Research map / Large language models / Language, safety and interpretability
An Annotated Corpus of Reference Resolution for Interpreting Common Grounding
Takuma Udagawa, Akiko Aizawa
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 reference-resolution training (REF) to TSEL (ablation) | TSEL · Target selection | score: 67.79$\pm$1.53 -> 69.01$\pm$1.58 | Improved |
| Add reference-resolution training (REF) to TSEL-DIAL (ablation) | TSEL-DIAL · Target selection | score: 67.01$\pm$1.29 -> 69.09$\pm$1.12 | Improved |
| Add TSEL and DIAL training to REF (ablation) | REF · Reference resolution | Exact Match: 85.75$\pm$0.22 -> 85.86$\pm$0.18 | No clear effect |
| Add reference-resolution training (REF) to TSEL-DIAL (ablation) | TSEL-DIAL · Selfplay dialogue (#Shared=4) | score: 42.07$\pm$1.27 -> 45.78$\pm$2.15 | Improved |
| Add reference-resolution training (REF) to TSEL-DIAL (ablation) | TSEL-DIAL · Selfplay dialogue (#Shared=5) | score: 57.37$\pm$1.29 -> 61.95$\pm$1.72 | Improved |
| Add reference-resolution training (REF) to TSEL-DIAL (ablation) | TSEL-DIAL · Selfplay dialogue (#Shared=6) | score: 77.00$\pm$1.13 -> 80.01$\pm$1.61 | Improved |
Closest papers by meaning
- A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Context (AAAI 2019 · similarity 0.93)
- ChatterBox: Multimodal Referring and Grounding with Chain-of-Questions (AAAI 2025 · similarity 0.87)
- Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding (AAAI 2021 · similarity 0.86)
- CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models (AAAI 2024 · similarity 0.85)
- Hierarchical Alignment-enhanced Adaptive Grounding Network for Generalized Referring Expression Comprehension (AAAI 2025 · similarity 0.84)
- The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans (NeurIPS 2026 · similarity 0.84)
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.
