Papers › Small Changes Make Big Differences: Improving Multi-turn Response Selection in...
Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning
Yuntao Li, Can Xu, Huang Hu, Lei Sha, Yan Zhang, Daxin Jiang
Retrieve-based dialogue response selection aims to find a proper response from a candidate set given a multi-turn context. Pre-trained language models (PLMs) based methods have yielded significant improvements on this task. The sequence representation plays a key role in the learning of matching degree between the dialogue context and the response. However, we observe that different context-response pairs sharing the same context always have a greater similarity in the sequence representations calculated by PLMs, which makes it hard to distinguish positive responses from negative ones. Motivated by this, we propose a novel \textbf{F}ine-\textbf{G}rained \textbf{C}ontrastive (FGC) learning method for the response selection task based on PLMs. This FGC learning strategy helps PLMs to generate more distinguishable matching representations of each dialogue at fine grains, and further make better predictions on choosing positive responses. Empirical studies on two benchmark datasets demonstrate that the proposed FGC learning method can generally and significantly improve the model performance of existing PLM-based matching models.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 |
|---|---|---|---|---|---|---|---|
| Conversational Response Selection | Ubuntu Dialogue (v1, Ranking) | BERT-UMS+FGC | R10@1 | 0.886 | #5 of 25 | Archive leaderboard | report |
| Conversational Response Selection | Ubuntu Dialogue (v1, Ranking) | BERT-UMS+FGC | R10@2 | 0.948 | #5 of 25 | Archive leaderboard | report |
| Conversational Response Selection | Ubuntu Dialogue (v1, Ranking) | BERT-UMS+FGC | R10@5 | 0.990 | #5 of 25 | 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.
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