Large language models

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

22,911 stories · RSS feed

arXiv Machine Learning

Jul 15

Extractable Memorization From First Principles

arXiv:2607. 12649v1 Announce Type: new Abstract: Recent work on extractable memorization in LLMs suffers from two contrasting validity problems.

By A. Feder Cooper, Marika Swanberg, Jamie Hayes, Lea Duesterwald, Christopher De Sa, Daniel E. Ho, Mark A. Lemley, Percy Liang

llms

arXiv Machine Learning

Jul 15

Language Identification with Succinct Machine-Independent Traces

arXiv:2607. 12443v1 Announce Type: cross Abstract: Motivated by the power of large language models, there has been renewed interest in the Gold-Angluin model of language identification in the limit, with an eye toward variants of the model that might overcome the negative results for its original formulation.

By Moses Charikar, Jon Kleinberg, Chirag Pabbaraju

llms

arXiv AI

Jul 15

Sparse Inter-Layer Dependencies of Transformer FFN Neurons

arXiv:2607. 11990v1 Announce Type: cross Abstract: Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in Transformer architectures, yet their internal structure remains difficult to interpret due to the additive superposition induced by the residual stream.

By Johannes Knittel, Hanspeter Pfister

llms efficiency safety

arXiv AI

Jul 15

RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers

arXiv:2606. 20101v3 Announce Type: replace-cross Abstract: Audio editing aims to modify specific content in an existing audio clip according to a text instruction or description while preserving the remaining acoustic content.

By Liting Gao, Yonggang Zhu, Yaru Chen, Dongyu Wang, Shubin Zhang, Zhenbo Li, Jean-Yves Guillemaut, Wenwu Wang

llms diffusion multimodal safety

arXiv AI

Jul 15

CrochetBench: Can Vision-Language Models Move from Describing to Doing in Crochet Domain?

arXiv:2511. 09483v3 Announce Type: replace Abstract: While multimodal large language models can describe visual content, their ability to generate executable procedures remains underexplored.

By Peiyu Li, Xiaobao Huang, Ting Hua, Nitesh V. Chawla

llms multimodal benchmarks

arXiv AI

Jul 15

LLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos

arXiv:2607. 12733v1 Announce Type: new Abstract: Large language models (LLMs) excel at pattern recognition and text generation, but their capacity for abductive inference - inferring latent hypotheses that explain observed behavior - remains poorly understood.

By Julius Steiglechner, Lucas Mahler, Gabriele Lohmann

llms agents

arXiv AI

Jul 15

Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model

arXiv:2607. 13013v1 Announce Type: new Abstract: Automatic speech recognition is dominated by autoregressive decoders that emit one token at a time.

By Harsha Vardhan Khurdula, Abhinav Kumar Singh, Yoeven D Khemlani, Vineet Agarwal

llms rag diffusion multimodal

arXiv AI

Jul 15

Optimization Is Not All You Need

arXiv:2607. 11977v1 Announce Type: new Abstract: In 2019, OpenAI released two million GPT-2 outputs-ungrammatical, half broken-to aid the detection of machine-generated text.

By Minh Hua, Rita Raley

llms benchmarks safety

arXiv AI

Jul 15

G-SHARE: A Guideline-Based Structured Reasoning Framework for Human-Factor Event Diagnosis

arXiv:2607. 11892v1 Announce Type: cross Abstract: Human-factor event diagnosis is essential for learning from operational events in nuclear power plants, yet its quality depends strongly on expert interpretation of narrative reports and guideline-based reasoning.

By Xingyu Xiao, Mao Du, Jiejuan Tong, Jingang Liang, Haitao Wang

llms benchmarks safety

arXiv AI

Jul 15

First, do NOHARM: a medical safety benchmark and randomized study of physician and AI teaming on clinical consultations

arXiv:2512. 01241v4 Announce Type: replace-cross Abstract: Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized.

By David Wu, Fateme Nateghi Haredasht, Saloni Kumar Maharaj, Priyank Jain, Jessica Tran, Matthew Gwiazdon, Arjun Rustagi, Jenelle Jindal, Jacob M. Koshy, Vinay Kadiyala, Anup Agarwal, Bassman Tappuni, Brianna French, Sirus Jesudasen, Christopher V. Cosgriff, Rebanta Chakraborty, Jillian Caldwell, Susan Ziolkowski, David J. Iberri, Robert Diep, Rahul S. Dalal, Kira L. Newman, Kristin Galetta, J. Carl Pallais, Nancy Wei, Kathleen M. Buchheit, David I. Hong, Vartan Pahalyants, Ernest Y. Lee, Allen Shih, Tamara B. Kaplan, Vishnu Ravi, Sarita Khemani, Thomas A. Buckley, April S. Liang, Daniel Shirvani, Advait Patil, Nicholas Marshall, Kanav Chopra, Joel Koh, Adi Badhwar, Anastasia Perez, Austin J. Schoeffler, Mahbuba Tusty, Chase M. Walton, Liam G. McCoy, David J. H. Wu, Yingjie Weng, Sumant Ranji, Kevin Schulman, Nigam H. Shah, Jason Hom, Arnold Milstein, Arjun K. Manrai, Adam Rodman, Jonathan H. Chen, Ethan Goh

llms rag agents benchmarks safety

arXiv AI

Jul 15

FAIR GraphRAG: A Retrieval-Augmented Generation Approach for Semantic Data Analysis

arXiv:2607. 11464v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) addresses the limitations of Large Language Models (LLMs) when providing responses to domain-specific questions.

By Marlena Fl\"uh, Soo-Yon Kim, Carolin Victoria Schneider, Sandra Geisler

llms rag nlp

arXiv Machine Learning

Jul 15

Fine-Tuned Multi-Agent Framework for Detecting OCEAN in Life Narratives

arXiv:2607. 12215v1 Announce Type: cross Abstract: Accurately assessing personality from text is challenging because traits are latent, context-dependent, and often subtly expressed across long narratives.

By Rasiq Hussain, Darshil Italiya, Joshua Oltmanns, Mehak Gupta

llms agents fine-tuning

arXiv AI

Jul 15

So Many Opinions, So Many LLMs: Comparing Large Language Models to Traditional Machine Learning for Open- Ended Survey Analysis

arXiv:2607. 11890v1 Announce Type: cross Abstract: Open-ended surveys offer valuable insights, but they are notoriously difficult to analyze at scale.

By Abdullah Akinde, Mariam Akinde, Rasheedat Emiola, Ahmed Akinsola

llms nlp safety

arXiv AI

Jul 15

PM-Bench: Evaluating Prospective Memory in LLM Agents

arXiv:2607. 12385v1 Announce Type: new Abstract: A significant challenge in agentic AI is prospective memory: the ability to execute an intention at a specific future cue or state while other activities are ongoing.

By Genglin Liu, Saadia Gabriel

llms agents benchmarks

arXiv AI

Jul 15

AutoTrace: From Patches to Triggers via Agentic Interprocedural Exploration

arXiv:2607. 12058v1 Announce Type: cross Abstract: Given a vulnerability-fixing commit, trigger localization asks which specific statement turns the vulnerable program state into a concrete unsafe operation.

By Arastoo Zibaeirad, Marco Vieira, Thomas Zimmermann

llms agents benchmarks

arXiv AI

Jul 15

RCWT: Measuring Task-Budget Displacement from Coordination Content in LLM Calls

arXiv:2607. 12216v1 Announce Type: cross Abstract: Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instructions, inside the same finite prompt used for the current task.

By Brenda Lelis, Rodrigo Cabral-Carvalho

llms agents benchmarks

arXiv Machine Learning

Jul 15

AdaPCLA: Adaptive Prior-Calibrated Logit Adjustment for Long-Tailed Longitudinal EHR Generation

arXiv:2607. 12645v1 Announce Type: new Abstract: Generative modeling of longitudinal Electronic Health Records is increasingly important for privacy-preserving research, yet standard autoregressive models tend to underrepresent the co-occurrence structure of tail events (i.

By Shuai Cui, Chen Wenxuan, Wenjie Du, Jian Lou, Dan Li, Wenjie Feng

llms safety

arXiv AI

Jul 15

Comparing Semantic Navigation in Humans and Large Language Models using Natural Language Processing

arXiv:2607. 12195v1 Announce Type: cross Abstract: Semantic memory retrieval can be conceptualized as navigation through conceptual space.

By Gabriel Paris-Colombo, Rodrigo M. Cabral-Carvalho, Felipe D. Toro-Hern\'andez

llms rag nlp

arXiv AI

Jul 15

Evaluating Health Misinformation in Low-Resource Languages: Integrating Small Language Models with a Culturally-Sensitive Responsible NLP Framework (Bangla as a Case Study)

arXiv:2607. 12336v1 Announce Type: cross Abstract: Artificial Intelligence (AI) technologies, while serving as a foundational enabler for modern social media and digital health services, exert a bivalent effect by simultaneously acting as a combatant against and a spread vector for misinformation.

By Farnaz Farid, Raihan Alam, Al Al-Areqi, Farhad Ahamed, Muhammad Hassan Khan, Sadia Hossain, Irena Veljanova, Anika Tabassum Binte Hossain

llms nlp fine-tuning

arXiv AI

Jul 15

IQA-T1: Tool-based Visual Evidence Reasoning for Image Quality Assessment

arXiv:2607. 12375v1 Announce Type: cross Abstract: Image Quality Assessment (IQA) in open-world environments remains challenging due to limited generalization and interpretability.

By Jinjian Wu, Jiaqi Tang, Wei Wei, Yingying Yan, Jianmin Chen, Botong Geng, Lei Zhang, Qifeng Chen

llms multimodal benchmarks safety

Get the daily briefing