Query-driven Contrastive Summarization on Hotels (test)
82Contrast Win RateQ-STRUM Debate
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Q-STRUM DebateEvaluation Model=GPT-4o, Comparison Baseline=Contrastive2025.02 | 82 | 62 | 80 | 78 | |
| Q-STRUM DebateEvaluation Model=GPT-4o, Comparison Baseline=Base2025.02 | 82 | 59 | 86 | 84 |