Research map / Large language models / Retrieval and knowledge
Capturing Greater Context for Question Generation
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 encoder attention to the document representation (ablation) | Question generation model · SQuAD split1 | BLEU-4: 3.06 -> 17.76 | Helped |
| add answer masking before decoder input (ablation) | Question generation model · SQuAD split1 | BLEU-4: 5.19 -> 17.76 | Helped |
| use 2-stage instead of 1-stage attention (ablation) | Question generation model · SQuAD split1 | BLEU-4: 14.52 -> 17.76 | Helped |
| use 3-stage instead of 2-stage attention (ablation) | Question generation model · SQuAD split1 | BLEU-4: 17.76 -> 12.87 | Hurt |
| use multi-stage attention to incorporate broader answer-related document context | Question generation model · SQuAD split1 | Rouge-L: 44.99 -> 45.89 | Helped |
Closest papers by meaning
- Provence: efficient and robust context pruning for retrieval-augmented generation (ICLR 2025 · similarity 0.87)
- How Teachers Can Use Large Language Models and Bloom’s Taxonomy to Create Educational Quizzes (AAAI 2024 · similarity 0.86)
- Rethinking Generative Large Language Model Evaluation for Semantic Comprehension (ICML 2024 · similarity 0.86)
- Explicitly Guided Difficulty-Controllable Visual Question Generation (AAAI 2025 · similarity 0.86)
- BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack (NeurIPS 2024 · similarity 0.85)
- Retrieval is Accurate Generation (ICLR 2024 · 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.