{"id":"https://openalex.org/W7166809932","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.24","title":"More Than Efficiency: Embedding Compression Improves Domain Adaptation in Dense Retrieval","display_name":"More Than Efficiency: Embedding Compression Improves Domain Adaptation in Dense Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166809932","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.24"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.surgellm-1.24","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.24","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.surgellm-1.24","pdf_url":"https://aclanthology.org/2026.surgellm-1.24.pdf","source":{"id":"https://openalex.org/S7407121045","display_name":"Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.surgellm-1.24.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093917254","display_name":"Chunsheng Zuo","orcid":"https://orcid.org/0009-0000-4988-2401","observed_orcids":["https://orcid.org/0009-0000-4988-2401"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunsheng Zuo","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043628255","display_name":"Daniel Khashabi","orcid":"https://orcid.org/0009-0009-7664-2230","observed_orcids":["https://orcid.org/0009-0009-7664-2230"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Khashabi","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":21.3461,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99211347,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6820999979972839,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.6820999979972839,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2705000042915344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.028699999675154686,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.8420000076293945},{"id":"https://openalex.org/keywords/dense-retrieval","display_name":"dense retrieval","score":0.9789999723434448},{"id":"https://openalex.org/keywords/embedding-compression","display_name":"embedding compression","score":0.9509999752044678},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"principal component analysis","score":0.9390000104904175},{"id":"https://openalex.org/keywords/query-embedding","display_name":"query embedding","score":0.9549999833106995},{"id":"https://openalex.org/keywords/pre-trained-embeddings","display_name":"pre-trained embeddings","score":0.6579999923706055},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"document retrieval","score":0.7200000286102295},{"id":"https://openalex.org/keywords/mteb-benchmark","display_name":"MTEB benchmark","score":0.671999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5461999773979187},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5297999978065491},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39629998803138733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3797000050544739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.surgellm-1.24","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.24","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.surgellm-1.24","pdf_url":"https://aclanthology.org/2026.surgellm-1.24.pdf","source":{"id":"https://openalex.org/S7407121045","display_name":"Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.surgellm-1.24","doi":"https://doi.org/10.18653/v1/2026.surgellm-1.24","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.surgellm-1.24","pdf_url":"https://aclanthology.org/2026.surgellm-1.24.pdf","source":{"id":"https://openalex.org/S7407121045","display_name":"Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the LLM Era (SURGeLLM 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166809932.pdf","grobid_xml":"https://content.openalex.org/works/W7166809932.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7077869830","https://openalex.org/W4389520221","https://openalex.org/W4281493120","https://openalex.org/W4291238844","https://openalex.org/W4303684020","https://openalex.org/W4406841034","https://openalex.org/W4311556096","https://openalex.org/W7138879855","https://openalex.org/W7151516777","https://openalex.org/W7131783209"],"abstract_inverted_index":{"Dense":[0],"retrievers":[1,80],"powered":[2],"by":[3],"pretrained":[4],"embeddings":[5,49,90],"are":[6],"widely":[7],"used":[8,63],"for":[9,64,104],"document":[10],"retrieval":[11,76],"but":[12],"struggle":[13],"in":[14,93],"specialized":[15],"domains":[16],"due":[17],"to":[18,47,50,88],"the":[19,22],"mismatches":[20],"between":[21],"training":[23],"and":[24,33,81,101],"target":[25],"domain":[26,48,105],"distributions.Domain":[27],"adaptation":[28],"typically":[29],"requires":[30],"costly":[31],"annotation":[32],"retraining":[34],"of":[35,95],"query-document":[36],"pairs.In":[37],"this":[38,69],"work,":[39],"we":[40,66],"revisit":[41],"an":[42],"overlooked":[43],"alternative:":[44],"applying":[45],"PCA":[46,85],"derive":[51],"lower-dimensional":[52],"representations":[53],"that":[54,68],"preserve":[55],"domain-relevant":[56],"features":[57],"while":[58],"discarding":[59],"non-discriminative":[60],"components.Though":[61],"traditionally":[62],"efficiency,":[65],"demonstrate":[67],"simple":[70,100],"embedding":[71],"compression":[72],"can":[73],"effectively":[74],"improve":[75],"performance.Evaluated":[77],"across":[78],"9":[79],"14":[82],"MTEB":[83],"datasets,":[84],"applied":[86],"solely":[87],"query":[89],"improves":[91],"NDCG@10":[92],"75.4%":[94],"modeldataset":[96],"pairs,":[97],"offering":[98],"a":[99],"lightweight":[102],"method":[103],"adaptation.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}