Large language models

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

29,741 stories · RSS feed

arXiv AI

Sep 30

Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving

arXiv:2609.36750v1 Announce Type: cross Abstract: Self-rewarding reinforcement learning (RL) enables large language models (LLMs) to self-evolve without human labels. Existing ensemble-based methods...

By Yiming Wang, Yikang Liu, Qingyuan Tian, Xingyu Chen, Zhuosheng Zhang, Zhaopeng Tu, Rui Wang

llms reinforcement-learning benchmarks

arXiv Machine Learning

Sep 30

Harnessing Large Language Models to Compile Task-Relevant Context into Bayesian Optimisation

arXiv:2609.36788v1 Announce Type: new Abstract: Incorporating rich task-relevant context, such as domain knowledge and external observations, is a key capability yet remains challenging for Bayesian...

By Zhongwei Yu, Sourabh Roy, Bin Cao, Xue Yan, Anjie Liu, Jun Wang

llms rag benchmarks

arXiv Machine Learning

Sep 30

Towards Better Training Signal: Advantage Clipped Policy Optimization

arXiv:2609.36816v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a cornerstone for improving the reasoning capabilities of large language models (LLMs), but the need for on-poli...

By Ruichuan Huang, Jinghan Liu, Congliang Chen

llms reinforcement-learning benchmarks

arXiv Machine Learning

Sep 30

Fine-Tuning on Self-Generated and Reward-Weighted Data: Learning Dynamics, Convergence Rates, and Benefits of Off-Policyness

arXiv:2609.36945v1 Announce Type: new Abstract: We study the learning dynamics of fine-tuning a policy model on self-generated and reward-weighted data, with particular focus on a generalized version...

By Zhiwei Wang, Yanxi Chen, Yaliang Li, Bolin Ding

llms reinforcement-learning fine-tuning

arXiv Machine Learning

Sep 30

Cool the Sampler, Not the Learner: Sampling Temperature Moves the Staleness Cliff of Importance-Corrected GRPO

arXiv:2609.36953v1 Announce Type: new Abstract: Production RL for language models lets the sampler fall behind the learner and repairs the resulting mismatch with a truncated importance weight. We as...

By Taiheng Pan

llms reinforcement-learning

arXiv Machine Learning

Sep 30

TaskBridge: Bridging Unsupervised Tabular Anomaly Detection and In-Context Learning via Virtual Tasks

arXiv:2609.36968v1 Announce Type: new Abstract: Unsupervised tabular anomaly detection (TAD) aims to identify anomalous rows in tabular data using normal training samples. While conventional methods...

By Doyun Choi, Dooho Lee, Jaemin Yoo

llms benchmarks

arXiv Machine Learning

Sep 30

High-Resolution Dynamic Functional Connectivity Generation with Graph-Variate Flow Matching

arXiv:2609.37037v1 Announce Type: new Abstract: High-resolution dynamic functional connectivity (DFC) can reveal rapidly evolving brain-network interactions, but short temporal windows yield noisy, o...

By Om Roy, Yashar Moshfeghi, Keith Malcolm Smith

llms diffusion

arXiv Machine Learning

Sep 30

Looped Transformers as Optimizers

arXiv:2609.37379v1 Announce Type: new Abstract: Looped Transformers provide a parameter-efficient approach to depth scaling by repeatedly applying shared Transformer blocks. Recent reasoning models h...

By Yulong Huang, Chen Jiang, Zhanpeng Zhou, Hongtao Zhang, Tianyu Li, Tianyu He, Xiangyu Zhang, Bojun Cheng

llms

arXiv Machine Learning

Sep 30

Probability Contracts: Accuracy, Coherence, and Decisions Across LLM Interfaces

arXiv:2609.37470v1 Announce Type: new Abstract: A probability used for a decision should refer to the same event across equivalent requests. We introduce probability contracts, a benchmark connecting...

By Han Chen, Yingrui Li

llms benchmarks

arXiv AI

Sep 30

Risk-Controlled Selective LLM Answering by Pricing Label-Free Checks

arXiv:2609.37493v1 Announce Type: cross Abstract: Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error...

By Dongyub Jude Lee, Jungseob Lee, Chanjun Park, Hyeonseok Moon, Heuiseok Lim

llms

arXiv AI

Sep 30

Hierarchical Compression of Vision-Language Model Benchmarks

arXiv:2609.37515v1 Announce Type: cross Abstract: Thorough evaluation of vision-language models (VLMs) has become prohibitively expensive, as benchmarks span an ever-broader spectrum of capabilities...

By Hyunjong Ok, Seunggu Kang, Jaeho Lee

llms rag efficiency multimodal benchmarks

arXiv Machine Learning

Sep 30

Why Adaptive Optimizers Underestimate Rare Tokens

arXiv:2609.37535v1 Announce Type: new Abstract: In the softmax output layer, a rare token receives a small positive logit gradient on most steps and a much larger negative gradient on the few steps w...

By Sangsidhya Kar

llms rag safety

arXiv AI

Sep 30

ReLMem: Learning Recurrent Memory for Longitudinal EHR Modeling

arXiv:2609.37587v1 Announce Type: cross Abstract: Longitudinal electronic health record (EHR) modeling requires integrating new visits with an expanding patient history. Yet the continual accumulatio...

By Zijie Meng, Xiwei Dai, Yingying Zhang, Jian Wu, Xian Wu, Zuozhu Liu

llms

arXiv Machine Learning

Sep 30

Predictive Geometry of Hidden Trajectories in Transformers

arXiv:2609.37717v1 Announce Type: new Abstract: Decoder-only transformers are trained only through a terminal next-token prediction loss, yet this loss constrains every intermediate hidden state thro...

By Timur Mudarisov, Mikhail Burtsev, Tatiana Petrova, Radu State

llms efficiency

arXiv Machine Learning

Sep 30

Optimizer-dependent training dynamics converge to the same one-third optimal data scaling

arXiv:2609.37745v1 Announce Type: new Abstract: Neural scaling, in which loss falls as a power law with training, is central to large language models, and one recent proposal is that a $1/3$ exponent...

By Hyunseok Lee, Mihir Basil, Yizhou Liu, Jeff Gore

llms safety

arXiv AI

Sep 30

Privy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR

arXiv:2609.37825v1 Announce Type: cross Abstract: Assigning credit to intermediate steps remains a central challenge in training Large Language Models (LLMs) on multi-step reasoning tasks with sparse...

By Kun Liang, Chenming Tang, Clive Bai, Weijie Liu, Zeyuan Liu, Qingyang Zhang, Saiyong Yang, Yunfang Wu

llms reinforcement-learning benchmarks

arXiv AI

Sep 30

Scaling Influence Functions in LLMs through Eigenbasis-Corrected One-Bit Gradient Projection

arXiv:2609.37842v1 Announce Type: cross Abstract: Influence functions estimate how individual training examples affect the behavior of large language models (LLMs). Analyzing how training data influe...

By Jaeseung Heo, J Rosser, Dongwoo Kim

llms fine-tuning efficiency

arXiv Machine Learning

Sep 30

Overcoming Scaling Limits in On-Policy Self-Distillation for LLM Reasoning

arXiv:2609.37915v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a student to match a privileged teacher distribution along its own sampled trajectory. Standard OPSD applies...

By Md. Ismail Hossain, Humaira Kousar, Isidora Chara Tourni

llms efficiency

arXiv Machine Learning

Sep 30

Pattern Formation in Transformers

arXiv:2609.37921v1 Announce Type: new Abstract: What are the inductive biases of a Transformer architecture? Existing theory on how the forward pass shapes representations either considers whether Tr...

By Erkan Turan, Gaspard Abel, Maks Ovsjanikov

llms

arXiv Machine Learning

Sep 30

TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models

arXiv:2609.37989v1 Announce Type: new Abstract: Tabular foundation models achieve strong zero-shot accuracy on structured data by pretraining on synthetic tables, but they ignore the column names, ta...

By Deqing Fu, Huangyuan Su, Rajat Sen, Taman Narayan, Sujay Sanghavi, Abhimanyu Das, Weihao Kong

llms agents benchmarks data-engineering

Get the daily briefing