Research map / Large language models / Language, safety and interpretability
Towards Scalable Multi-Domain Conversational Agents: The Schema-Guided Dialogue Dataset
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 pointer-generator-style copying for non-categorical slots | Schema-guided DST · MultiWOZ 2.1 | Joint Goal Accuracy: 0.434 -> 0.489 | Helped |
| Train on the entire training set instead of single-domain dialogues only | Schema-guided DST · SGD test | Active Intent Accuracy: 0.885 -> 0.906 | Helped |
| Train on the entire training set instead of single-domain dialogues only | Schema-guided DST · SGD test | Requested Slot F1: 0.956 -> 0.965 | Helped |
| Train on the entire training set instead of single-domain dialogues only | Schema-guided DST · SGD test | Average Goal Accuracy: 0.684 -> 0.560 | Hurt |
| Train on the entire training set instead of single-domain dialogues only | Schema-guided DST · SGD test | Joint Goal Accuracy: 0.356 -> 0.254 | Hurt |
| Use a shared model conditioned on service schema descriptions to support unseen APIs | Schema-guided DST · SGD unseen services | Active Intent Accuracy | Helped |
Closest papers by meaning
- ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models (ICLR 2025 · similarity 0.87)
- StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
- Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules (NeurIPS 2025 · similarity 0.85)
- Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training (ICLR 2025 · similarity 0.85)
- Building Conversational Artifacts to Enable Digital Assistant for APIs and RPAs (AAAI 2024 · similarity 0.85)
- Exploring Conversational Adaptability: Assessing the Proficiency of Large Language Models in Dynamic Alignment with Updated User Intent (AAAI 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.