Papers › A Unified Pre-training Framework for Conversational AI
A Unified Pre-training Framework for Conversational AI
Siqi Bao, Bingjin Chen, Huang He, Xin Tian, Han Zhou, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Yingzhan Lin
In this work, we explore the application of PLATO-2 on various dialogue systems, including open-domain conversation, knowledge grounded dialogue, and task-oriented conversation. PLATO-2 is initially designed as an open-domain chatbot, trained via two-stage curriculum learning. In the first stage, a coarse-grained response generation model is learned to fit the simplified one-to-one mapping relationship. This model is applied to the task-oriented conversation, given that the semantic mappings tend to be deterministic in task completion. In the second stage, another fine-grained generation model and an evaluation model are further learned for diverse response generation and coherence estimation, respectively. With superior capability on capturing one-to-many mapping, such models are suitable for the open-domain conversation and knowledge grounded dialogue. For the comprehensive evaluation of PLATO-2, we have participated in multiple tasks of DSTC9, including interactive evaluation of open-domain conversation (Track3-task2), static evaluation of knowledge grounded dialogue (Track3-task1), and end-to-end task-oriented conversation (Track2-task1). PLATO-2 has obtained the 1st place in all three tasks, verifying its effectiveness as a unified framework for various dialogue systems.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Coherent | 2.8017 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Consistent | 0.9390 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Diversity | 2.7441 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Error Recovery | 2.7518 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Flexible | 2.8000 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Informative | 2.7881 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Inquisitive | 2.7949 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Likeable | 2.7878 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Overall Human Rating | 4.15 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Topic Depth | 2.7678 | #1 of 1 | Archive leaderboard | report |
| Interactive Evaluation of Dialog | DSTC9 Track 3 - Task 2 | PLATO-2 | Understanding | 2.8285 | #1 of 1 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections