2 papers
cs.CL2026
English Word Sense Disambiguation in 2026: When the Labels Become the Bottleneck
Vassili Philippov, Amro Salman, Dmitrii Andreev +4
In English all-words word sense disambiguation (WSD), the labels, not the models, have become the bottleneck: frontier LLMs are accurate enough that the errors surviving in the gol…
cs.MA2026
Glite ARF: Verifier-Driven Research with Parallel LLM Coding Agents
Vassili Philippov, Pavel Katunin, Dmitry Andreev +2
LLM coding agents make it tempting to automate empirical research by delegating experiments to them directly, but naive delegation does not scale to large projects: low-rate instru…