{"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/drama-diverse-augmentation-from-large","title":"DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers","arxiv_id":"2502.18460","date":"2025-02-25","proceeding":null,"authors":["Xueguang Ma","Xi Victoria Lin","Barlas Oguz","Jimmy Lin","Wen-tau Yih","Xilun Chen"],"abstract":"Large language models (LLMs) have demonstrated strong effectiveness and robustness while fine-tuned as dense retrievers. However, their large parameter size brings significant inference time computational challenges, including high encoding costs for large-scale corpora and increased query latency, limiting their practical deployment. While smaller retrievers offer better efficiency, they often fail to generalize effectively with limited supervised fine-tuning data. In this work, we introduce DRAMA, a training framework that leverages LLMs to train smaller generalizable dense retrievers. In particular, we adopt pruned LLMs as the backbone and train on diverse LLM-augmented data in a single-stage contrastive learning setup. Experiments show that DRAMA offers better multilingual and long-context capabilities than traditional encoder-based retrievers, and achieves strong performance across multiple tasks and languages. These highlight the potential of connecting the training of smaller retrievers with the growing advancements in LLMs, bridging the gap between efficiency and generalization.","url_abs":"https://arxiv.org/abs/2502.18460v1","url_pdf":"https://arxiv.org/pdf/2502.18460v1.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":"drama-diverse-augmentation-from-large","repo_url":"https://github.com/facebookresearch/dpr-scale","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"adopt","method_name":"ADOPT"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.18460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.18460"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/facebookresearch/dpr-scale","reach":null}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"950270b8eff952f4","entry":"DPRDistillTask","repo":"facebookresearch/dpr-scale","repo_kind":"official","path":"dpr_scale/task/dpr_distill_task.py","file_url":"https://github.com/facebookresearch/dpr-scale/blob/HEAD/dpr_scale/task/dpr_distill_task.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"950270b8eff952f4"}},{"code_sha256_prefix":"5d7702a97fbee6f3","entry":"ScriptEncoder","repo":"facebookresearch/dpr-scale","repo_kind":"official","path":"dpr_scale/task/dpr_distill_task.py","file_url":"https://github.com/facebookresearch/dpr-scale/blob/HEAD/dpr_scale/task/dpr_distill_task.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5d7702a97fbee6f3"}},{"code_sha256_prefix":"7d9ea7f9bfbb2e6c","entry":"WrapTransform","repo":"facebookresearch/dpr-scale","repo_kind":"official","path":"dpr_scale/task/dpr_distill_task.py","file_url":"https://github.com/facebookresearch/dpr-scale/blob/HEAD/dpr_scale/task/dpr_distill_task.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d9ea7f9bfbb2e6c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}