Papers with narrative summarization
NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization (2025.acl-long)
Copied to clipboard
| Challenge: | Summarizing long-form narratives requires capturing intricate plotlines, character interactions, and thematic coherence over tens of thousands of tokens. |
| Approach: | They propose a multi-agent LLM framework for narrative summarization that processes long-form text through a structured pipeline without fine-tuning. |
| Outcome: | The proposed framework achieves 30.0% improvement in BERTScore across books, movies, and TV scripts. |
Agent-as-Judge for Factual Summarization of Long Narratives (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated near-human performance in summarization tasks based on traditional metrics such as ROUGE and BERTScore . however, these metrics do not adequately capture critical aspects of summarizing quality, such as factual accuracy, especially for long narratives. |
| Approach: | They propose a framework that evaluates and refines factuality in narrative summarization by leveraging a Character Knowledge Graph extracted from input narrative. |
| Outcome: | The proposed framework evaluates factuality and provides actionable guidance for refinement. |