Research map / Large language models / Retrieval and knowledge
Enhanced Story Comprehension for Large Language Models through Dynamic Document-Based Knowledge Graphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add document-specific knowledge graph facts to prompts | GPT-2 · LF-SQuAD | F1: 8.1 -> 18.6 | Helped |
| Add document-specific knowledge graph facts to prompts | GPT-2 · LF-QUOREF | F1: 24.0 -> 25.4 | Helped |
| Add document-specific knowledge graph facts to prompts | GPT-3 · LF-SQuAD | F1: 15.7 -> 20.0 | Helped |
| Add document-specific knowledge graph facts to prompts | GPT-3 · LF-QUOREF | F1: 22.4 -> 25.7 | Helped |
| Add document-specific knowledge graph facts to prompts | XLNet · LF-SQuAD | F1: 6.6 -> 12.9 | Helped |
| Add document-specific knowledge graph facts to prompts | XLNet · LF-QUOREF | F1: 14.1 -> 18.5 | Helped |
| Add document-specific knowledge graph facts to prompts | GPT-2 · Sparknotes | PPL: 2.42 -> 2.24 | Helped |
| Add document-specific knowledge graph facts to prompts | GPT-2 · Sparknotes | BLEU: 0.0620 -> 0.0622 | Helped |
| Add document-specific knowledge graph facts to prompts | GPT-3 · Sparknotes | PPL: 10.93 -> 10.89 | Helped |
| Add document-specific knowledge graph facts to prompts | GPT-3 · Sparknotes | BLEU: 0.0643 -> 0.0455 | Hurt |
| Add document-specific knowledge graph facts to prompts | XLNet · Sparknotes | PPL: 1.61 -> 1.56 | Helped |
| Add document-specific knowledge graph facts to prompts | XLNet · Sparknotes | BLEU: 0.0306 -> 0.0254 | Hurt |
Closest papers by meaning
- NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens (ICLR 2025 · similarity 0.88)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (AAAI 2025 · similarity 0.87)
- Chain of Agents: Large Language Models Collaborating on Long-Context Tasks (NeurIPS 2024 · similarity 0.86)
- Knowledge Graph Prompting for Multi-Document Question Answering (AAAI 2024 · similarity 0.86)
- Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models (NeurIPS 2025 · similarity 0.86)
- StoryGPT-V: Large Language Models as Consistent Story Visualizers (CVPR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.