Research map / Large language models / Retrieval and knowledge
History-Adaption Knowledge Incorporation Mechanism for Multi-Turn Dialogue System
Yajing Sun, Yue Hu, Luxi Xing, Jing Yu, Yuqiang Xie
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 persona knowledge to history-adaption model (vs w/o knowledge) (ablation) | history-adaption model · PERSONA-CHAT original persona | r@1: 47.1 -> 57.6 | Improved |
| add history-aware knowledge updating (ablation) | history-adaption model · PERSONA-CHAT original persona | r@1: 55.7 -> 57.6 | Improved |
| add history-aware knowledge updating (ablation) | history-adaption model · PERSONA-CHAT revised persona | r@1: 49.4 -> 52.4 | Improved |
| history length 7 vs 6 or 8 (ablation) | history-adaption model · PERSONA-CHAT original persona | r@1: 55.5 / 57.6 / 54.8 for 6 / 7 / 8 | Mixed |
| use history-adaption model instead of Transformer | Transformer baseline · CMUDoG | r@1: 60.3 -> 82.7 | Improved |
| use history-adaption model instead of KV profile memory | KV-profile network · human evaluation repetition | repetition score: 2.07 -> 2.36 | Improved |
Closest papers by meaning
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue (ICLR 2020 · similarity 0.87)
- Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference (ICML 2023 · similarity 0.87)
- Improving Open-Domain Dialogue Response Generation with Multi-Source Multilingual Commonsense Knowledge (AAAI 2024 · similarity 0.85)
- Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State (NeurIPS 2026 · similarity 0.84)
- From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue (AAAI 2024 · similarity 0.84)
- StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning (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.
