Large language models

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

30,670 stories · RSS feed

arXiv AI

Jun 10

IDP-Bench: Benchmarking ability of LLMs to protect personal information in interdependent privacy contexts

arXiv:2606. 09908v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data, making privacy a major challenge for their design and evaluation.

By Ayana Hussain, Soumya Sharma, Golnoosh Farnadi, Nicholas Vincent, H\'eber Hwang Arcolezi, Ulrich A\"ivodji

llms benchmarks safety

arXiv AI

Jun 10

KG-SoftMAP: Soft Knowledge-Graph Priors for Bayesian Network Structure Learning from Sparse Discrete Data

arXiv:2606. 10358v1 Announce Type: cross Abstract: Learning Bayesian network (BN) structure from sparse discrete data is hard: when each instance records only a few variables, most variable pairs lack the joint observations needed for reliable scoring, and data-only methods recover little structure.

By Guoliang Xu, James E. Corter

llms benchmarks

arXiv AI

Jun 10

RAG over Thinking Traces Can Improve Reasoning Tasks

arXiv:2605. 03344v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) has proven effective for knowledge-intensive tasks, but is widely believed to offer limited benefit for reasoning-intensive problems such as math and code generation.

By Negar Arabzadeh, Wenjie Ma, Sewon Min, Matei Zaharia

llms rag benchmarks

arXiv Machine Learning

Jun 10

The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring

arXiv:2606. 10327v1 Announce Type: cross Abstract: Automated Essay Scoring (AES) systems must judge interdependent discourse elements (e.

By Ali Keramati, Mark Warschauer

llms nlp fine-tuning efficiency

arXiv AI

Jun 10

Advancing the State-of-the-Art in Empirical Privacy Auditing

arXiv:2606. 10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples.

By Nicole Mitchell, Galen Andrew, Arun Ganesh, Brendan McMahan, Peter Kairouz

llms fine-tuning benchmarks safety

arXiv AI

Jun 10

ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs

arXiv:2606. 10461v1 Announce Type: cross Abstract: Text-attributed Graphs (TAGs) incorporate textual node attributes with graph structures to describe rich relational semantics.

By Xianlin Zeng, Fan Xia, Xiangyu Chen

llms rag diffusion benchmarks safety

arXiv Machine Learning

Jun 10

Multi-task LLMs for Bug Classification: Efficient Inference with Auxiliary Decoding Heads

arXiv:2606. 09956v1 Announce Type: cross Abstract: The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severely underdeveloped.

By Nikolai Rozanov

llms agents nlp efficiency benchmarks safety

arXiv AI

Jun 10

Transformer Based Model for Spatiotemporal Feature Learning in EEG Emotion Recognition

arXiv:2606. 10718v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a widely adopted technique for monitoring brain activity, offering valuable insights into neurological states due to its high temporal resolution and cost-effectiveness.

By Xinglong Cui, Dian Gu

llms benchmarks

arXiv Machine Learning

Jun 10

GRAFT: Gain-Recalibrated Adapters for Transformer-Based Neural Population Activity Modeling

arXiv:2606. 11066v1 Announce Type: new Abstract: Neural population activity models can recover rich temporal structure from binned spikes, but their read-in and readout layers often remain tied to a fixed set of recorded neurons.

By Xiangsheng Ge, Yang Xie

llms

arXiv AI

Jun 10

CANVAS: Captioning Art with Narrative Visual-Audio AI Systems

arXiv:2606. 09846v1 Announce Type: cross Abstract: Visual art remains largely inaccessible to blind and low-vision (BLV) audiences due to brief or absent alt-text, which rarely conveys the sensory, spatial, or emotional qualities of an artwork.

By Vignesh Nagarajan

llms multimodal

arXiv AI

Jun 10

Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey

arXiv:2606. 10706v1 Announce Type: cross Abstract: Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large language models (LLMs), yet efficiency is often studied through isolated techniques rather than as an interacting system of limits.

By Vanessa Schmidt, Huy Hoang Nguyen, C\'edric Jung, Shirin Salehi, Anke Schmeink

llms fine-tuning efficiency

arXiv AI

Jun 10

The Role of Feedback Alignment in Self-Distillation

arXiv:2606. 11173v1 Announce Type: new Abstract: Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response.

By Semih Kara, O\u{g}uzhan Ersoy

llms efficiency safety

arXiv AI

Jun 10

Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTS

arXiv:2606. 09837v1 Announce Type: cross Abstract: Emotional interaction is increasingly crucial for conversational AI, yet current systems lack a self-emotion determination mechanism to drive the streaming text-to-speech (TTS) synthesis.

By Yue Zhao, Hongyan Li, Yong Chen, Luo Ji

llms reinforcement-learning fine-tuning multimodal safety

arXiv AI

Jun 10

Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling

arXiv:2606. 09926v1 Announce Type: cross Abstract: Sampling from the sequence-level power distribution $p^\alpha$ elicits RL-level reasoning from base language models without any parameter updates, but the standard Metropolis--Hastings (MH), a Markov Chain Monte Carlo (MCMC) sampler, is both expensive and slow-mixing.

By Hong Guo, Nianhui Guo, Christoph Meinel, Haojin Yang

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 10

Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations

arXiv:2606. 10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots.

By Beomjun Kim, Seong Hyeon Park, Seunghoon Sim, Seungjun Moon, Sanghyeok Lee, Jinwoo Shin

llms agents robotics fine-tuning benchmarks

arXiv Machine Learning

Jun 10

CodeAlchemy: Synthetic Code Rewriting at Scale

arXiv:2606. 10087v1 Announce Type: cross Abstract: Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats.

By Ankit Gupta, Aditya Prasad, Rameswar Panda

llms benchmarks

arXiv AI

Jun 10

CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs

arXiv:2606. 11063v1 Announce Type: new Abstract: AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model.

By Joachim Schaeffer, Thomas Jiralerspong, Alexander Panfilov, Guillaume Lajoie, Jonas Geiping, Yoshua Bengio, Roland S. Zimmermann

llms benchmarks

arXiv AI

Jun 10

Can Multi-Agent LLMs Identify Their Peers? Stylometric Fingerprinting in Role-Constrained Political Analysis

arXiv:2606. 09854v1 Announce Type: cross Abstract: Multi-agent large language model (LLM) pipelines for political statement analysis are vulnerable to peer-preservation bias: models tend to protect peer models from deactivation and show identity-dependent scoring distortions.

By Juergen Dietrich

llms agents fine-tuning safety

arXiv Machine Learning

Jun 10

How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs

arXiv:2606. 10646v1 Announce Type: new Abstract: Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat all tokens equally, failing to distinguish decisive reasoning steps from routine formatting or fluent filler.

By Zhichen Dong, Yang Li, Yuhan Sun, Weixun Wang, Yijia Luo, Zinian Peng, Taiheng Ye, Chao Yang, Wenbo Su, Yu Cheng, Bo Zheng, Junchi Yan

llms reinforcement-learning efficiency

arXiv AI

Jun 10

Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models

arXiv:2606. 11074v1 Announce Type: cross Abstract: With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under complex personality conditions is essential.

By Peiqi Jia (Xi'an Jiaotong University), Haonan Jia (Beihang University), Ziqi Miao (Beihang University), Linkang Du (Xi'an Jiaotong University), Yuntao Wang (Xi'an Jiaotong University), Zhou Su (Xi'an Jiaotong University)

llms nlp multimodal

Get the daily briefing