Large language models

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

31,067 stories · RSS feed

arXiv Machine Learning

Jun 8

A Dynamic Self-Evolving Extraction System

arXiv:2603. 06915v2 Announce Type: replace-cross Abstract: The extraction of structured information from raw text is a fundamental component of many NLP applications, including document retrieval, ranking, and relevance estimation.

By Moin Amin-Naseri, Hannah Kim, Estevam Hruschka

llms rag nlp fine-tuning

arXiv AI

Jun 8

Human Adults and LLMs as Scientists: Who Benefits from Active Exploration?

arXiv:2606. 06464v1 Announce Type: cross Abstract: A long-standing finding in the causal learning literature is that adults struggle to identify conjunctive causal rules, where an effect requires the simultaneous presence of multiple causes, while performing better in disjunctive settings.

By Mandana Samiei, Eunice Yiu, Anthony GX-Chen, Dongyan Lin, Jocelyn Shen, Blake A. Richards, Alison Gopnik, Doina Precup

llms benchmarks safety

arXiv AI

Jun 8

TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents

arXiv:2606. 07054v1 Announce Type: cross Abstract: Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring.

By Vijitha Mittapalli, Shreyaa Jayant Dani, Satya Srujana Pilli, Snigdha Ansu, Mohammadreza Teymoorianfard, Franck Dernoncourt, Hongjie Chen, Yu Wang, Ryan A. Rossi, Nesreen K. Ahmed

llms agents benchmarks

arXiv AI

Jun 8

Auditing Training Data in Domain-adapted LLMs: LoRA-MINT

arXiv:2606. 06946v1 Announce Type: cross Abstract: We present LoRA-MINT, a new methodology for Membership Inference Test (MINT) applied to recent Large Language Models (LLMs) fine-tuned for specific Natural Language Processing (NLP) tasks through Low-Rank Adaptation (LoRA).

By Gonzalo Mancera, Daniel DeAlcala, Aythami Morales, Julian Fierrez, Ruben Tolosana, Francisco Jurado

llms nlp fine-tuning benchmarks

arXiv AI

Jun 8

Attention Consistent Longitudinal Medical Visual Question Answering Guided by Vision Foundation Models

arXiv:2606. 06534v1 Announce Type: cross Abstract: Longitudinal medical visual question answering (VQA) requires reasoning about anatomical differences between an image of a current time point and an image of a referred time point.

By Jialin Wu, Qianru Zhang, Georges El Fakhri, Xiaofeng Liu

llms nlp multimodal benchmarks safety

arXiv Machine Learning

Jun 8

Trace Reconstruction with Language Models

arXiv:2507. 12927v2 Announce Type: replace Abstract: The general trace reconstruction problem seeks to recover an original sequence from its noisy copies independently corrupted by insertions, deletions, and substitutions.

By Franziska Weindel, Michael Girsch, Reinhard Heckel

llms fine-tuning benchmarks

arXiv AI

Jun 8

Online Pandora's Box for Contextual LLM Cascading

arXiv:2606. 07392v1 Announce Type: new Abstract: Motivated by Large Language Model (LLM) cascading, we propose an online contextual Pandora's Box model for adaptively querying and selecting LLM APIs.

By Alexandre Belloni, Yan Chen, Yehua Wei

llms

arXiv AI

Jun 8

PandaAI: A Practical Agent CQ2 for Neuro-symbolic Data Analysis And Integrated Decision-Making in Quantitative Finance

arXiv:2606. 06823v1 Announce Type: cross Abstract: While deep learning has excelled in various domains, its application to sequential decision-making in finance remains challenging due to the low Signal-to-Noise Ratio (SNR) and non-stationarity of financial data.

By Yuqi Li, Siyuan Liu, Bingjun Liu

llms agents fine-tuning benchmarks safety

arXiv AI

Jun 8

Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces

arXiv:2606. 06941v1 Announce Type: new Abstract: Large language models (LLMs) now solve a wide range of expert-level exams at or above human level, yet remain brittle on specialised, evidence-intensive domains such as law.

By Laura Wynter, Nirvik Sahoo, Paul Griffin

llms benchmarks

arXiv AI

Jun 8

Declarative Skills for AI Agents in Knowledge-Grounded Tool-Use Workflows

arXiv:2606. 06923v1 Announce Type: new Abstract: We study orchestration mechanisms for tool-using AI agents in realistic customer-service workflows over an unstructured knowledge base.

By M. Danish Lim, I. Danial Bin Sharudin, Wen Han Chen, Cedric Lim, Laura Wynter

llms rag agents reinforcement-learning benchmarks

arXiv AI

Jun 8

Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation

arXiv:2606. 06712v1 Announce Type: cross Abstract: We study the transformation of autoregressive models (ARLMs) into diffusion language models (DLMs).

By Xingyu Su, Jacob Helwig, Shubham Parashar, Atharv Chagi, Lakshmi Jotsna, Degui Zhi, James Caverlee, Dileep Kalathil, Shuiwang Ji

llms diffusion efficiency

arXiv Machine Learning

Jun 8

Sparsely gated tiny linear experts

arXiv:2606. 07414v1 Announce Type: new Abstract: Sparsity allows scaling model parameters without proportionally increasing computational cost.

By Simon Schug

llms efficiency safety

arXiv Machine Learning

Jun 8

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

arXiv:2606. 07006v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert trajectory as the target behavior.

By Yongliang Miao, Fengyuan Liu, Wei Shi, Yanguang Liu, Fei Sun, Na Zou, Mengnan Du

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 8

E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory

arXiv:2601. 16622v2 Announce Type: replace-cross Abstract: Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems.

By Lin Huang, Chengxiang Huang, Ziang Wang, Yiyue Du, Chu Wang, Haocheng Lu, Yunyang Li, Xiaoli Liu, Arthur Jiang, Jia Zhang

llms efficiency

arXiv AI

Jun 8

Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills

arXiv:2606. 07412v1 Announce Type: cross Abstract: LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks.

By Chuan Xiao, Zhengbo Jiao, Shaobo Wang, Wei Wang, Bing Zhao, Hu Wei, Linfeng Zhang, Lin Qu

llms agents safety

arXiv Machine Learning

Jun 8

Agentic World Modeling for 6G: Near-Real-Time Generative State-Space Reasoning

arXiv:2511. 02748v2 Announce Type: replace-cross Abstract: We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capacity to imagine and choose -- to simulate future scenarios, weigh trade-offs, and act with calibrated uncertainty.

By Farhad Rezazadeh, Amir Ashtari Gargari, Hatim Chergui, Sandra Lagen, Merouane Debbah, Houbing Song, Lingjia Liu

llms agents

arXiv AI

Jun 8

Training for Technology: Adoption and Productive Use of Generative AI in Legal Analysis

arXiv:2603. 04982v3 Announce Type: replace-cross Abstract: Can targeted user training unlock the productive potential of generative artificial intelligence in professional settings?

By Benjamin M. Chen, Hong Bao

llms

arXiv Machine Learning

Jun 8

Predictable Compression Failures: Order Sensitivity and Information Budgeting for Evidence-Grounded Binary Adjudication

arXiv:2509. 11208v3 Announce Type: replace-cross Abstract: Transformers used for evidence-grounded binary adjudication (e.

By Leon Chlon, Ahmed Karim, Maggie Chlon, MarcAntonio Awada

llms safety

arXiv Machine Learning

Jun 8

Skip a Layer or Loop It? Learning Program-of-Layers in LLMs

arXiv:2606. 06574v1 Announce Type: new Abstract: Large language models (LLMs) perform inference by following a fixed depth and order, non-recurrent execution of all layers.

By Ziyue Li, Yang Li, Tianyi Zhou

llms benchmarks

arXiv AI

Jun 8

MCERF: Advancing Multimodal LLM Evaluation of Engineering Documentation with Enhanced Retrieval

arXiv:2604. 09552v2 Announce Type: replace-cross Abstract: Engineering rulebooks and technical standards contain multimodal information like dense text, tables, and illustrations that are challenging for retrieval augmented generation (RAG) systems.

By Kiarash Naghavi Khanghah, Hoang Anh Nguyen, Anna C. Doris, Amir Mohammad Vahedi, Daniele Grandi, Faez Ahmed, Hongyi Xu

llms rag agents nlp multimodal benchmarks

Get the daily briefing