Papers › Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and...
Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning
Yuxin Jiang, Linhan Zhang, Wei Wang
Contrastive learning has been demonstrated to be effective in enhancing pre-trained language models (PLMs) to derive superior universal sentence embeddings. However, existing contrastive methods still have two limitations. Firstly, previous works may acquire poor performance under domain shift settings, thus hindering the application of sentence representations in practice. We attribute this low performance to the over-parameterization of PLMs with millions of parameters. To alleviate it, we propose PromCSE (Prompt-based Contrastive Learning for Sentence Embeddings), which only trains small-scale \emph{Soft Prompt} (i.e., a set of trainable vectors) while keeping PLMs fixed. Secondly, the commonly used NT-Xent loss function of contrastive learning does not fully exploit hard negatives in supervised learning settings. To this end, we propose to integrate an Energy-based Hinge loss to enhance the pairwise discriminative power, inspired by the connection between the NT-Xent loss and the Energy-based Learning paradigm. Empirical results on seven standard semantic textual similarity (STS) tasks and a domain-shifted STS task both show the effectiveness of our method compared with the current state-of-the-art sentence embedding models. Our code is publicly avaliable at https://github.com/YJiangcm/PromCSE
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 |
|---|---|---|---|---|---|---|---|
| Semantic Textual Similarity | CxC | PromCSE-RoBERTa-large (0.355B) | avg ± std | 74.8± 1.0 | #1 of 4 | Archive leaderboard | report |
| Semantic Textual Similarity | SICK | PromCSE-RoBERTa-large (0.355B) | Spearman Correlation | 0.8243 | #1 of 22 | Archive leaderboard | report |
| Semantic Textual Similarity | STS Benchmark | PromCSE-RoBERTa-large (0.355B) | Spearman Correlation | 0.8787 | #38 of 66 | Archive leaderboard | report |
| Semantic Textual Similarity | STS12 | PromCSE-RoBERTa-large (0.355B) | Spearman Correlation | 0.7956 | #3 of 20 | Archive leaderboard | report |
| Semantic Textual Similarity | STS13 | PromCSE-RoBERTa-large (0.355B) | Spearman Correlation | 0.8897 | #6 of 22 | Archive leaderboard | report |
| Semantic Textual Similarity | STS14 | PromCSE-RoBERTa-large (0.355B) | Spearman Correlation | 0.8381 | #7 of 21 | Archive leaderboard | report |
| Semantic Textual Similarity | STS15 | PromCSE-RoBERTa-large (0.355B) | Spearman Correlation | 0.8808 | #8 of 20 | Archive leaderboard | report |
| Semantic Textual Similarity | STS16 | PromCSE-RoBERTa-large (0.355B) | Spearman Correlation | 0.8496 | #8 of 20 | 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