← Back to all news

AI safety and alignment

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

17,798 stories · RSS feed

arXiv Machine Learning

Sep 23

PACT: From Credit Assignment to Critic Alignment

arXiv:2609.26355v1 Announce Type: new Abstract: Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level credit lacks a generally accepted ma...

By Jiayan Fu, Hang Xu, Yong Zhang, Zhaokai Luo, Yao Hu, Dongyan Zhao, Mu Chuan

llms agents reinforcement-learning efficiency benchmarks safety

arXiv Machine Learning

Sep 23

Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning

arXiv:2609.26708v1 Announce Type: new Abstract: Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathema...

By Yuanteng Chen, Zhilei Liu, Peisong Wang, Yuantian Shao, Chuangyi Li, Weining Wang, Shuang Qiu, Gang Li, Jing Liu, Jian Cheng

efficiency benchmarks safety

arXiv Machine Learning

Sep 23

Target alignment, dilution and forecast selection when cross-sectional forecasts share a common target

arXiv:2609.26303v1 Announce Type: cross Abstract: Forecasters often score the same units per date against one standardized realized outcome. We show that every standardized forecast splits exactly in...

By Masoud Soleimani

arXiv Machine Learning

Sep 23

The Challenge of Identifying the Origin of Black-Box Large Language Models

arXiv:2503.04332v2 Announce Type: replace-cross Abstract: The tremendous commercial potential of large language models (LLMs) has heightened concerns over their unauthorized use. To address this, we...

By Ziqing Yang, Yixin Wu, Yun Shen, Wei Dai, Michael Backes, Yang Zhang

llms rag benchmarks safety

arXiv Machine Learning

Sep 23

Text-only adaptation in LLM-based ASR through text denoising

arXiv:2601.20900v4 Announce Type: replace-cross Abstract: Adapting large language model (LLM)-based automatic speech recognition (ASR) systems to new domains using text-only data is a significant yet...

By Andr\'es Carofilis, Sergio Burdisso, Esa\'u Villatoro-Tello, Shashi Kumar, Kadri Hacioglu, Srikanth Madikeri, Pradeep Rangappa, Manjunath K E, Petr Motlicek, Shankar Venkatesan, Andreas Stolcke

llms fine-tuning multimodal benchmarks safety

arXiv Computation and Language

Sep 23

FinFIRST: Benchmarking Search Agents for Financial Information Retrieval, Sourcing and Traceability

arXiv:2609.25192v1 Announce Type: new Abstract: Financial search is a highly demanding task for LLM agents, requiring not only a correct final answer but also temporally valid information retrieval,...

By Wenqing Wang, Haitao Xiang, Xinyi Zhao, Mingming Yin, Ying Zhong, Zhaoxin Huan, Qiheng Zhou, Jin Zhu, Xiaolu Zhang, Shi Chang, Jun Zhou

llms agents benchmarks safety

arXiv Computation and Language

Sep 23

FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing

arXiv:2609.25298v1 Announce Type: new Abstract: Cultural evaluation coverage and robustness in language models are difficult to diagnose because pretraining corpora and cultural benchmarks are rarely...

By Yusser Al Ghussin, Eva Gavaller, Cristina Espa\~na-Bonet, Josef van Genabith, Simon Ostermann

llms nlp benchmarks safety

arXiv Computation and Language

Sep 23

Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction

arXiv:2609.25176v1 Announce Type: cross Abstract: Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these...

By Lujia Bao, Qian Chen, Luyao Cheng, Chong Deng, Yuxiang Kong, Xiangang Li, Xu Li, Jiaqing Liu, Chao-Hong Tan, Haoyu Wang, Wen Wang, Xilou Wang, Junhao Xu, Liang Yi, Binbin Zhang, Qinglin Zhang, Qiquan Zhang

agents fine-tuning efficiency safety

arXiv Computation and Language

Sep 23

Universal Fractal Natural Language Decision Map: Real-Time Edge Triage Across Heterogeneous Domains

arXiv:2609.25498v1 Announce Type: cross Abstract: Deploying Large Language Models for runtime operational triage incurs prohibitive latency (>100-500 ms), high VRAM requirements (>4-8 GB), and excess...

By Volkan Da\u{g}l{\i}, Zerrin Da\u{g}l{\i}, Da\u{g}han Da\u{g}l{\i}

llms efficiency safety

arXiv Computation and Language

Sep 23

SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking

arXiv:2508.15526v2 Announce Type: replace Abstract: The rapid proliferation of large language models (LLMs) has intensified the requirement for reliable safety evaluation to uncover model vulnerabili...

By Xiangyang Zhu, Yuan Tian, Chunyi Li, Kaiwei Zhang, Wei Sun, Guangtao Zhai

llms agents benchmarks safety

arXiv Computation and Language

Sep 23

GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning

arXiv:2605.25200v3 Announce Type: replace Abstract: Travel planning in the real world is overwhelmingly a \textit{group} activity, yet existing LLM travel-planning benchmarks reduce it to a single us...

By Xiang Cheng, Yulan Hu, Lulu Zheng, Xiangwen Zhang, Zheng Pan, Xin Li, Yong Liu

llms agents benchmarks safety

arXiv Computer Vision

Sep 23

Deepfakes and Synthetic Media: Generation, Detection, and Governance

arXiv:2609.25017v1 Announce Type: new Abstract: Deepfakes, synthetic audiovisual content produced by deep generative models, have escalated into a critical threat across civilian and military domains...

By Alexandros Gazis, Efstathios Karypidis, Kleanthi Santamouri, Theodoros Vavouras, Nikos E. Mastorakis, Stylianos Pappas

llms diffusion computer-vision robotics benchmarks safety

arXiv Computer Vision

Sep 23

Towards Systematic Qualification of Vision-Language Models for Automotive Perception Systems

arXiv:2609.25945v1 Announce Type: new Abstract: The field of Artificial Intelligence has been adopted for many application domains. Vision Language Models are one of the recently advanced AI techniqu...

By Malsha Ashani Mahawatta Dona, Konstantinos Rokanas, Alexander S\"afstr\"om, Krishna Ronanki, Christian Berger

llms multimodal benchmarks safety

arXiv Computer Vision

Sep 23

Cellular-Communication-Level Interpretability for Pathology Foundation Models via Graph Distillation on Microenvironment

arXiv:2609.26073v1 Announce Type: new Abstract: Pathology foundation models (PFMs) provide strong tile-level representations but remain difficult to interpret at the cellular and microenvironmental s...

By Yuxiang Xiao, Zhiwei Chen, Dan Dai, Wei Li, Tianyang Zhang, Yakun Ju, Yang Hu, Kaixiang Yang

rag efficiency safety

arXiv Computer Vision

Sep 23

RECAP: Relation Evidence Calibration for Detecting Spatial Relation Hallucinations in Vision-Language Models

arXiv:2609.26093v1 Announce Type: new Abstract: Vision-language models can answer spatial relation questions confidently even when the image supports an incompatible relation. We formulate relation-g...

By Feixiang Liu, Qiang Qiu, Qingyang Li, Hui Xu

llms multimodal safety

arXiv Computer Vision

Sep 23

Complementary Roles of Radiomics and Foundation Representations in Renal Cell Carcinoma Classification: A Comparative Study of 2D and 3D CT Encodings

arXiv:2609.26463v1 Announce Type: new Abstract: Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. R...

By Yuan Liang, Sourav Bhattacharjee, Abraham Campbell

benchmarks safety

arXiv Computer Vision

Sep 23

Radiomics--Foundation Fusion for Interpretable RCC Classification: Internal Benchmarking and Exploratory External Transfer

arXiv:2609.26578v1 Announce Type: new Abstract: Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced CT remains clinically challenging because clear cell...

By Yuan Liang, Fangyijie Wang, Kathleen M. Curran, Gu\'enol\'e Silvestre, Sourav Bhattacharjee, Abraham Campbell

benchmarks safety

arXiv Computer Vision

Sep 23

Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving

arXiv:2609.25831v1 Announce Type: cross Abstract: Recent VLM-based autonomous driving planners adopt GRPO-style reinforcement learning to optimize driving performance. However, existing GRPO recipes...

By Yuqi Ye, Shangkun Sun, Junhong Lin, Jiayi Zhao, Changhao Peng, Wei Zheng, Guoqing Liu, Tiesong Zhao, Wei Gao

agents reinforcement-learning robotics multimodal benchmarks safety

arXiv Computer Vision

Sep 23

Bayesian Fusion of Active Contour Models and ConvNet Priors for Standing Dead Tree Segmentation

arXiv:2410.07421v2 Announce Type: replace Abstract: Instance segmentation is a core computer vision task with great practical significance. Recent advances, driven by large-scale benchmark datasets,...

By Przemyslaw Polewski, Jacquelyn Shelton, Wei Yao, Marco Heurich

diffusion computer-vision benchmarks safety

arXiv Computer Vision

Sep 23

Route-MHT: Multimodal Transformer Guardrails for Thermal Visual Place Recognition

arXiv:2607.04745v2 Announce Type: replace-cross Abstract: Strong mapped-region thermal visual place recognition (VPR) does not ensure safe rejection of unmapped queries. We identify and quantify this...

By Zhiyuan Lu, Kanji Tanaka

llms robotics multimodal benchmarks safety