Large language models

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

21,300 stories · RSS feed

arXiv AI

Jul 21

MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs

arXiv:2507. 20804v3 Announce Type: replace Abstract: Large Language Models (LLMs) suffer from hallucinations due to their static parametric knowledge.

By Xueyao Wan, Hang Yu

llms rag multimodal benchmarks safety

arXiv AI

Jul 21

OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment

arXiv:2607. 17657v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) still struggle with spatial reasoning that requires perspective transformation.

By Wenxiao Fan, Hang Yin, Kan Li

llms multimodal safety

arXiv AI

Jul 21

DeLIVeR: Decomposed Learning for Information-grounded Veracity Recognition via Reinforced Knowledge Graph Exploration

arXiv:2607. 17935v1 Announce Type: cross Abstract: Automated fact-checking remains a challenge for Large Language Models (LLMs) due to "query brittleness" in traditional retrieval systems.

By Cong Hoan Nguyen, Thomas Hoang, Hieu Minh Duong, Long Nguyen

llms benchmarks

arXiv Machine Learning

Jul 21

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models

arXiv:2607. 17117v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose language model activations into sparse features, but standard SAEs encode each token independently and do not expose information that persists across a sequence.

By Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik

llms

arXiv Machine Learning

Jul 21

Manifold-Constrained Hyper-Connections for Parameter-Efficient Finetuning

arXiv:2607. 18130v1 Announce Type: new Abstract: Most parameter-efficient finetuning (PEFT) methods adapt weights or activations, thus leaving one of the key Transformer components unchanged: residual connections.

By Valentijn Oldenburg, Floris de Kam, Bente Zuijdam, Lieve Eberson, Nicky van Zutphen, Stef de Wildt, Ivo Verhoeven

llms fine-tuning benchmarks

arXiv Machine Learning

Jul 21

A Weisfeiler-Leman Characterization of Global-Attention Graph Transformers for Mixed-Integer Linear Programs

arXiv:2607. 17570v1 Announce Type: new Abstract: Graph foundation models (GFMs) with global attention are increasingly used to represent mixed-integer linear programs (MILPs), aiming to capture structure beyond the locality of standard graph neural networks.

By Md Abrar Jahin, Craig A. Knoblock, Jay Pujara

llms rag

arXiv AI

Jul 21

Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

arXiv:2607. 18100v1 Announce Type: new Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable.

By Sheldon Yu, Tong Yu, Xunyi Jiang, Rohan Surana, Gagan Mundada, Sungchul Kim, Lina Yao, Julian McAuley, Junda Wu

llms

arXiv AI

Jul 21

RealDESED: A Real-World Domestic Sound Event Detection Benchmark

arXiv:2607. 16736v1 Announce Type: cross Abstract: This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes.

By Florian Schmid, Paul Primus, Alexander Fichtinger, Tara Jadidi, Tobias Morocutti, Gerhard Widmer

llms benchmarks

arXiv Machine Learning

Jul 21

Explaining and Tuning Transformer-based LLMs in Arithmetic Tasks with Human Strategies

arXiv:2607. 17166v1 Announce Type: new Abstract: Transformer-based large language models (LLMs) continue to achieve state-of-the-art performance across various natural language processing tasks.

By Luyu Qiu, Jianing Li, Hwanhee Kim, Xiaoyong Wei, Yueyuan Zheng, Janet Hsiao, Lei Chen

llms nlp benchmarks safety

arXiv AI

Jul 21

SGA: Plug&Play Geometric Verification for Educational Video Synthesis

arXiv:2607. 18116v1 Announce Type: new Abstract: Recent work leverages Large Language Models (LLMs) to generate executable code for pedagogical animations using libraries such as Manim.

By Lopez Jhon, Hinojosa Carlos, Ghanem Bernard

llms agents benchmarks

arXiv AI

Jul 21

AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows

arXiv:2607. 16345v1 Announce Type: cross Abstract: Modern agentic systems increasingly rely on skills: installable packages of natural language and code that teach an LLM agent to perform a domain task.

By Tejas Singh Anand, Yuet Ying Christina Wang, Wanting Jiang, Steve Masson, Tian Zheng, Bingjie Zhou

llms agents safety

arXiv AI

Jul 21

"Not in My Backyard": LLMs Uncover Online and Offline Social Biases Against Homelessness

arXiv:2508. 13187v4 Announce Type: replace-cross Abstract: Homelessness is a persistent social challenge, impacting millions worldwide.

By Jonathan A. Karr Jr., Benjamin F. Herbst, Matthew L. Sisk, Xueyun Li, Ting Hua, Matthew Hauenstein, Georgina Curto, Nitesh V. Chawla

llms benchmarks safety

arXiv AI

Jul 21

LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models

arXiv:2607. 16305v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding.

By Zeyu Xu, Xingzhong Hou, Pengkai Guo, Siling Lin, Xiao Xu, Menghua Zhai, Haoyu Chen, Yunke Zhang, Fei Huang

llms rag multimodal benchmarks

arXiv Machine Learning

Jul 21

The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric

arXiv:2607. 18237v1 Announce Type: cross Abstract: Human visual similarity judgments are context-dependent.

By Sheng-Yu Wang, Yotam Nitzan, Aaron Hertzmann, Jun-Yan Zhu, Eli Shechtman, Alexei A. Efros, Richard Zhang

llms fine-tuning multimodal benchmarks

arXiv AI

Jul 21

Environment-free Synthetic Data Generation for API-Calling Agents

arXiv:2607. 16900v1 Announce Type: new Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories.

By Seanie Lee, Sanjoy Chowdhury, Chao Jiang, Cheng-Yu Hsieh, Ting-Yao Hu, Alexander T Toshev, Oncel Tuzel, Raviteja Vemulapalli

llms agents fine-tuning benchmarks

arXiv Machine Learning

Jul 21

Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression?

arXiv:2607. 17425v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) compress model activations into sparse codes, but equal reconstruction error and sparsity can preserve different linearly decodable signals.

By Aniket Deshpande

llms efficiency benchmarks

arXiv AI

Jul 21

Rooted Absorbed Prefix Trajectory Balance with Submodular Replay for GFlowNet Training

arXiv:2603. 00454v3 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) enable fine-tuning large language models to approximate reward-proportional posteriors, but they remain prone to mode collapse, manifesting as prefix collapse and length bias.

By Xi Wang, Wenbo Lu, Shengjie Wang

llms fine-tuning safety

Hugging Face Trending Papers

Jul 21

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding.

llms rag agents benchmarks safety

Hugging Face Trending Papers

Jul 21

Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents

LLM-based browser agents are rapidly changing the threat landscape for web security. Unlike traditional automation frameworks that execute predefined scripts, these agents can autonomously navigate websites, reason about page content, and interact with web interfaces using natural-language instructions.

llms agents

Hugging Face Trending Papers

Jul 21

Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs

Safety interventions on dual-use knowledge typically choose between destroying hazardous content (e. g.

llms fine-tuning benchmarks safety

Get the daily briefing