Research map / Vision-language and multimodal / Visual question answering
R3: Reinforced Ranker-Reader for Open-Domain Question Answering
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 |
|---|---|---|---|
| jointly train ranker and reader with RL (R3) instead of separate supervised ranker (SR2) (ablation) | Ranker-Reader · Quasar-T | EM: 31.9 -> 34.2 | Helped |
| jointly train ranker and reader with RL (R3) instead of separate supervised ranker (SR2) (ablation) | Ranker-Reader · SQuAD-open | EM: 27.2 -> 29.1 | Helped |
| jointly train ranker and reader with RL (R3) instead of separate supervised ranker (SR2) (ablation) | Ranker-Reader · WikiMovies | EM: 38.1 -> 38.8 | Helped |
| jointly train ranker and reader with RL (R3) instead of separate supervised ranker (SR2) (ablation) | Ranker-Reader · CuratedTREC | EM: 27.7 -> 28.4 | No clear effect |
| jointly train ranker and reader with RL (R3) instead of separate supervised ranker (SR2) (ablation) | Ranker-Reader · WebQuestions | EM: 15.6 -> 17.1 | Helped |
| use ranker trained by R3 instead of SR2 ranker with fixed reader (ablation) | Single Reader · Quasar-T | EM: 31.8 -> 33.1 | Helped |
| train reader jointly in R3 instead of separately, same ranker (ablation) | R3 · Quasar-T | EM: 33.1 -> 34.1 | Helped |
| R3 ranker instead of SR2 ranker (ablation) | Ranker · Quasar-T | top-1 recall: 28.8 -> 40.3 | Helped |
| R3 ranker instead of SR2 ranker (ablation) | Ranker · Quasar-T | top-5 recall: 54.9 -> 54.5 | No clear effect |
Closest papers by meaning
- RINK: Reader-Inherited Evidence Reranker for Table-and-Text Open Domain Question Answering (AAAI 2023 · similarity 0.90)
- Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering (ICLR 2018 · similarity 0.88)
- HAS-QA: Hierarchical Answer Spans Model for Open-Domain Question Answering (AAAI 2019 · similarity 0.88)
- Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering (ICLR 2019 · similarity 0.88)
- SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs (ICLR 2024 · similarity 0.86)
- 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.