The State Of LLMs 2025: Progress, Problems, and Predictions

RELISH: LLM REgression with a Latent Iterative State Head

arXiv:2604. 01206v2 Announce Type: replace-cross Abstract: We present RELISH (REgression with a Latent Iterative State Head), a novel, lightweight architecture designed for text regression with large language models.

Fast Inference on Large Language Models: BLOOMZ on Habana Gaudi2 Accelerator

Scaling Point-in-Time Language Models

arXiv:2607. 11889v1 Announce Type: cross Abstract: Large language models trained on unrestricted internet corpora inevitably embed information from the future, introducing lookahead bias that compromises the validity of backtests and causal inference in finance and the social sciences.

A Latent Variable Framework for Scaling Laws in Large Language Models

arXiv:2512. 06553v2 Announce Type: replace-cross Abstract: We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs).

Cross-LLM Consistency in Inference: Evidence from Shared Interactions

arXiv:2606. 08129v1 Announce Type: new Abstract: Large language models (LLMs) differ in architecture, training data, and optimization procedures, yet they may still develop similar internal inference patterns.

Very Large Language Models and How to Evaluate Them

A Survey on Diffusion Language Models

arXiv:2508. 10875v3 Announce Type: replace-cross Abstract: Diffusion Language Models (DLMs) are rapidly emerging as a powerful and promising alternative to the dominant autoregressive (AR) paradigm.

Inverse Depth Scaling From Most Layers Being Similar

arXiv:2602. 05970v2 Announce Type: replace-cross Abstract: Neural scaling laws relate loss to model size in large language models (LLMs), yet depth and width may contribute to performance differently, requiring more detailed studies.

Accelerating Large Language Model Inference with Self-Supervised Early Exits

arXiv:2407. 21082v3 Announce Type: replace-cross Abstract: This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers.

Improved Large Language Diffusion Models

arXiv:2606. 25331v1 Announce Type: cross Abstract: Modern large language models are predominantly trained with autoregressive factorization and causal attention.

Matryoshka Language Model Suites

arXiv:2608. 09703v1 Announce Type: new Abstract: Training a language model suite classically requires training each model separately and serving them independently.

How Much is Left? LLMs Linearly Encode Their Remaining Output Length

Large language models generate one token at a time, yet their responses show remarkably consistent length structure: step-by-step solutions converge in predictable token counts, retrievals stop after a few sentences, retractions extend responses by measurable amounts. We ask whether the model carries an internal estimate of how much response remains.