Saltar al contenido
← volver

Where Do LLM Ensemble Gains Come From? Decomposing Candidate Value, Diversity, and Aggregation

arXiv cs.AI · arxiv.org Publicado:

arXiv:2610.18786v2 Announce Type: replace-cross Abstract: LLM ensemble gains are often measured against a single baseline, but the value attributed to additional candidates can change with the comparison used. We study an LLM aggregator under four matched conditions: Direct (no candidates), Single-slot (one candidate in a multi-slot interface), Duplicate (one candidate repeated), and Multi-candidate (separately generated candidates). Under either non-diverse control, overall candidate gain (CIV…

Leer original →

Más de arXiv cs.AI