Showing 2026Show all
2 papers · 1 filter
cs.CL2026
The Astonishing Ability of Large Language Models to Parse Jabberwockified Language
Gary Lupyan, Senyi Yang
We show that large language models (LLMs) have an astonishing ability to recover meaning from severely degraded English texts. Texts in which content words have been randomly subst…
cs.CL2026
GRRM: Group Relative Reward Modeling for Machine Translation
Sen Yang, Shanbo Cheng, Lu Xu +2
While Group Relative Policy Optimization (GRPO) offers a powerful framework for LLM post-training, its effectiveness in open-ended domains like Machine Translation hinges on accura…