Large language models

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

19,764 stories · RSS feed

arXiv AI

Jul 22

Bounding Boxes to Improve Small Language Model Performance on Vision-Based Grading Tasks

arXiv:2607. 18767v1 Announce Type: cross Abstract: The deployment of Small Language Models (SLMs) in educational settings offers significant advantages in terms of privacy, cost, and scalability.

By Lachlan McGinness

llms safety

arXiv AI

Jul 22

Saving the legacy of Hero Ibash: Evaluating Four Language Models for Aminoacian

arXiv:2402. 18121v2 Announce Type: replace-cross Abstract: This study assesses four cutting-edge language models in the underexplored Aminoacian language.

By Yunze Xiao, Yiyang Pan

llms nlp benchmarks

arXiv AI

Jul 22

AutoJourn: Multi-Perspective Summarisation, Bias Detection and Bias Neutralisation for LLM-Generated News in Automated Journalism

arXiv:2607. 18983v1 Announce Type: cross Abstract: We present AutoJourn, a demonstration system for multi-perspective news generation and bias-aware evaluation using large language models (LLMs).

By Himel Ghosh, Ahmed Mosharafa, Georg Groh

llms safety

arXiv AI

Jul 22

Enhancing Transformer-based Routing by Encoding Distance via Relative Positional Encoding

arXiv:2607. 18909v1 Announce Type: new Abstract: This paper explores Relative Positional Encoding (RPE) as an additive bias in Transformer architectures to solve the Team Orienteering Problem.

By Leyre Enc\'io, Daniel Fuertes, Carlos R. del-Blanco, Fernando Jaureguizar

llms rag benchmarks safety

arXiv AI

Jul 22

OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillation

arXiv:2607. 18850v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have recently shown strong potential for industrial anomaly detection (IAD) by providing image-level anomaly judgments and interpretable defect reasoning.

By Shuimu Chen, Jing Jin, Nan Su, Hongbo Xu, Zebang Cheng, Wenming Yang, Fei Ma, Guijin Wang

llms efficiency multimodal

arXiv AI

Jul 22

HALLMARK: Diagnosing Three Failure Modes in LLM Citation Verifiers

arXiv:2607. 18360v1 Announce Type: cross Abstract: Large language models (LLMs) now routinely draft literature reviews and assist with academic writing, which means a higher risk of fabricated references: GPTZero found 53 papers with hallucinated citations among NeurIPS 2025's accepted set.

By Patrik Reizinger, Wieland Brendel

llms agents benchmarks safety

arXiv AI

Jul 22

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

arXiv:2607. 18485v1 Announce Type: cross Abstract: Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows.

By Jie Li

llms agents benchmarks safety

arXiv AI

Jul 22

Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interactio

arXiv:2607. 18985v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge.

By Jialian Li, Junhong Liu, Yuchen Cao, Weiran Guo, Jiaming Song, Xutao Wang, Yi Zhao, Jiangpin Liu, Jie Chen

llms agents reinforcement-learning robotics fine-tuning benchmarks

arXiv Machine Learning

Jul 22

Estimating near-verbatim extraction risk in language models with decoding-constrained beam search

arXiv:2603. 24917v2 Announce Type: replace-cross Abstract: Recent work shows that standard greedy-decoding extraction methods for quantifying memorization in LLMs miss how extraction risk varies across sequences.

By A. Feder Cooper, Mark A. Lemley, Christopher De Sa, Lea Duesterwald, Allison Casasola, Jamie Hayes, Katherine Lee, Daniel E. Ho, Percy Liang

llms safety

arXiv AI

Jul 22

Evaluating medical AI under missing information: same-provider judges and human raters change apparent safety

arXiv:2607. 18828v1 Announce Type: new Abstract: Readiness stress-testing of medical AI has focused on closed-ended and multimodal benchmarks.

By Koyar Afrasyab

llms multimodal benchmarks safety

arXiv AI

Jul 22

M-RAG: Semantic Key-Value Indexing for Retrieval-Augmented Generation

arXiv:2603. 26667v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) turns external documents into evidence for large language models.

By Xu Sun, Tongkai Xu, Baiheng Xie, Li Huang, Qiang Gao, Kunpeng Zhang

llms rag

arXiv AI

Jul 22

Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary

arXiv:2607. 18553v1 Announce Type: cross Abstract: Can a language model read the quality of ongoing computation, and can an external intervention turn that readout into better outcomes?

By Jan Kirin

llms fine-tuning

arXiv Machine Learning

Jul 22

Pain in 3D: Generating Controllable Synthetic Faces for Automated Pain Assessment

arXiv:2509. 16727v5 Announce Type: replace-cross Abstract: Automated pain assessment from facial expressions is crucial for non-communicative patient.

By Xin Lei Lin, Soroush Mehraban, Abhishek Moturu, Babak Taati

llms diffusion computer-vision

arXiv AI

Jul 22

Now You See the Hate: Adaptive View Retrieval for Hidden Hateful Illusions

arXiv:2607. 19061v1 Announce Type: cross Abstract: Hateful optical illusions expose a serious gap in current multimodal safety systems.

By Qianpu Chen, Derya Soydaner

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jul 22

LatentMT: Machine Translation with Latent Reasoning

arXiv:2607. 18618v1 Announce Type: cross Abstract: Latent-reasoning looped language models (LoopLMs) offer a different scaling path for machine translation (MT): instead of increasing parameter count or emitting explicit chain-of-thought tokens, they spend additional recurrent computation inside hidden states.

By Wei-Rui Chen, Samar M. Magdy, Chiyu Zhang, Wenhui Zhu, Zhipeng Wang, Muhammad Abdul-Mageed

llms nlp benchmarks

arXiv AI

Jul 22

A Controlled Study of Attention-Only Transformers

arXiv:2607. 18363v1 Announce Type: cross Abstract: Feed-forward networks hold two thirds of a transformer's non-embedding parameters, yet the architecture has not received a necessity test that controls parameters, compute, and depth at once.

By Henry Ndubuaku, Karen Mosoyan, Jakub Mroz, Noah Cylich, Satyajit Kumar, Parkirat Sandhu, Roman Shemet, Justin H Lee

llms rag

arXiv AI

Jul 22

Dr. Zero: Self-Evolving Search Agents without Training Data

arXiv:2601. 07055v2 Announce Type: replace Abstract: As high-quality data becomes increasingly difficult to obtain, self-evolution without curated training data has emerged as a promising paradigm.

By Zhenrui Yue, Kartikeya Upasani, Xianjun Yang, Suyu Ge, Shaoliang Nie, Yuning Mao, Zhe Liu, Dong Wang

llms agents nlp benchmarks

arXiv AI

Jul 22

Global Automation Atlas

arXiv:2605. 17086v2 Announce Type: replace-cross Abstract: Automation can displace or complement labour, but this need not be constant across economies.

By Prashant Garg, Tommaso Crosta, Jasmin Baier

llms

arXiv Machine Learning

Jul 22

One Student, Many Teachers: Multi-Task On-Policy Distillation via Soft-Prompt Privileged Context

arXiv:2607. 18293v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) teaches large language models new skills through a teacher that shares the student's backbone and supervises its own rollouts.

By Yingzi Ma, Zichen Zhu, Ming Jiang, Chaowei Xiao

llms agents fine-tuning efficiency benchmarks

arXiv Machine Learning

Jul 22

Benchmarking Deep Learning Approaches for AEC Engineering Drawing Layout Detection and Information Extraction

arXiv:2607. 18997v1 Announce Type: cross Abstract: Information Extraction (IE) from Architecture, Engineering, and Construction (AEC) drawings remains hindered by manual inefficiency, while Layout Detection, a vital 'middleware' organizing graphical and textual hierarchies, is underexplored.

By Tianyang Huang, Alessio Lombardi, Ahmed Elnagar, Ahmed Zalouk, George Paul, Sepehr Najjarpour, Arvid Sigurdsson, Khalid Ismail, Mohamed Ragab, Edlira Vakaj

llms multimodal benchmarks

Get the daily briefing