Answering natural language queries over relational data often requires retrieving and reasoning over multiple tables, yet most retrievers optimize only for query-table relevance and ignore table table compatibility. We introduce REAR (Retrieve, Expand and Refine), a three-stage, LLM-free framework that separates semantic relevance from structural joinability for efficient, high-fidelity multi-table retrieval. REAR (i) retrieves query-aligned tables, (ii) expands these with structurally joinable tables via fast, precomputed column-embedding comparisons, and (iii) refines them by pruning noisy or weakly related candidates. Empirically, REAR is retriever-agnostic and consistently improves dense\/sparse retrievers on complex table QA datasets (BIRD, MMQA, and Spider) by improving both multi-table retrieval quality and downstream SQL execution. Despite being LLM-free, it delivers performance competitive with state-of-the-art LLM-augmented retrieval systems (e.g.,ARM) while achieving much lower latency and cost. Ablations confirm complementary gains from expansion and refinement, underscoring REAR as a practical, scalable building block for table-based downstream tasks (e.g., Text-to-SQL).<\/p>\n","protected":false},"excerpt":{"rendered":"
Answering natural language queries over relational data often requires retrieving and reasoning over multiple tables, yet most retrievers optimize only for query-table relevance and ignore table table compatibility. We introduce REAR (Retrieve, Expand and Refine), a three-stage, LLM-free framework that separates semantic relevance from structural joinability for efficient, high-fidelity multi-table retrieval. REAR (i) retrieves query-aligned […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"text","value":"Rishita Agarwal","user_id":0},{"type":"user_nicename","value":"Himanshu Singhal","user_id":"44249"},{"type":"text","value":"Peter Baile Chen","user_id":0},{"type":"text","value":"Manan Roy Choudhury","user_id":0},{"type":"text","value":"Dan Roth","user_id":0},{"type":"text","value":"Vivek Gupta","user_id":0}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"ACL 2026","msr_doi":"10.18653\/v1\/2026.acl-long.1826","msr_arxiv_id":"2511.00805","msr_mag_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_release_tracker_id":"","msr_highlight_type":"","msr_date_display_format":"","msr_main_download_label":"","msr_external_link_label":"","msr_doi_label":"","msr_published_date":"2026-07-02","msr_startdate":"","msr_presentation_date":"","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_year":2026,"msr_month":7,"msr_day":2,"msr_microsoftintellectualproperty":false,"msr_pub_id":"e48b3d1aa5cb9d5ce0e10d6820148cf52c14a9a9","msr_publication_uploader":[{"type":"url","title":"https:\/\/doi.org\/10.18653\/v1\/2026.acl-long.1826","label_id":243106,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/aclanthology.org\/2026.acl-long.1826\/","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_original_fields_of_study":[],"msr_s2_paper_id":"","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[{"provider":"s2","id":"e48b3d1aa5cb9d5ce0e10d6820148cf52c14a9a9"},{"provider":"doi","id":"10.48550\/arXiv.2511.00805"},{"provider":"arxiv","id":"2511.00805"},{"provider":"dblp","id":"journals\/corr\/abs-2511-00805"},{"provider":"corpusid","id":"282738902"}],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556,13555],"msr-publication-type":[193716],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[243594,243676],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[257968,248503],"msr-conference":[259084],"msr-journal":[268188],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1178712","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-search-information-retrieval","msr-focus-area-natural-language-processing","msr-focus-area-search-indexing","msr-locale-en_us","msr-field-of-study-efficiency","msr-field-of-study-information-retrieval"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2026-07-02","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"10.18653\/v1\/2026.acl-long.1826","msr_publication_uploader":[{"type":"url","title":"https:\/\/doi.org\/10.18653\/v1\/2026.acl-long.1826","label_id":243106,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/aclanthology.org\/2026.acl-long.1826\/","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"2511.00805","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Rishita Agarwal","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Himanshu Singhal","user_id":44249,"rest_url":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Himanshu Singhal"},{"type":"text","value":"Peter Baile Chen","user_id":0,"rest_url":false},{"type":"text","value":"Manan Roy Choudhury","user_id":0,"rest_url":false},{"type":"text","value":"Dan Roth","user_id":0,"rest_url":false},{"type":"text","value":"Vivek Gupta","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1178712","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":3,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1178712\/revisions"}],"predecessor-version":[{"id":1178718,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1178712\/revisions\/1178718"}],"wp:attachment":[{"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1178712"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1178712"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1178712"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1178712"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1178712"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1178712"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1178712"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1178712"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1178712"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1178712"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1178712"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1178712"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1178712"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/find.codeghost.online\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1178712"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}