Question Answering on MeetingBank in-domain (test)
87.75EMOriginal
Evaluation results
| Method | Links | |
|---|---|---|
| OriginalTokens=3,003, Compression Ratio (1/τ)=1.0x, Target LLM=GPT-3.5-Turbo-06132024.03 | 87.75 | |
| LLMLingua-2Tokens=970, Compression Ratio (1/τ)=3.1x, Target LLM=GPT-3.5-Turbo-0613, Backbone=xlm-roberta-large2024.03 | 86.92 | |
| LLMLingua-2-smallTokens=984, Compression Ratio (1/τ)=3.0x, Target LLM=GPT-3.5-Turbo-0613, Backbone=multilingual-BERT2024.03 | 85.82 | |
| LLMLinguaTokens=1,176, Compression Ratio (1/τ)=2.5x, Target LLM=GPT-3.5-Turbo-06132024.03 | 67.52 | |
| Selective-ContextTokens=1,222, Compression Ratio (1/τ)=2.5x, Target LLM=GPT-3.5-Turbo-06132024.03 | 66.28 |