Research map / Large language models / Retrieval and knowledge
Conclusion-Supplement Answer Generation for Non-Factoid Questions
Makoto Nakatsuji, Sohei Okui
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 conclusion-to-supplement attention (ablation) | NAGM · Oshiete-goo | ROUGE-L: 0.291 -> 0.299 | Improved |
| add conclusion-to-supplement attention (ablation) | NAGM · Oshiete-goo | BLEU-4: 0.147 -> 0.158 | Improved |
| add conclusion-to-supplement attention (ablation) | NAGM · nfL6 | ROUGE-L: 0.383 -> 0.402 | Improved |
| add conclusion-to-supplement attention (ablation) | NAGM · nfL6 | BLEU-4: 0.157 -> 0.181 | Improved |
| add sentence-type embeddings (ablation) | NAGM · Oshiete-goo | ROUGE-L: 0.235 -> 0.299 | Improved |
| add sentence-type embeddings (ablation) | NAGM · Oshiete-goo | BLEU-4: 0.090 -> 0.158 | Improved |
| add sentence-type embeddings (ablation) | NAGM · nfL6 | ROUGE-L: 0.349 -> 0.402 | Improved |
| add sentence-type embeddings (ablation) | NAGM · nfL6 | BLEU-4: 0.067 -> 0.181 | Improved |
| set ensemble-loss weight alpha to 1 instead of 0 (ablation) | NAGM · Oshiete-goo | ROUGE-L: 0.251 -> 0.299 | Improved |
| set ensemble-loss weight alpha to 1 instead of 0 (ablation) | NAGM · nfL6 | BLEU-4: 0.062 -> 0.181 | Improved |
| increase ensemble-loss weight alpha from 1 to 2 (ablation) | NAGM · Oshiete-goo | ROUGE-L: 0.299 -> 0.211 | Hurt |
| increase ensemble-loss weight alpha from 1 to 2 (ablation) | NAGM · nfL6 | BLEU-4: 0.181 -> 0.023 | Hurt |
Closest papers by meaning
- Improving Question Generation with Sentence-Level Semantic Matching and Answer Position Inferring (AAAI 2020 · similarity 0.88)
- Representation Consistency for Accurate and Coherent LLM Answer Aggregation (NeurIPS 2025 · similarity 0.85)
- Rethinking Generative Large Language Model Evaluation for Semantic Comprehension (ICML 2024 · similarity 0.85)
- SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs (ICLR 2024 · similarity 0.85)
- Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering (NeurIPS 2024 · similarity 0.85)
- A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering (NeurIPS 2026 · 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.
