Large language models (LLMs) are increasingly deployed for enterprise information extraction (IE), where the same document must be reorganized differently for each user. Existing prompt optimization methods, however, rely on a single prompt optimized against a global objective, which is misaligned with the inherent user heterogeneity of real workplaces. We formulate enterprise IE as per-user prompt adaptation under interaction feedback and propose Self-Meta-Evolve, a hierarchical framework that maintains a dedicated prompt for each user and continuously refines it through a dual-loop process: an inner loop that edits structured prompts based on persona-conditioned feedback, and an outer loop that evolves the meta-prompt itself by distilling successful editing patterns. To enable scalable training and evaluation, we release a persona-driven IE benchmark of 292 simulated enterprise users, paired with a reproducible persona-generation pipeline grounded in O*NET occupational taxonomies. On this benchmark, Self-Meta-Evolve achieves a 74.58% success rate, outperforming the strongest prompt-optimization baseline by 13.56 absolute points, and reaches 52.54% within only two iterations. A double-blind human study with twenty real professionals further confirms that prompts adapted by our framework win against static baselines in 71% of pairwise comparisons.<\/p>\n","protected":false},"excerpt":{"rendered":"
Large language models (LLMs) are increasingly deployed for enterprise information extraction (IE), where the same document must be reorganized differently for each user. Existing prompt optimization methods, however, rely on a single prompt optimized against a global objective, which is misaligned with the inherent user heterogeneity of real workplaces. We formulate enterprise IE as per-user […]<\/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":"user_nicename","value":"Hongliang Li","user_id":"32024"},{"type":"user_nicename","value":"Lu Wang","user_id":"44027"},{"type":"user_nicename","value":"Yong Xu","user_id":"37125"},{"type":"text","value":"Hanyang Chen","user_id":0},{"type":"user_nicename","value":"Zhitao Hou","user_id":"35124"},{"type":"user_nicename","value":"Xiaoting Qin","user_id":"43008"},{"type":"user_nicename","value":"Song Ge","user_id":"33692"},{"type":"user_nicename","value":"Qingwei Lin \u6797\u5e86\u7ef4","user_id":"33318"},{"type":"user_nicename","value":"Dongmei Zhang","user_id":"31665"}],"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":"AACL","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"AACL-IJCNLP 2026","msr_doi":"","msr_arxiv_id":"2609.21626","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":"2026-09-18","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":9,"msr_day":18,"msr_microsoftintellectualproperty":false,"msr_pub_id":"798e210d2df89be68fadcb8084ffc0c24a0a5de3","msr_publication_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2609.21626","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_original_fields_of_study":[],"msr_s2_paper_id":"798e210d2df89be68fadcb8084ffc0c24a0a5de3","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":57,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[{"provider":"s2","id":"798e210d2df89be68fadcb8084ffc0c24a0a5de3"},{"provider":"arxiv","id":"2609.21626"},{"provider":"corpusid","id":"292197451"}],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556,13545],"msr-publication-type":[193716],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[256039,246691],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1189068","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-locale-en_us","msr-field-of-study-artifcial-intelligence","msr-field-of-study-computer-science"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2026-09-18","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":"AACL","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":"","msr_publication_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2609.21626","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"798e210d2df89be68fadcb8084ffc0c24a0a5de3","msr_influential_citations":0,"msr_reference_count":57,"msr_arxiv_id":"2609.21626","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Hongliang Li","user_id":32024,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Hongliang Li"},{"type":"user_nicename","value":"Lu Wang","user_id":44027,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Lu Wang"},{"type":"user_nicename","value":"Yong Xu","user_id":37125,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Yong Xu"},{"type":"text","value":"Hanyang Chen","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Zhitao Hou","user_id":35124,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Zhitao Hou"},{"type":"user_nicename","value":"Xiaoting Qin","user_id":43008,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Xiaoting Qin"},{"type":"user_nicename","value":"Song Ge","user_id":33692,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Song Ge"},{"type":"user_nicename","value":"Qingwei Lin \u6797\u5e86\u7ef4","user_id":33318,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Qingwei Lin \u6797\u5e86\u7ef4"},{"type":"user_nicename","value":"Dongmei Zhang","user_id":31665,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Dongmei Zhang"}],"msr_impact_theme":[],"msr_research_lab":[199560,1012650],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1189068","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":4,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1189068\/revisions"}],"predecessor-version":[{"id":1190252,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1189068\/revisions\/1190252"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1189068"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1189068"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1189068"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1189068"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1189068"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1189068"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1189068"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1189068"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1189068"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1189068"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1189068"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1189068"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1189068"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1189068"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}