RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation

TL;DR

The paper describes a winning ensemble system for multi-turn response generation in SemEval-2026, combining seven LLMs with a GPT-4o-mini judge, achieving top performance and providing insights into model diversity and cost-effective models.

Contribution

It introduces a heterogeneous LLM ensemble with a judge for improved response generation and presents Meno-Lite-0.1, a cost-effective domain-adapted model.

Findings

Ensemble outperforms individual models in response quality.

Diversity in models and prompting strategies is crucial.

Meno-Lite-0.1 offers a strong cost-performance balance.

Abstract

We present our winning system for Task~B (generation with reference passages) in SemEval-2026 Task~8: MTRAGEval. Our method is a heterogeneous ensemble of seven LLMs with two prompting variants, where a GPT-4o-mini judge selects the best candidate per instance. We ranked 1st out of 26 teams, achieving a conditioned harmonic mean of 0.7827 and outperforming the strongest baseline (gpt-oss-120b, 0.6390). Ablations show that diversity in model families, scales, and prompting strategies is essential, with the ensemble consistently beating any single model. We also introduce Meno-Lite-0.1, a 7B domain-adapted model with a strong cost--performance trade-off, and analyse MTRAGEval, highlighting annotation limitations and directions for improvement. Our code is publicly available: https://github.com/RaguTeam/ragu_mtrag_semeval