Summarization Faithfulness on SAMSum (SummaC, AlignScore)
41.08SummaCVanilla
Evaluation results
| Method | Links | ||
|---|---|---|---|
| VanillaSystem=Vanilla, Model Class=LLM (GPT-4.1), Shots=0-shot2025.12 | 41.08 | 72.44 | |
| GPT-5System=GPT-5, Model Class=Large Reasoning Models (LRM), Shots=0-shot2025.12 | 39.6 | 74.82 | |
| Cited Summarization (Cite)System=Cite, Model Class=LLM (GPT-4.1), Shots=0-shot2025.12 | 39.36 | 67.54 | |
| Plan-then-Write (Plan)System=Plan, Model Class=LLM (GPT-4.1), Shots=0-shot2025.12 | 38.83 | 72.78 | |
| Iterative Refine (IR)System=IR, Model Class=LLM (GPT-4.1), Shots=0-shot2025.12 | 38.66 | 69.23 | |
| Self-Consistency (SC)System=SC, Model Class=LLM (GPT-4.1), Shots=0-shot2025.12 | 38.65 | 67.06 | |
| o3System=o3, Model Class=Large Reasoning Models (LRM), Shots=0-shot2025.12 | 37.98 | 69.22 | |
| Decomposition (Deco)System=Deco, Model Class=LLM (GPT-4.1), Shots=0-shot2025.12 | 37.5 | 73.2 | |
| o1System=o1, Model Class=Large Reasoning Models (LRM), Shots=0-shot2025.12 | 27.61 | 86.52 | |
| Chain-of-Thought (CoT)System=COT, Model Class=LLM (GPT-4.1), Shots=0-shot2025.12 | 27.41 | 86.62 | |
| Extract-to-Abstract (E2A)System=E2A, Model Class=LLM (GPT-4.1), Shots=0-shot2025.12 | 25.96 | 90.14 | |
| Question-Answer Guided (QAG)System=QAG, Model Class=LLM (GPT-4.1), Shots=0-shot2025.12 | 24.43 | 88.32 |