{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/deep-continuous-prompt-for-contrastive-1","title":"Improved Universal Sentence Embeddings with Prompt-based Contrastive Learning and Energy-based Learning","arxiv_id":"2203.06875","date":"2022-03-14","proceeding":null,"authors":["Yuxin Jiang","Linhan Zhang","Wei Wang"],"abstract":"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","url_abs":"https://arxiv.org/abs/2203.06875v2","url_pdf":"https://arxiv.org/pdf/2203.06875v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-continuous-prompt-for-contrastive-1","repo_url":"https://github.com/yjiangcm/promcse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"sts","task_name":"STS"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"nt-xent","method_name":"NT-Xent"},{"method_slug":"simcse","method_name":"SimCSE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-textual-similarity-on-cxc","task":"Semantic Textual Similarity","dataset":"CxC","model":"PromCSE-RoBERTa-large (0.355B)","rank_in_archive_order":1,"of":4,"metrics":{"avg ± std":"74.8± 1.0"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sick","task":"Semantic Textual Similarity","dataset":"SICK","model":"PromCSE-RoBERTa-large (0.355B)","rank_in_archive_order":1,"of":22,"metrics":{"Spearman Correlation":"0.8243"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"PromCSE-RoBERTa-large (0.355B)","rank_in_archive_order":38,"of":66,"metrics":{"Spearman Correlation":"0.8787"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts12","task":"Semantic Textual Similarity","dataset":"STS12","model":"PromCSE-RoBERTa-large (0.355B)","rank_in_archive_order":3,"of":20,"metrics":{"Spearman Correlation":"0.7956"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts13","task":"Semantic Textual Similarity","dataset":"STS13","model":"PromCSE-RoBERTa-large (0.355B)","rank_in_archive_order":6,"of":22,"metrics":{"Spearman Correlation":"0.8897"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts14","task":"Semantic Textual Similarity","dataset":"STS14","model":"PromCSE-RoBERTa-large (0.355B)","rank_in_archive_order":7,"of":21,"metrics":{"Spearman Correlation":"0.8381"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts15","task":"Semantic Textual Similarity","dataset":"STS15","model":"PromCSE-RoBERTa-large (0.355B)","rank_in_archive_order":8,"of":20,"metrics":{"Spearman Correlation":"0.8808"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts16","task":"Semantic Textual Similarity","dataset":"STS16","model":"PromCSE-RoBERTa-large (0.355B)","rank_in_archive_order":8,"of":20,"metrics":{"Spearman Correlation":"0.8496"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.06875","atlas_url":"https://app.syntology.ai/?focus=2203.06875","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2203.06875"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.06875\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.06875"},"call":"get_concepts_for_paper(arxiv_id=\"2203.06875\")"}],"by_repo":[{"repo":"yjiangcm/promcse","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1908.10084"],"harvested_for_calls":[{"arxiv_id":"1908.10084","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1908.10084"},"call":"get_harvested_code_for_paper(arxiv_id=\"1908.10084\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0b97299c24484d8d9a8a22e63a94b3df619d784b1897795ead0a2ec3059078b2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}