notesum.ai
Published at December 3Leveraging Large Language Models for Comparative Literature Summarization with Reflective Incremental Mechanisms
cs.CL
cs.IR
Released Date: December 3, 2024
Authors: Fernando Gabriela Garcia, Spencer Burns1, Harrison Fuller1
Aff.: 1Autonomous University of Nuevo León
| Model | ROUGE-1 | ROUGE-2 | ROUGE-L | G-Score |
|---|---|---|---|---|
| GPT-4.0 (Zero-Shot) | 0.45 | 0.20 | 0.40 | 85 |
| BART | 0.42 | 0.18 | 0.38 | 80 |
| T5 | 0.40 | 0.16 | 0.36 | 75 |
| CoT | 0.37 | 0.14 | 0.33 | 72 |
| ChatCite (Ours) | 0.50 | 0.25 | 0.45 | 92 |