Large language models

Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.

31,046 stories · RSS feed

arXiv AI

Jun 10

IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts

arXiv:2606. 09908v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data, making privacy a major challenge for their design and evaluation.

By Ayana Hussain, Soumya Sharma, Golnoosh Farnadi, Nicholas Vincent, H\'eber Hwang Arcolezi, Ulrich A\"ivodji

llms benchmarks safety

arXiv Machine Learning

Jun 10

How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

arXiv:2606. 10646v1 Announce Type: new Abstract: Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing to distinguish decisive reasoning steps from routine formatting or fluent filler.

By Zhichen Dong, Yang Li, Yuhan Sun, Weixun Wang, Yijia Luo, Zinian Peng, Taiheng Ye, Chao Yang, Wenbo Su, Yu Cheng, Bo Zheng, Junchi Yan

llms reinforcement-learning efficiency

arXiv Machine Learning

Jun 10

Hasse Diagrams for Attention: A Partial Order Framework for Designing Transformer Masks

arXiv:2606. 09951v1 Announce Type: new Abstract: During the training of large Transformer models, attention masks regulate the scope and direction of information flow across a sequence.

By Chentao Li, Han Guo

llms

arXiv Machine Learning

Jun 10

Spatiotemporal Graph Transformer for 3D Neighborhood Interaction and Quality Prediction in Metal Additive Manufacturing

arXiv:2606. 10227v1 Announce Type: new Abstract: Metal additive manufacturing enables the fabrication of complex parts, but achieving consistent build quality remains challenging due to interactions induced by repeated layer-wise melting, solidification, and reheating across the 3D build.

By Joyce Karen Pelaez, Siqi Zhang, Hoo Sang Ko

llms multimodal

arXiv Machine Learning

Jun 10

Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs

arXiv:2606. 09876v1 Announce Type: new Abstract: Large language models often express high confidence in answers that are wrong.

By Ke Li, Chongzhe Zhang, Zifan Zeng, Feng Liu, Qunli Zhang, Zheng Hu

llms

arXiv AI

Jun 10

CITRAS: Covariate-Informed Transformer for Time Series Forecasting

arXiv:2503. 24007v4 Announce Type: replace-cross Abstract: In time series forecasting, covariates represent external factors that influence target variables.

By Yosuke Yamaguchi, Issei Suemitsu, Wenpeng Wei

llms

arXiv AI

Jun 10

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

arXiv:2407. 20242v5 Announce Type: replace-cross Abstract: Embodied AI represents systems where AI is integrated into physical entities.

By Hangtao Zhang, Chenyu Zhu, Xianlong Wang, Ziqi Zhou, Changgan Yin, Minghui Li, Lulu Xue, Yichen Wang, Shengshan Hu, Aishan Liu, Peijin Guo, Leo Yu Zhang

llms agents robotics benchmarks safety

arXiv AI

Jun 10

Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training

arXiv:2606. 10709v1 Announce Type: cross Abstract: The use of GRPO-style algorithms has become the standard strategy for training LLM search agents under outcome-only rewards.

By Jo\~ao Coelho, Jo\~ao Magalh\~aes, Bruno Martins, Chenyan Xiong

llms agents reinforcement-learning benchmarks

arXiv AI

Jun 10

Local Is Not a Sufficient Privacy Boundary: Governing OS-Integrated On-Device AI

arXiv:2606. 10173v1 Announce Type: cross Abstract: As AI systems move into operating systems, privacy no longer turns only on whether a model runs locally.

By Jonghyun Chung, Sanket Badhe

llms rag safety

arXiv AI

Jun 10

Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies

arXiv:2606. 10371v1 Announce Type: cross Abstract: Diffusion-based action generation has become a foundational component of embodied AI, but its reliance on visual conditioning leaves deployed visuomotor policies vulnerable to adversarial manipulation.

By Zi Yin, Peilin Chai, Siyuan Huang, Zhanhao Hu

llms diffusion robotics safety

arXiv AI

Jun 10

AutoPDE: Reliable Agentic PDE Solving via Explicitly Represented Solver Strategies

arXiv:2606. 10752v1 Announce Type: new Abstract: Numerical solvers for partial differential equations (PDEs) are core computational tools in science and engineering.

By Huanshuo Dong, Keyao Zhang, Hong Wang, Zhezheng Hao, Zhiwei Zhuang, Ziyan Liu, Jiacong Wang, Gengyuan Liu, Xin Jin

llms agents

arXiv Machine Learning

Jun 10

CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecasting

arXiv:2606. 10798v1 Announce Type: new Abstract: Pretrained time series foundation models (TSFMs) have enabled zero-shot forecasting on unseen target series.

By Yosuke Yamaguchi, Issei Suemitsu, Yuki Kajihara, Wenpeng Wei

llms benchmarks

arXiv AI

Jun 10

An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models

arXiv:2606. 09843v1 Announce Type: cross Abstract: Large language models (LLMs) produce stable self-reports on personality inventories, but these self-reports do not predict observed behavior.

By Juan Manuel Contreras

llms safety

arXiv Machine Learning

Jun 10

DAH-Net: A Dual-Attention Hybrid Network for Interpretable and Robust EEG-Based Emotion Recognition

arXiv:2602. 06411v2 Announce Type: replace Abstract: EEG-based emotion recognition supports affective brain-computer interfaces and mental health monitoring yet remains challenged by signal complexity, subject variability, and limited interpretability.

By S M Rakib UI Karim, Diponkor Bala, Wenyi Lu, Rownak Ara Rasul, Sean Goggins

llms safety

arXiv Machine Learning

Jun 10

The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring

arXiv:2606. 10327v1 Announce Type: cross Abstract: Automated Essay Scoring (AES) systems must judge interdependent discourse elements (e.

By Ali Keramati, Mark Warschauer

llms nlp fine-tuning efficiency

arXiv Machine Learning

Jun 10

Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads

arXiv:2606. 09956v1 Announce Type: cross Abstract: The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severely underdeveloped.

By Nikolai Rozanov

llms agents nlp efficiency benchmarks safety

arXiv Machine Learning

Jun 10

Alignment Defends LLMs from Property Inference Attacks

arXiv:2606. 10217v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties.

By Pengrun Huang, Chhavi Yadav, Ruihan Wu, Kamalika Chaudhuri

llms reinforcement-learning fine-tuning safety

arXiv AI

Jun 10

The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans

arXiv:2606. 09844v1 Announce Type: cross Abstract: Large Language Models (LLMs) alter their privacy behavior based on the perceived identity of their interlocutor.

By Faouzi El Yagoubi, Godwin Badu-Marfo, Ranwa Al Mallah

llms agents benchmarks safety

arXiv AI

Jun 10

Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought

arXiv:2509. 04027v4 Announce Type: replace Abstract: Test-time scaling, primarily manifested through multi-step Chain-of-Thought (CoT) reasoning via Reinforcement Learning (RL), has emerged as a pivotal paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs).

By Zeyu Gan, Hao Yi, Yong Liu

llms reinforcement-learning

arXiv AI

Jun 10

FOGO: Forgetting-aware Orthogonalization Optimizer

arXiv:2606. 10406v1 Announce Type: cross Abstract: We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch gradients suppress rare but useful update directions, causing short-term forgetting at every step.

By Toan Nguyen, Yang Liu, Trung Le, Celso de Melo, Flora D. Salim

llms fine-tuning

Get the daily briefing