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

Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning

arXiv:2607. 19181v1 Announce Type: cross Abstract: Neural machine translation (NMT) in the legal domain is a linguistically and conceptually demanding task, primarily due to the complexity of legal language and the high level of precision it requires.

By Aixiu An, Michael Jungo, Eloi Eynard, Mark Drenhaus, Andreas Fischer, Jean Hennebert, S\'ebastien Rumley

llms nlp reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 22

Fence: Specialized SLM Guardrails for LLM Applications

arXiv:2607. 18268v1 Announce Type: new Abstract: Real-world applications that use closed-source large language models (LLMs) need advanced safety measures that go beyond the basic content filters.

By Kumud Lakara, Ruibo Shi, Fran Silavong

llms diffusion safety

arXiv AI

Jul 22

SR-Agent: An Experience-Driven Agentic Framework for Post-Ranking Strategy Refinement in E-Commerce Recommendation

arXiv:2607. 17719v2 Announce Type: replace Abstract: User experience is a first-class objective in industrial e-commerce recommender systems (RS).

By Hanchen Yang, Kaiwen Yang, Junpeng Zhuang, Yang He, Keting Cen, Bochao Liu, Zhongbo Sun, An Liu, Zhongteng Han, Chenyi Lei

llms agents

arXiv AI

Jul 22

BioSecBench-Surveillance: A Verifiable Benchmark for AI Agents in Pathogen Genomic Surveillance

arXiv:2607. 19262v1 Announce Type: new Abstract: As pathogen genomic surveillance scales, the bottleneck is shifting from data generation to analysis.

By Harmon Bhasin, Kevin Flyangolts, Dianzhuo Wang, Evan Seeyave, Arjun Banerjee, Amanda Darling, Joshua Stallings, David Stern, Shawn Higdon, Claire Duvallet, Bryan Tegomoh, Kenny Workman

llms agents benchmarks

arXiv AI

Jul 22

SkillSight: Seeing Through Shared Descriptions for Accurate Skill Retrieval

arXiv:2607. 18785v1 Announce Type: new Abstract: As large language model agents gain access to increasingly large skill libraries, retrieving the right skill becomes critical to reliable capability selection and execution.

By Jinying Xiao, Bin Ji, Shasha Li, Xiaodong Liu, Ma Jun, Jiacheng Jie, Chao Wang, Nyima Tashi, Jie Yu

llms agents safety

arXiv Machine Learning

Jul 22

Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentation

arXiv:2512. 08216v4 Announce Type: replace-cross Abstract: Accurate segmentation of lung tumors from 3D computed tomography (CT) scans is essential for automated treatment planning and response assessment.

By Aneesh Rangnekar, Harini Veeraraghavan

llms computer-vision benchmarks safety

arXiv AI

Jul 22

Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression

arXiv:2607. 18284v1 Announce Type: cross Abstract: To excel at their domain large language models are comprised of billions of parameters.

By Athanasios Ntovas, Alexandros Doumanoglou, Petros Drakoulis, Dimitris Zarpalas

llms efficiency benchmarks

arXiv AI

Jul 22

Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training

arXiv:2607. 19058v1 Announce Type: cross Abstract: Optimizer state is the largest single line item in the memory budget of mixture-of-experts (MoE) training: on a 6.

By Nuemaan Malik

llms benchmarks

arXiv Machine Learning

Jul 22

Elicitation without Backpropagation: Steering Model Behavior by Optimizing the Latent Posterior

arXiv:2607. 18804v1 Announce Type: new Abstract: In the \emph{latent posterior model} of transformer behavior, the next-token distribution arises from a posterior over latent predictive models conditioned on the context, mixed to generate continuations.

By Garrett Baker, Vinayak Pathak, Daniel Murfet, Susan Wei

llms

arXiv AI

Jul 22

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

arXiv:2607. 18659v1 Announce Type: cross Abstract: LLM-based browser agents are rapidly changing the threat landscape for web security.

By Behzad Ousat, Nikita Turkmen, Lalchandra Rampersaud, Dillan Bailey, Amin Kharraz

llms agents

arXiv AI

Jul 22

Binding Drift in Multi-Step Tool-Augmented Agents

arXiv:2607. 18316v1 Announce Type: cross Abstract: Tool-augmented language-model agents execute multi-step workflows over external systems, resolving an entity once and then acting on it across subsequent steps.

By Rahul Suresh Babu, Shashank Indukuri

llms agents

arXiv AI

Jul 22

Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in GUI Agents

arXiv:2506. 17913v2 Announce Type: replace Abstract: Graphical User Interface (GUI) agents have made significant progress in automating digital tasks through the utilization of computer vision and language models.

By Jinjie Wei, Jiyao Liu, Lihao Liu, Ming Hu, Junzhi Ning, Mingcheng Li, Weijie Yin, Junjun He, Xiao Liang, Chao Feng, Dingkang Yang

llms agents computer-vision benchmarks

arXiv AI

Jul 22

Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models

arXiv:2607. 18695v1 Announce Type: cross Abstract: A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors.

By Gautam Rajendrakumar Gare, Jia Shi, Zhiqiu Lin, Deepak Pathak, John Galeotti, Deva Ramanan

llms rag multimodal

arXiv AI

Jul 22

Sequential Learner Modeling Using Multi-Relational Graph Convolutional Networks

arXiv:2607. 19253v1 Announce Type: new Abstract: User modeling is a critical task in a variety of personalized systems.

By Rawaa Alatrash, Mohamed Amine Chatti, Hong Yang, Yumeng Wang

llms rag

arXiv AI

Jul 22

Context-Masked Truncated Reasoning Audits for Answer-Key Dependence in LLM Tutors

arXiv:2607. 04572v2 Announce Type: replace Abstract: Large language model (LLM) tutors may have access to teacher notes, answer keys, rubrics, or retrieved solutions while producing student-facing explanations.

By Bonan Shen, Dingyan Shang, Youting Wang, Tao Ning, Bowen Liu

llms

arXiv AI

Jul 22

Phionyx: A Deterministic AI Runtime Architecture with Structured State Management and Pre-Response Governance

arXiv:2607. 18246v1 Announce Type: new Abstract: We present Phionyx, a deterministic AI runtime architecture derived from the broader Echoism interaction framework that introduces a governance-first approach to AI engineering: treating large language model (LLM) outputs as noisy sensor measurements rather than direct decisions.

By Ali Toygar Abak

llms agents benchmarks safety

arXiv AI

Jul 22

Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information

arXiv:2607. 19313v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models.

By Priyank Agrawal, Ankur Samanta, Shervin Ghasemlou, Jalaj Bhandari, Kavosh Asadi, Daniel Jiang, Aditya Modi

llms reinforcement-learning benchmarks

arXiv AI

Jul 22

Calibrated Selective Fact-Checking via Evidence Chain Evaluation

arXiv:2607. 18240v1 Announce Type: new Abstract: Large language models (LLMs) can achieve strong fact-checking accuracy, yet forced binary decisions conceal a critical reliability problem: systems may issue confident verdicts even when supporting evidence is weak, sparse, or internally inconsistent.

By Dekun Yang

llms agents safety

arXiv AI

Jul 22

From Dependency to Compositionality: A Neurosymbolic Lifting of LLM Outputs via Combinatory Categorial Grammar

arXiv:2607. 18961v1 Announce Type: new Abstract: Large language models (LLMs) generate fluent text by incrementally predicting the next token from a prefix.

By Remo Pareschi

llms data-engineering

arXiv Machine Learning

Jul 22

On the Limits of Support-Preserving Alignment and Bounded Filtering

arXiv:2607. 18295v1 Announce Type: new Abstract: We study whether alignment schemes that reshape a base model's output distribution, combined with bounded safety filters, can drive the probability of harmful behavior to zero in modern large language models.

By Aryan Dutt, Rui Mao, Anupam Chattopadhyay

llms benchmarks safety

Get the daily briefing