A Socratic RAG Approach to Connect Natural Language Queries on Research Topics with Knowledge Organization Systems. Lefton, L., Rong, K., Dankhara, C., Ghemri, L., Kausar, F., & Hamdallahi, A. H. February, 2025. arXiv:2502.15005 [cs]![A Socratic RAG Approach to Connect Natural Language Queries on Research Topics with Knowledge Organization Systems [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex In this paper, we propose a Retrieval Augmented Generation (RAG) agent that maps natural language queries about research topics to precise, machine-interpretable semantic entities. Our approach combines RAG with Socratic dialogue to align a user's intuitive understanding of research topics with established Knowledge Organization Systems (KOSs). The proposed approach will effectively bridge "little semantics" (domain-specific KOS structures) with "big semantics" (broad bibliometric repositories), making complex academic taxonomies more accessible. Such agents have the potential for broad use. We illustrate with a sample application called CollabNext, which is a person-centric knowledge graph connecting people, organizations, and research topics. We further describe how the application design has an intentional focus on HBCUs and emerging researchers to raise visibility of people historically rendered invisible in the current science system.
@misc{lefton_socratic_2025,
title = {A {Socratic} {RAG} {Approach} to {Connect} {Natural} {Language} {Queries} on {Research} {Topics} with {Knowledge} {Organization} {Systems}},
url = {http://arxiv.org/abs/2502.15005},
doi = {10.48550/arXiv.2502.15005},
abstract = {In this paper, we propose a Retrieval Augmented Generation (RAG) agent that maps natural language queries about research topics to precise, machine-interpretable semantic entities. Our approach combines RAG with Socratic dialogue to align a user's intuitive understanding of research topics with established Knowledge Organization Systems (KOSs). The proposed approach will effectively bridge "little semantics" (domain-specific KOS structures) with "big semantics" (broad bibliometric repositories), making complex academic taxonomies more accessible. Such agents have the potential for broad use. We illustrate with a sample application called CollabNext, which is a person-centric knowledge graph connecting people, organizations, and research topics. We further describe how the application design has an intentional focus on HBCUs and emerging researchers to raise visibility of people historically rendered invisible in the current science system.},
urldate = {2025-03-04},
publisher = {arXiv},
author = {Lefton, Lew and Rong, Kexin and Dankhara, Chinar and Ghemri, Lila and Kausar, Firdous and Hamdallahi, A. Hannibal},
month = feb,
year = {2025},
note = {arXiv:2502.15005 [cs]},
keywords = {Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Human-Computer Interaction},
}
Downloads: 0
{"_id":"34D4hZHhFvCxdnJZ2","bibbaseid":"lefton-rong-dankhara-ghemri-kausar-hamdallahi-asocraticragapproachtoconnectnaturallanguagequeriesonresearchtopicswithknowledgeorganizationsystems-2025","author_short":["Lefton, L.","Rong, K.","Dankhara, C.","Ghemri, L.","Kausar, F.","Hamdallahi, A. H."],"bibdata":{"bibtype":"misc","type":"misc","title":"A Socratic RAG Approach to Connect Natural Language Queries on Research Topics with Knowledge Organization Systems","url":"http://arxiv.org/abs/2502.15005","doi":"10.48550/arXiv.2502.15005","abstract":"In this paper, we propose a Retrieval Augmented Generation (RAG) agent that maps natural language queries about research topics to precise, machine-interpretable semantic entities. Our approach combines RAG with Socratic dialogue to align a user's intuitive understanding of research topics with established Knowledge Organization Systems (KOSs). The proposed approach will effectively bridge \"little semantics\" (domain-specific KOS structures) with \"big semantics\" (broad bibliometric repositories), making complex academic taxonomies more accessible. Such agents have the potential for broad use. We illustrate with a sample application called CollabNext, which is a person-centric knowledge graph connecting people, organizations, and research topics. We further describe how the application design has an intentional focus on HBCUs and emerging researchers to raise visibility of people historically rendered invisible in the current science system.","urldate":"2025-03-04","publisher":"arXiv","author":[{"propositions":[],"lastnames":["Lefton"],"firstnames":["Lew"],"suffixes":[]},{"propositions":[],"lastnames":["Rong"],"firstnames":["Kexin"],"suffixes":[]},{"propositions":[],"lastnames":["Dankhara"],"firstnames":["Chinar"],"suffixes":[]},{"propositions":[],"lastnames":["Ghemri"],"firstnames":["Lila"],"suffixes":[]},{"propositions":[],"lastnames":["Kausar"],"firstnames":["Firdous"],"suffixes":[]},{"propositions":[],"lastnames":["Hamdallahi"],"firstnames":["A.","Hannibal"],"suffixes":[]}],"month":"February","year":"2025","note":"arXiv:2502.15005 [cs]","keywords":"Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Human-Computer Interaction","bibtex":"@misc{lefton_socratic_2025,\n\ttitle = {A {Socratic} {RAG} {Approach} to {Connect} {Natural} {Language} {Queries} on {Research} {Topics} with {Knowledge} {Organization} {Systems}},\n\turl = {http://arxiv.org/abs/2502.15005},\n\tdoi = {10.48550/arXiv.2502.15005},\n\tabstract = {In this paper, we propose a Retrieval Augmented Generation (RAG) agent that maps natural language queries about research topics to precise, machine-interpretable semantic entities. Our approach combines RAG with Socratic dialogue to align a user's intuitive understanding of research topics with established Knowledge Organization Systems (KOSs). The proposed approach will effectively bridge \"little semantics\" (domain-specific KOS structures) with \"big semantics\" (broad bibliometric repositories), making complex academic taxonomies more accessible. Such agents have the potential for broad use. We illustrate with a sample application called CollabNext, which is a person-centric knowledge graph connecting people, organizations, and research topics. We further describe how the application design has an intentional focus on HBCUs and emerging researchers to raise visibility of people historically rendered invisible in the current science system.},\n\turldate = {2025-03-04},\n\tpublisher = {arXiv},\n\tauthor = {Lefton, Lew and Rong, Kexin and Dankhara, Chinar and Ghemri, Lila and Kausar, Firdous and Hamdallahi, A. Hannibal},\n\tmonth = feb,\n\tyear = {2025},\n\tnote = {arXiv:2502.15005 [cs]},\n\tkeywords = {Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Human-Computer Interaction},\n}\n\n","author_short":["Lefton, L.","Rong, K.","Dankhara, C.","Ghemri, L.","Kausar, F.","Hamdallahi, A. H."],"key":"lefton_socratic_2025","id":"lefton_socratic_2025","bibbaseid":"lefton-rong-dankhara-ghemri-kausar-hamdallahi-asocraticragapproachtoconnectnaturallanguagequeriesonresearchtopicswithknowledgeorganizationsystems-2025","role":"author","urls":{"Paper":"http://arxiv.org/abs/2502.15005"},"keyword":["Computer Science - Artificial Intelligence","Computer Science - Computation and Language","Computer Science - Human-Computer Interaction"],"metadata":{"authorlinks":{}}},"bibtype":"misc","biburl":"https://api.zotero.org/groups/4790165/items?key=qWYUkNg8G2tSrs1m5i7SsKOn&format=bibtex&limit=100","dataSources":["txmtuJDjhqHfaZE3C","wkZmECJAmJTTcjXCL","ttiB3rxTuWH3fiHv3","XooGe8m5uEyMY8yz7"],"keywords":["computer science - artificial intelligence","computer science - computation and language","computer science - human-computer interaction"],"search_terms":["socratic","rag","approach","connect","natural","language","queries","research","topics","knowledge","organization","systems","lefton","rong","dankhara","ghemri","kausar","hamdallahi"],"title":"A Socratic RAG Approach to Connect Natural Language Queries on Research Topics with Knowledge Organization Systems","year":2025}