{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/little-giants-synthesizing-high-quality","title":"Little Giants: Synthesizing High-Quality Embedding Data at Scale","arxiv_id":"2410.18634","date":"2024-10-24","proceeding":null,"authors":["Haonan Chen","Liang Wang","Nan Yang","Yutao Zhu","Ziliang Zhao","Furu Wei","Zhicheng Dou"],"abstract":"Synthetic data generation has become an increasingly popular way of training models without the need for large, manually labeled datasets. For tasks like text embedding, synthetic data offers diverse and scalable training examples, significantly reducing the cost of human annotation. However, most current approaches rely heavily on proprietary models like GPT-4, which are expensive and inefficient for generating large-scale embedding data. In this paper, we introduce SPEED, a framework that aligns open-source small models (8B) to efficiently generate large-scale synthetic embedding data. Through supervised fine-tuning, preference optimization, and self-improvement, SPEED enables small open-source models to produce high-quality data. Remarkably, SPEED uses only less than 1/10 of the GPT API calls, outperforming the state-of-the-art embedding model E5_mistral when both are trained solely on their synthetic data. Using this efficient generator, we conduct a comprehensive study on how various factors within the alignment pipeline impact data quality and reveal the scaling law for synthetic embedding data.","url_abs":"https://arxiv.org/abs/2410.18634v2","url_pdf":"https://arxiv.org/pdf/2410.18634v2.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":"little-giants-synthesizing-high-quality","repo_url":"https://github.com/haon-chen/SPEED","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.18634","atlas_url":"https://app.syntology.ai/?focus=2410.18634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18634"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/haon-chen/SPEED","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"83a8f71b8b7b680b","entry":"extract_first_json","repo":"haon-chen/SPEED","repo_kind":"official","path":"utils.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83a8f71b8b7b680b"}},{"code_sha256_prefix":"9c3b4aa57aec9ac7","entry":"extract_innermost_json","repo":"haon-chen/SPEED","repo_kind":"official","path":"utils.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9c3b4aa57aec9ac7"}},{"code_sha256_prefix":"edb132d24082dccb","entry":"fix_common_json_errors_and_loads","repo":"haon-chen/SPEED","repo_kind":"official","path":"utils.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"edb132d24082dccb"}},{"code_sha256_prefix":"1dbde3bd8af6325a","entry":"get_brainstorm_classify_tasks_prompt_with_topic","repo":"haon-chen/SPEED","repo_kind":"official","path":"prompts_tasks.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/prompts_tasks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1dbde3bd8af6325a"}},{"code_sha256_prefix":"30c186e2f12fbdd3","entry":"get_brainstorm_retrieval_tasks_prompt_with_topic_ICL","repo":"haon-chen/SPEED","repo_kind":"official","path":"prompts_tasks.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/prompts_tasks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"30c186e2f12fbdd3"}},{"code_sha256_prefix":"dbcb6e8909c91a41","entry":"get_brainstorm_s2s_tasks_prompt_with_topic","repo":"haon-chen/SPEED","repo_kind":"official","path":"prompts_tasks.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/prompts_tasks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dbcb6e8909c91a41"}},{"code_sha256_prefix":"08099b8533ba7d63","entry":"get_create_all_revise_data_prompt","repo":"haon-chen/SPEED","repo_kind":"official","path":"prompts_aligning.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/prompts_aligning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08099b8533ba7d63"}},{"code_sha256_prefix":"61fab83334f5a653","entry":"get_create_classify_data_prompt","repo":"haon-chen/SPEED","repo_kind":"official","path":"prompts_synthesis.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/prompts_synthesis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61fab83334f5a653"}},{"code_sha256_prefix":"d08b9bbc29efb49d","entry":"get_create_dpo_data_prompt","repo":"haon-chen/SPEED","repo_kind":"official","path":"prompts_aligning.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/prompts_aligning.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d08b9bbc29efb49d"}},{"code_sha256_prefix":"bdb4e35a652580f3","entry":"get_create_retrieval_data_prompt","repo":"haon-chen/SPEED","repo_kind":"official","path":"prompts_synthesis.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/prompts_synthesis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdb4e35a652580f3"}},{"code_sha256_prefix":"2a35be1618a3b7ed","entry":"get_sts_prompt_with_topic","repo":"haon-chen/SPEED","repo_kind":"official","path":"prompts_synthesis.py","file_url":"https://github.com/haon-chen/SPEED/blob/HEAD/prompts_synthesis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a35be1618a3b7ed"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}