077v2 Announce Type: replace Abstract: Weak-to-strong alignment offers a promising route to scalable supervision, but it can fail when a strong model becomes confidently wrong on examples that lie in the weak model's blind spots.

By Hamid Osooli, Kareema Batool, Rick Gentry, Tiasa Singha Roy, Ashwin Gupta, Anirudha Ramesh

reinforcement-learning fine-tuning safety

arXiv AI

Jul 24

Drive As You Like: Multi-Head Diffusion with Reinforcement Learning for Personalized Driving

arXiv:2508. 16947v2 Announce Type: replace-cross Abstract: Despite significant progress, imitation learning-based autonomous driving planners remain largely restricted to reproducing high-frequency biased behaviors, overlooking the inherent behavioral diversity of human driving.

By Fan Ding, Xuewen Luo, Fucai Ke, Hwa Hui Tew, Susilawati Susilawati, Vishnu Monn Baskaran, Junn Yong Loo

llms agents diffusion reinforcement-learning robotics benchmarks safety

arXiv Machine Learning

Jul 24

End-to-End Learning of Safe Optimal Feedback Control in High Dimensions with Control Barrier Function Layers

arXiv:2607. 20674v1 Announce Type: new Abstract: We consider the problem of learning high-dimensional semi-global feedback controllers under hard safety constraints enforced by control barrier functions (CBFs).

By Xingjian Li, Kelvin Kan, Deepanshu Verma, Krishna Kumar, Stanley Osher, Samy Wu Fung

rag agents safety

arXiv Machine Learning

Jul 24

Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusion

arXiv:2607. 20742v1 Announce Type: new Abstract: Multimodal learning is a robust approach to improve predictive performance in applications such as medical prognosis.

By Mohammad Raahemi, Ali Sekhavati, Alireza Maleki, Hamid Nasiri

multimodal benchmarks safety data-engineering

Get the daily briefing