Search papers, labs, and topics across Lattice.
The RaguTeam's winning system for SemEval-2026 MTRAGEval Task B employs a heterogeneous ensemble of seven LLMs, prompted in two ways, with a GPT-4o-mini judge selecting the best response from the candidates. This ensemble achieved a conditioned harmonic mean of 0.7827, significantly outperforming the strongest baseline (gpt-oss-120b at 0.6390). Ablation studies confirmed the importance of diversity in model families, scales, and prompting strategies for ensemble performance.
A judge-orchestrated ensemble of diverse LLMs trounces single models in multi-turn response generation, proving that strategic model selection beats brute force scaling.
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
