Model card
GPT-3.5-Turbo + TriSum Rationale.
OpenAIproprietaryGPT-3.5-Turbo prompted with structured aspect-triple rationale
GPT-3.5-Turbo prompted with the structured TriSum rationale (aspect-triple-summary format). Reported in TriSum (arXiv:2403.10351, NAACL 2024) Table 2. Best ROUGE-1 result in the TriSum paper.
§ 01 · Benchmarks
Every benchmark GPT-3.5-Turbo + TriSum Rationale has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | cnn-/-daily-mail | Computer Vision · Optical Character Recognition | rouge-2 | 23.5% | #3 | 2024-03-15 | source ↗ |
| 02 | cnn-/-daily-mail | Computer Vision · Optical Character Recognition | rouge-1 | 46.7% | #4 | 2024-03-15 | source ↗ |
| 03 | cnn-/-daily-mail | Computer Vision · Optical Character Recognition | rouge-l | 40.7% | #12 | 2024-03-15 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where GPT-3.5-Turbo + TriSum Rationale actually performs.
§ 03 · Papers
1 paper with results for GPT-3.5-Turbo + TriSum Rationale.
- 2024-03-15· Natural Language Processing· 3 results
TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale
§ 04 · Related models
Other OpenAI models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
3
results
3 of 3 rows marked verified.