Large language models

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

25,303 stories · RSS feed

arXiv AI

Jul 1

TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models

arXiv:2606. 31976v1 Announce Type: new Abstract: Human-labeled data are widely used as reference annotations in ML, despite known variability across annotators in many expert-driven domains.

By Shiyi Chen, Nicholas Saban, Collin Hargreaves, Huiqi Wang

llms agents multimodal safety

arXiv AI

Jul 1

Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models

arXiv:2606. 31614v1 Announce Type: cross Abstract: Engineering specifications such as interlocks, alarm rationalization tables, and cause-and-effect (C&E) matrices remain central to process control and safety, yet their creation is still predominantly manual, document-driven, and prone to inconsistency.

By Javal Vyas, Milapji Singh Gill, Mehmet Mercang\"oz

llms safety

arXiv AI

Jul 1

HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents

arXiv:2606. 31179v1 Announce Type: new Abstract: As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous and holistic evaluation is essential for measuring progress toward real-world healthcare applications.

By Qianchu Liu, Sheng Zhang, Guanghui Qin, Jeya Maria Jose Valanarasu, Maximilian Rokuss, Mingyu Lu, Timothy Ossowski, Juan Manuel Zambrano Chaves, Cliff Wong, Peniel Argaw, Yashna Hasija, Mu Wei, Wen-wai Yim, Qin Liu, Zilin Jing, Jason Entenmann, Naoto Usuyama, Tristan Naumann, Hoifung Poon

llms agents benchmarks

arXiv AI

Jul 1

Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health Support

arXiv:2606. 30887v1 Announce Type: cross Abstract: Large language models show promise for mental health support, yet therapeutic quality improves only when evaluation functions as an actionable control signal rather than a passive metric.

By Mizanur Rahman, Abeer Badawi, Elahe Rahimi, Laleh Seyyed-Kalantari, Frank Rudzicz, Enamul Hoque, Elham Dolatabadi

llms agents nlp safety

arXiv AI

Jul 1

TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scenarios

arXiv:2603. 29759v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment.

By Qiucheng Yu, Ruijie Xu, Mingang Chen Jianfeng Dong, Xin Tan

llms multimodal benchmarks safety

arXiv AI

Jul 1

Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions

arXiv:2606. 30790v1 Announce Type: cross Abstract: Romanized Code Mixing (RCM), where bilingual speakers fluidly blend local languages with English in Roman script, has emerged as the dominant form of communication across multilingual communities.

By Avisha Das, Mihir Parmar, Mohana Ramnath, Pulkit Verma

llms benchmarks safety

arXiv AI

Jul 1

Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?

arXiv:2606. 31213v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed as moral advisors and agents, they need to address dilemmas between two competing values.

By Jongchan Choi, Nari Yang, Sung Soo Park, Jaemin Cho, Han Seoyoung, Haerin Shin, Jun-Hyung Park

llms agents

arXiv AI

Jul 1

DDIAgents: Mechanism-Conditioned Context Flow for Drug-Drug Interaction Prediction

arXiv:2606. 31085v1 Announce Type: new Abstract: Drug-drug interaction (DDI) prediction is essential for medication safety, yet it requires reasoning over heterogeneous biomedical evidence whose relevance changes across interaction mechanisms.

By Zhenqian Shen, Yu Liu, Xiaoyi Fu, Quanming Yao

llms agents benchmarks safety

arXiv AI

Jul 1

Learning by Surprise: Adaptive Mitigation of Model Collapse in Large Language Models

arXiv:2410. 12341v4 Announce Type: replace-cross Abstract: As AI-generated content increasingly populates the web, generative AI models are at growing risk of being trained on their own outputs, a process known as AI autophagy.

By Daniele Gambetta, Gizem Gezici, Fosca Giannotti, Dino Pedreschi, Alistair Knott, Luca Pappalardo

llms fine-tuning

arXiv Machine Learning

Jul 1

Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors

arXiv:2606. 31845v1 Announce Type: cross Abstract: A transformer's feed-forward (FFN) sublayer materializes the distinctions attention gathers, yet gives no account of what it computes.

By Mark Oskin

llms

arXiv AI

Jul 1

Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection Defense

arXiv:2606. 30783v1 Announce Type: cross Abstract: We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by suppressing untrusted text, which corrupts tasks that must preserve it, such as translation and document editing.

By Mitchell Hermon, Rahul Gupta, Weitong Ruan, Ekraam Sabir, Haohan Wang

llms benchmarks

arXiv AI

Jul 1

Adaptive Cluster-First Route-Second Decomposition for Industrial-Scale Vehicle Routing

arXiv:2606. 31820v1 Announce Type: new Abstract: Large-scale capacitated vehicle routing problems (CVRPs) are commonly addressed using cluster-first route-second (CFRS) approaches that split a routing instance into smaller, computationally tractable subproblems.

By Oguzhan Karaahmetoglu (Carnegie Mellon University), Hyong Kim (Carnegie Mellon University)

llms benchmarks

arXiv AI

Jul 1

Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning

arXiv:2606. 31825v1 Announce Type: cross Abstract: Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on final answer correctness or sequence-level preferences.

By Junha Jung, Minbyul Jeong, Suhyeon Lim, Sungwook Jung, Jaehoon Yun, Taeyun Roh, Mujeen Sung, Jaewoo Kang

llms nlp reinforcement-learning multimodal benchmarks

arXiv AI

Jul 1

CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs

arXiv:2606. 31309v1 Announce Type: cross Abstract: While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.

By Zhengxing Li, David J. Miller, Guangmingmei Yang, George Kesidis

llms rag

arXiv AI

Jul 1

Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG

arXiv:2606. 30989v1 Announce Type: cross Abstract: Warning: This paper contains several toxic and offensive statements.

By Naihao Deng, Yilun Zhu, Joan Nwatu, Clayton Scott, Rada Mihalcea

llms benchmarks safety

arXiv AI

Jul 1

How Human Feedback Shapes AI-generated Community Notes

arXiv:2606. 30905v1 Announce Type: cross Abstract: Community Notes, a bridging-based crowd-sourced fact-checking system, has emerged as a new mechanism for moderating misleading information on social media and has been adopted by major platforms including X, Facebook, Instagram, Threads, and TikTok.

By Soham De, Isaac Slaughter, Jiawei Guo, Qiao-Yun Cheng, Jiayuan Yan, Sruti Banerjee, Martin Saveski

llms

arXiv AI

Jul 1

From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators

arXiv:2606. 30704v1 Announce Type: cross Abstract: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment.

By Gan Luo, Zihan Qin, Bin Dong, Wotao Yin

llms nlp reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 1

Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning

arXiv:2606. 30686v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) systems, built on pretrained vision-language models (VLMs), have shown rapidly improving performance on robot manipulation benchmarks.

By Taozhao Chen, Ian Manchester, Huaming Chen

llms robotics multimodal benchmarks

arXiv AI

Jul 1

ELEVATE: Designing Human-Centered GenAI Virtual Tutors for Scalable and Inclusive Education

arXiv:2606. 30662v1 Announce Type: cross Abstract: The advent of Generative Artificial Intelligence (GenAI), and in particular Large Language Models (LLMs), is reshaping educational practice, while intensifying ethical debate about its adoption.

By Lorenzo Stacchio, Michele Giordano, Daniele Berardini, Primo Zingaretti, Emanuele Frontoni

llms robotics multimodal safety

arXiv AI

Jul 1

The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes

arXiv:2606. 30653v1 Announce Type: cross Abstract: Large language models are increasingly deployed in agentic pipelines that depend on the model evaluating its own outputs without external verification.

By Marina Mancoridis, Zo\"e Hitzig

llms agents

Get the daily briefing