Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2609.37857v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly scaled to wider dictionaries to recover fine-grained structure from large language model activations. Howev...
arXiv:2609.37988v1 Announce Type: new Abstract: As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This i...
arXiv:2604.25415v2 Announce Type: replace-cross Abstract: People increasingly turn to general-purpose AI chatbots for advice about emotional and mental health problems, but the ability of these syste...
arXiv:2609.37788v1 Announce Type: cross Abstract: Rubrics support the structured evaluation of language models. We propose a rubric for assessing expressed clinical reasoning in model responses, draw...
arXiv:2609.35800v1 Announce Type: new Abstract: Low-bit key-value (KV) cache quantization saves storage but can sharply degrade vision-language model (VLM) accuracy. We introduce HeadGuard, a composa...
arXiv:2609.35797v1 Announce Type: cross Abstract: Large language model (LLM) judges are often used as rewards to train policies on objectives that deterministic verifiers cannot capture. However, the...
arXiv:2609.35852v1 Announce Type: new Abstract: Pooled statistics of Transformer weights obscure how magnitude is distributed across functional channels, while individual weights are too numerous to...
The paper presents a method that uses generative large language models (LLMs) to automatically classify news articles as discussing Economic Policy Uncertainty (EPU) and to identify the specific type of EPU. Unlike earlier keyword‑based or heavily supervised machine learning approaches, this work employs weak supervision by prompting LLMs to generate synthetic labels, making the process cost‑effective and scalable. It also introduces techniques for multi‑label and hierarchical classification of EPU‑related articles.
LoopICL is a transformer architecture that loops a single block to address tabular tasks. It separates parameter count from computational depth by using a cell stream for per‑cell features and a row stream for in‑context examples, refined via within‑column and cross‑column attention. During pre‑training, varying loop counts and a learned exit‑gate allow the model to adjust inference depth at test time, achieving competitive performance with TabICLv2 while using about 90% fewer parameters.
arXiv:2609.36116v1 Announce Type: new Abstract: We study how to build more capable general-purpose agents by extending large language models (LLMs) with native typed decision-making. We introduce Dya...
arXiv:2609.36221v1 Announce Type: new Abstract: The way a model distributes activity over each layer's attention heads offers a coarse view of how it routes information through depth; how this change...
arXiv:2609.36230v1 Announce Type: new Abstract: We study the dynamical behavior of tokens in transformers from a control-theoretic perspective. Our model includes the feed-forward layer present after...
arXiv:2609.36281v1 Announce Type: new Abstract: Deep forecasters predict from a fixed-length lookback window, and lengthening it gives diminishing returns at a growing cost. Retrieval augmentation in...
arXiv:2609.36393v1 Announce Type: cross Abstract: Traditional reinforcement learning (RL) techniques focus on maximizing expected cumulative reward, where each action assumes to take a constant unit...
arXiv:2609.36448v1 Announce Type: new Abstract: Transformers have demonstrated remarkable in-context learning (ICL) capabilities, enabling them to perform new tasks without additional fine-tuning. Ho...
arXiv:2609.36612v1 Announce Type: new Abstract: Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable conte...
arXiv:2609.36636v1 Announce Type: new Abstract: Looped language models (LoopLMs) increase computational depth through parameter sharing, offering a path to scale inference computation without adding...
arXiv:2609.36641v1 Announce Type: cross Abstract: Process reward models (PRMs) have become a key component for LLMs, as their step-level feedback supports both post-training and test-time reasoning....
arXiv:2609.36653v1 Announce Type: new Abstract: Recurrent reasoning models have attracted growing attention for scaling test-time computation, typically by iteratively refining latent states with sha...
arXiv:2609.36695v1 Announce Type: new Abstract: Self-distillation turns knowledge distillation into a closed learning loop and offers a path toward recursive self-improvement. Without an external tea...