Comparison of Output-Space LLM Merging Methods

Open Research Knowledge Graph (ORKG) 2026 Dataset Open access

Read full text
Authors: Furel TEGUIMENE YENDJI, Azanzi Jiomekong, Sanju Mishra Tiwari
DOI: 10.48366/r1585708
Cited by: 0

Abstract

This table compares output-space LLM merging methods, where models are combined at the level of generated responses rather than internal parameters. It analyzes their usion strategies, architectural assumption, training requirements, and inference cost

Fields of Study & Subjects

Topic Modeling Natural Language Processing Techniques Domain Adaptation and Few-Shot Learning

Publication details

Journal / source
Open Research Knowledge Graph (ORKG)
Publication date
23 February 2026
Language
EN
Document type
Dataset