FusionEval: Benchmarking Model Fusion for Large Language Models
arXiv:2610.30162v1 Announce Type: new Abstract: Model fusion aims to integrate the capabilities of multi-expert models into a single model. Existing evaluations offer limited coverage of reasoning with long chains of thought and tool use, while strong average performance can mask substantial losses…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-23 04:00 · arXiv cs.CL
FusionEval: Benchmarking Model Fusion for Large Language Models