SAMSum

Overview edit

Variants: SAMSum, SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization, SAMSum Corpus (translated to Russian)

Associated Benchmarks

This dataset is used in 2 benchmarks:

• Summarization - Metrics: ROUGE-1, ROUGE-2, ROUGE-L, ROUGE-LSUM, gen_len, loss
• Text Summarization - Metrics: ROUGE-1, ROUGE-2, ROUGE-L, BertScoreF1

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation (2024) -
• Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization (2024) -
• Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles (2024) -
• Instructive Dialogue Summarization with Query Aggregations (2023) -
• Momentum Calibration for Text Generation (2022) -
• Calibrating Sequence likelihood Improves Conditional Language Generation (2022) -
• Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization (2022) -
• Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization (2021) -
• Hierarchical Learning for Generation with Long Source Sequences (2021) -