RLHF

Researchers at New York University and the University of Texas at Austin analyzed output from 14 language models and identified six linguistic constructions that frontier models overuse compared with human writing. Smaller models such as Llama and the Olmo base model came closest to human text, and the authors point to post-training as the likely cause.

IBM released Granite 4.1, a family of dense decoder-only LLMs (3B, 8B, 30B parameters) trained on approximately 15 trillion tokens using a five-phase pre-training pipeline. The 8B instruct model matches or surpasses the previous Granite 4.0-H-Small (32B-A9B MoE) despite using fewer parameters and a simpler dense architecture. All models support up to 512K context windows and are released under Apache 2.0 license.