Large language models

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

24,787 stories · RSS feed

arXiv Machine Learning

Jul 10

Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings

arXiv:2508. 11847v4 Announce Type: replace-cross Abstract: We propose a method for evaluating the robustness of widely used LLM ranking systems -- variants of a Bradley--Terry model -- to dropping a worst-case very small fraction of preference data.

By Jenny Y. Huang, Yunyi Shen, Dennis Wei, Tamara Broderick

llms

arXiv Machine Learning

Jul 10

Selective Left-Shift: Turning Test-Time Compute and Difficulty-based Curation into Training Data for Low-Resource Code Generation

arXiv:2607. 07748v1 Announce Type: new Abstract: Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia.

By Didula Samaraweera, Anjana Supun, Srinath Perera

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 10

RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting

arXiv:2607. 08234v1 Announce Type: cross Abstract: Real-world time series exhibit complex dynamics characterized by multiple simultaneous temporal patterns: short-term fluctuations, periodic seasonal cycles, long-term trends, and irregular abrupt changes.

By Sumit Satishrao Shevtekar, Chandresh Kumar Maurya

llms rag benchmarks safety

arXiv AI

Jul 10

SwinIFS: Landmark Guided Swin Transformer For Identity Preserving Face Super Resolution

arXiv:2601. 01406v2 Announce Type: replace-cross Abstract: Face super-resolution aims to recover high-quality facial images from severely degraded low-resolution inputs, but remains challenging due to the loss of fine structural details and identity-specific features.

By Habiba Kausar, Saeed Anwar, Omar Jamal Hammad, Abdul Bais

llms benchmarks

arXiv AI

Jul 10

LoKA: Low-precision Kernel Applications for Recommendation Models At Scale

arXiv:2605. 10886v3 Announce Type: replace-cross Abstract: Recent GPU generations deliver significantly higher FLOPs using lower-precision arithmetic, such as FP8.

By Liang Luo, Yinbin Ma, Quanyu Zhu, Vasiliy Kuznetsov, Yuxin Chen, Neng Shi, Jian Jiao, Jiecao Yu, Buyun Zhang, Tongyi Tang, Xiaohan Wei, Yanli Zhao, Zeliang Chen, Yuchen Hao, Venkatesh Ranganathan, Sandeep Parab, Yantao Yao, Maxim Naumov, Chunzhi Yang, Shen Li, Ellie Wen, Wenlin Chen, Santanu Kolay, Chunqiang Tang

llms benchmarks

arXiv Machine Learning

Jul 10

Eigenvalue Calibration for Semantic Embeddings of Large Language Models

arXiv:2607. 08377v1 Announce Type: new Abstract: Uncertainty quantification is central to the reliable deployment of large language models (LLMs), and eigenvalues of semantic embeddings have recently emerged as a key tool in state-of-the-art methods.

By Sebastian G. Gruber, Nassim Walha, Francis Bach, Florian Buettner

llms rag benchmarks

arXiv AI

Jul 10

MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer

arXiv:2605. 17361v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm for complex problem solving, where performance critically depends on the underlying inter-agent communication topology.

By Xuefei Wang, Jialu Wang, Fengbo Zhang, Yihan Hu, Di Zhang, Yutong Ye, Yikun Ban, Jun Han, Ruijie Wang

llms agents

arXiv AI

Jul 10

Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study

arXiv:2607. 08652v1 Announce Type: new Abstract: Self-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse.

By Eugene Ng Yi Sheng, Bingquan Shen

llms agents safety

arXiv AI

Jul 10

Reinforcing the Generation Order of Multimodal Masked Diffusion Models

arXiv:2607. 08056v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) have recently achieved substantial progress in natural language generation tasks.

By Yidong Ouyang, Zhe Wang, Sourav Bhabesh, Dmitriy Bespalov

llms diffusion multimodal benchmarks safety

arXiv Machine Learning

Jul 10

Resample or Reroute? Budget-Aware Test-Time Model Selection for Large Language Models

arXiv:2607. 08665v1 Announce Type: new Abstract: Routing among large language models (LLMs) trades response quality against serving cost, motivated by the reported gap between deployed routers and a per-instance oracle.

By Teng-Ruei Chen

llms benchmarks

arXiv AI

Jul 10

Structured Pruning of Large Language Models via Power Transformation and Sign-Preserving Score Aggregation with Adaptive Feature Retention

arXiv:2607. 08027v1 Announce Type: cross Abstract: This paper proposes an improved structured pruning method for large language models (LLMs) that addresses key challenges in adapting Adaptive Feature Retention (AFR), an unstructured pruning technique, to structured pruning.

By Ryota Kobayashi, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, Yasunori Ishii, Tomoyuki Okuno, Kazuki Kozuka

llms efficiency safety

arXiv AI

Jul 10

A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents

arXiv:2607. 07985v1 Announce Type: cross Abstract: We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the raw stereo waveform, tested across three models in the Gemini family: 2.

By A. Sayyad, J. Emmons, S. Jones, T. Lin, H. Krishnan

llms agents safety

arXiv AI

Jul 10

Who Analyses the Analyser? Self-Validating LLM Hazard Analysis with Constitutional Meta-STPA

arXiv:2607. 08054v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly trusted to draft the artifacts of safety analysis such as, losses, hazards, Unsafe Control Actions (UCAs), and safety constraints, inside rigorous processes such as Systems-Theoretic Process Analysis (STPA).

By Samuel Tetteh, Udip Shrestha, Joshua R. Waite, Cody Fleming

llms safety

arXiv AI

Jul 10

MetaHGNIE: Meta-Path Induced Hypergraph Contrastive Learning in Heterogeneous Knowledge Graphs

arXiv:2512. 12477v2 Announce Type: replace Abstract: Estimating node importance in heterogeneous knowledge graphs is a fundamental problem underlying recommendation, search, and knowledge decision systems.

By Jiawen Chen, Yanyan He, Qi Shao, Mengli Wei, Duxin Chen, Wenwu Yu, Yanlong Zhao

llms rag benchmarks safety

arXiv Machine Learning

Jul 10

Before the Last Token: Diagnosing Final-Token Safety Probe Failures

arXiv:2605. 12726v2 Announce Type: replace Abstract: Final-token safety probes monitor a single hidden state after prompt prefill, but jailbreak prompts can contain probe-visible unsafe evidence distributed across earlier user-token representations that is missed by this readout.

By Shravan Doda

llms safety

arXiv AI

Jul 10

Towards Isolated Interventions via Almost Orthogonal Features in Language Models

arXiv:2602. 04718v2 Announce Type: replace-cross Abstract: A central premise in mechanistic interpretability is that meaningful concepts in language models are represented by linear features in activation space.

By Moritz Miller, Florent Draye, Bernhard Sch\"olkopf

llms safety

arXiv AI

Jul 10

When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals

arXiv:2607. 08065v1 Announce Type: new Abstract: LLM-as-judge (Zheng et al.

By Kaihua Ding

llms safety

arXiv AI

Jul 10

Reaction-network reasoning with frontier models for experimentally confirmed catalyst-selectivity hypotheses

arXiv:2607. 08003v1 Announce Type: cross Abstract: Catalysts are essential for sustainable chemical manufacturing, yet discovering novel architectures remains a bottleneck dominated by trial-and-error experimentation and computationally intensive screening.

By Sutanay Choudhury, Anwesha Banerjee, Udishnu Sanyal, Jorin Dawidowicz, Chiezugolum Ijeoma Odilinye, Jesun Firoz, Liney Arnadottir, Simone Raugei, Johannes Lercher, Arnab Dutta

llms

arXiv AI

Jul 10

FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation

arXiv:2607. 08359v1 Announce Type: cross Abstract: Vision-Language Navigation (VLN) enables UAV autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs.

By Xueke Zhu, Qingyan Meng, Liutao Yu, Wei Zhang, Zhengyu Ma, Huihui Zhou, Yonghong Tian

llms agents diffusion multimodal benchmarks

arXiv AI

Jul 10

Large-Language-Models-as-a-Judge in Theory-Agnostic Adaptive Metric-Alignment for Prototypical Networks in Personality Recognition

arXiv:2607. 08374v1 Announce Type: cross Abstract: Personality recognition has traditionally been constrained by theory-dependent formulations, where models are trained to fit predefined psychological taxonomies rather than uncovering shared underlying behavioral structure.

By Jing Jie Tan, Ban-Hoe Kwan, Danny Wee-Kiat Ng, Yan-Chai Hum, Shih-Yu Lo, Po-An Chen, Noriyuki Kawarazaki, Kosuke Takano, Anissa Mokraoui

llms rag safety data-engineering

Get the daily briefing