autoregressive language models
PulseAugur coverage of autoregressive language models — every cluster mentioning autoregressive language models across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Language models' confidence signals disagree, impacting reliability assessment
A new research paper explores the distinction between local and global confidence signals in autoregressive language models. The study found that these two measures, derived from the probability of the greedy-selected a…
-
New research explores robust watermarking for AI text generation · 2 sources tracked
Two new research papers propose methods for detecting watermarks in AI-generated text, addressing different types of language models. The first paper, "Predictive Likelihood Ratios for Language Model Watermark Detection…
-
New Bayesian Penalty Reverses Attention Collapse in Language Models
Researchers have developed a new framework called Bayesian Repetition Penalty to address the issue of attention collapse in autoregressive language models. This pathology causes models to get stuck in repetitive loops. …
-
New framework detects AI copyright infringement via conditional sensitivity
Researchers have developed a new framework called Dual-Branch Conditional Sensitivity (DCS) to detect copyright infringement in AI-generated content. This framework treats infringement as a conditional distribution shif…
-
New research tackles diffusion language model limitations
Researchers are exploring new methods to improve diffusion language models (DLMs), which offer faster inference than autoregressive models. Several recent papers introduce techniques to enhance DLM performance, includin…