Gemma-2

Mentions · 7d0
Mentions · 30d0
All mentions2
First seenSep 15, 2026
Last mentionedSep 16, 2026

Timeline

2 articles · newest first

A Zeroth-Order Paradigm for LLM Preference Alignment

Researchers propose ComPO, a zeroth-order comparison-based preference alignment method with convergence guarantees that mitigates likelihood displacement in LLMs.

arXiv cs.AI / cs.LG / cs.CLSep 16, 17:59 UTC · Sep 16, 2026AI research1

A Zeroth-Order Paradigm for LLM Preference Alignment

ComPO is a zeroth-order preference alignment method using comparison oracles to mitigate likelihood displacement across Mistral, Llama, Gemma, and Qwen3 models.

Hugging Face daily papersSep 15, 20:00 UTC · Sep 15, 2026AI research1

Appears with

Llamaai model · 2
Qwen3ai model · 2
Gemma-3ai model · 2
Mistralai model · 2
ComPOproduct · 1

Entities are extracted by the model from each article. First seen Sep 15, 2026, last mentioned Sep 16, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.