{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:40:57Z","timestamp":1771267257976,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,2,22]]},"DOI":"10.1145\/3773966.3779394","type":"proceedings-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:50:01Z","timestamp":1771264201000},"page":"1216-1220","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge Homophily in Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3596-2996","authenticated-orcid":false,"given":"Utkarsh","family":"Sahu","sequence":"first","affiliation":[{"name":"University of Oregon, Eugene, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4961-8223","authenticated-orcid":false,"given":"Zhisheng","family":"Qi","sequence":"additional","affiliation":[{"name":"University of Oregon, Eugene, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2323-4753","authenticated-orcid":false,"given":"Mahantesh","family":"Halappanavar","sequence":"additional","affiliation":[{"name":"Pacific Northwest National Laboratory, Richland, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3779-7784","authenticated-orcid":false,"given":"Nedim","family":"Lipka","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9758-0635","authenticated-orcid":false,"given":"Ryan","family":"Rossi","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1119-1346","authenticated-orcid":false,"given":"Franck","family":"Dernoncourt","sequence":"additional","affiliation":[{"name":"Adobe Research, San Jose, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0540-6758","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Texas A&M University, College Station, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4985-8724","authenticated-orcid":false,"given":"Yao","family":"Ma","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6908-508X","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Oregon, Eugene, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"A review on language models as knowledge bases. arXiv","author":"AlKhamissi Badr","year":"2022","unstructured":"Badr AlKhamissi, Millicent Li, Asli Celikyilmaz, Mona Diab, and Marjan Ghazvininejad. 2022. A review on language models as knowledge bases. arXiv (2022)."},{"key":"e_1_3_2_1_2_1","volume-title":"An analysis of sequences of restricted associative responses. The Journal of General Psychology","author":"Bousfield Weston A","year":"1944","unstructured":"Weston A Bousfield and Charles Hill W Sedgewick. 1944. An analysis of sequences of restricted associative responses. The Journal of General Psychology (1944)."},{"key":"e_1_3_2_1_3_1","volume-title":"Knowledge neurons in pretrained transformers. arXiv preprint","author":"Dai Damai","year":"2021","unstructured":"Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, and Furu Wei. 2021. Knowledge neurons in pretrained transformers. arXiv preprint (2021)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Elsahar Hady","year":"2018","unstructured":"Hady Elsahar, Pavlos Vougiouklis, Arslen Remaci, Christophe Gravier, Jonathon Hare, Frederique Laforest, and Elena Simperl. 2018. T-rex: A large scale alignment of natural language with knowledge base triples. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)."},{"key":"e_1_3_2_1_5_1","volume-title":"Message passing for hyper-relational knowledge graphs. arXiv preprint arXiv:2009.10847","author":"Galkin Mikhail","year":"2020","unstructured":"Mikhail Galkin, Priyansh Trivedi, Gaurav Maheshwari, Ricardo Usbeck, and Jens Lehmann. 2020. Message passing for hyper-relational knowledge graphs. arXiv preprint arXiv:2009.10847 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Transformer feed-forward layers are key-value memories. arXiv preprint","author":"Geva Mor","year":"2020","unstructured":"Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. 2020. Transformer feed-forward layers are key-value memories. arXiv preprint (2020)."},{"key":"e_1_3_2_1_7_1","unstructured":"Haoyu Han Yu Wang Harry Shomer Kai Guo Jiayuan Ding Yongjia Lei Mahantesh Halappanavar Ryan A Rossi Subhabrata Mukherjee Xianfeng Tang et al. 2024. Retrieval-augmented generation with graphs (graphrag). arXiv preprint arXiv:2501.00309 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)."},{"key":"e_1_3_2_1_9_1","volume-title":"a continuous graph layout algorithm for handy network visualization designed for the Gephi software. PloS one","author":"Jacomy Mathieu","year":"2014","unstructured":"Mathieu Jacomy, Tommaso Venturini, Sebastien Heymann, and Mathieu Bastian. 2014. ForceAtlas2, a continuous graph layout algorithm for handy network visualization designed for the Gephi software. PloS one (2014)."},{"key":"e_1_3_2_1_10_1","unstructured":"Saurav Kadavath Tom Conerly Amanda Askell Tom Henighan Dawn Drain Ethan Perez Nicholas Schiefer Zac Hatfield-Dodds Nova DasSarma Eli Tran-Johnson et al. 2022. Language models (mostly) know what they know. arXiv preprint arXiv:2207.05221 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases. arXiv preprint arXiv:2502.20317","author":"Lei Yongjia","year":"2025","unstructured":"Yongjia Lei, Haoyu Han, Ryan A Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M Halappanavar, Jiliang Tang, and Yu Wang. 2025. Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases. arXiv preprint arXiv:2502.20317 (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958","author":"Lin Stephanie","year":"2021","unstructured":"Stephanie Lin, Jacob Hilton, and Owain Evans. 2021. Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958 (2021)."},{"key":"e_1_3_2_1_13_1","unstructured":"Bang Liu Xinfeng Li Jiayi Zhang Jinlin Wang Tanjin He Sirui Hong Hongzhang Liu Shaokun Zhang Kaitao Song Kunlun Zhu et al. 2025. Advances and challenges in foundation agents: From brain-inspired intelligence to evolutionary collaborative and safe systems. arXiv preprint arXiv:2504.01990 (2025)."},{"key":"e_1_3_2_1_14_1","volume-title":"Systematic assessment of factual knowledge in large language models. arXiv preprint arXiv:2310.11638","author":"Luo Linhao","year":"2023","unstructured":"Linhao Luo, Thuy-Trang Vu, Dinh Phung, and Gholamreza Haffari. 2023. Systematic assessment of factual knowledge in large language models. arXiv preprint arXiv:2310.11638 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Is homophily a necessity for graph neural networks? ICLR","author":"Ma Yao","year":"2021","unstructured":"Yao Ma, Xiaorui Liu, Neil Shah, and Jiliang Tang. 2021. Is homophily a necessity for graph neural networks? ICLR (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. arXiv preprint","author":"Mallen Alex","year":"2022","unstructured":"Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Daniel Khashabi, and Hannaneh Hajishirzi. 2022. When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. arXiv preprint (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Interpreting semantic clustering effects in free recall. Memory","author":"Manning Jeremy R","year":"2012","unstructured":"Jeremy R Manning and Michael J Kahana. 2012. Interpreting semantic clustering effects in free recall. Memory (2012)."},{"key":"e_1_3_2_1_18_1","volume-title":"Locating and editing factual associations in gpt. Advances in neural information processing systems","author":"Meng Kevin","year":"2022","unstructured":"Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022. Locating and editing factual associations in gpt. Advances in neural information processing systems, Vol. 35 (2022), 17359-17372."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645616"},{"key":"e_1_3_2_1_20_1","volume-title":"Rethinking language models as symbolic knowledge graphs. arXiv preprint arXiv:2308.13676","author":"Mruthyunjaya Vishwas","year":"2023","unstructured":"Vishwas Mruthyunjaya, Pouya Pezeshkpour, Estevam Hruschka, and Nikita Bhutani. 2023. Rethinking language models as symbolic knowledge graphs. arXiv preprint arXiv:2308.13676 (2023)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA58977.2023.00122"},{"key":"e_1_3_2_1_23_1","volume-title":"Network structure from a characterization of interactions in complex systems. Scientific Reports","author":"Rings Thorsten","year":"2022","unstructured":"Thorsten Rings, Timo Br\u00f6hl, and Klaus Lehnertz. 2022. Network structure from a characterization of interactions in complex systems. Scientific Reports (2022)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.437"},{"key":"e_1_3_2_1_25_1","volume-title":"Codex: A comprehensive knowledge graph completion benchmark. arXiv preprint arXiv:2009.07810","author":"Safavi Tara","year":"2020","unstructured":"Tara Safavi and Danai Koutra. 2020. Codex: A comprehensive knowledge graph completion benchmark. arXiv preprint arXiv:2009.07810 (2020)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679722"},{"key":"e_1_3_2_1_27_1","volume-title":"Knowledge unlearning for llms: Tasks, methods, and challenges. arXiv preprint arXiv:2311.15766","author":"Si Nianwen","year":"2023","unstructured":"Nianwen Si, Hao Zhang, Heyu Chang, Wenlin Zhang, Dan Qu, and Weiqiang Zhang. 2023. Knowledge unlearning for llms: Tasks, methods, and challenges. arXiv preprint arXiv:2311.15766 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Graph-based semi-supervised learning: A comprehensive review","author":"Song Zixing","year":"2022","unstructured":"Zixing Song, Xiangli Yang, Zenglin Xu, and Irwin King. 2022. Graph-based semi-supervised learning: A comprehensive review. IEEE Transactions on Neural Networks and Learning Systems (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9266.001.0001"},{"key":"e_1_3_2_1_30_1","volume-title":"Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. arXiv preprint arXiv:2305.14975","author":"Tian Katherine","year":"2023","unstructured":"Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, and Christopher D Manning. 2023. Just ask for calibration: Strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. arXiv preprint arXiv:2305.14975 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Wikidata: a free collaborative knowledgebase. Commun. ACM","author":"Vrande\u010di\u0107 Denny","year":"2014","unstructured":"Denny Vrande\u010di\u0107 and Markus Kr\u00f6tzsch. 2014. Wikidata: a free collaborative knowledgebase. Commun. ACM (2014)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482487"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29889"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557356"},{"key":"e_1_3_2_1_35_1","volume-title":"Seakr: Self-aware knowledge retrieval for adaptive retrieval augmented generation. arXiv preprint arXiv:2406.19215","author":"Yao Zijun","year":"2024","unstructured":"Zijun Yao, Weijian Qi, Liangming Pan, Shulin Cao, Linmei Hu, Weichuan Liu, Lei Hou, and Juanzi Li. 2024. Seakr: Self-aware knowledge retrieval for adaptive retrieval augmented generation. arXiv preprint arXiv:2406.19215 (2024)."},{"key":"e_1_3_2_1_36_1","volume-title":"RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering. In Findings of the Association for Computational Linguistics ACL","author":"Zhang Zihan","year":"2024","unstructured":"Zihan Zhang, Meng Fang, and Ling Chen. 2024. RetrievalQA: Assessing Adaptive Retrieval-Augmented Generation for Short-form Open-Domain Question Answering. In Findings of the Association for Computational Linguistics ACL 2024."},{"key":"e_1_3_2_1_37_1","volume-title":"Large language models as reliable knowledge bases? arXiv preprint arXiv:2407.13578","author":"Zheng Danna","year":"2024","unstructured":"Danna Zheng, Mirella Lapata, and Jeff Z Pan. 2024. Large language models as reliable knowledge bases? arXiv preprint arXiv:2407.13578 (2024)."},{"key":"e_1_3_2_1_38_1","volume-title":"KGLens: Towards Efficient and Effective Knowledge Probing of Large Language Models with Knowledge Graphs. arXiv preprint","author":"Zheng Shangshang","year":"2023","unstructured":"Shangshang Zheng, He Bai, Yizhe Zhang, Yi Su, Xiaochuan Niu, and Navdeep Jaitly. 2023. KGLens: Towards Efficient and Effective Knowledge Probing of Large Language Models with Knowledge Graphs. arXiv preprint (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Yuedong Yang, and Zhangming Niu.","author":"Zheng Shuangjia","year":"2021","unstructured":"Shuangjia Zheng, Jiahua Rao, Ying Song, Jixian Zhang, Xianglu Xiao, Evandro Fei Fang, Yuedong Yang, and Zhangming Niu. 2021. PharmKG: a dedicated knowledge graph benchmark for bomedical data mining. Briefings in bioinformatics (2021)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17332"}],"event":{"name":"WSDM '26:The Nineteenth ACM International Conference on Web Search and Data Mining","location":"Boise ID USA","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T17:54:41Z","timestamp":1771264481000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773966.3779394"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":40,"alternative-id":["10.1145\/3773966.3779394","10.1145\/3773966"],"URL":"https:\/\/doi.org\/10.1145\/3773966.3779394","relation":{},"subject":[],"published":{"date-parts":[[2026,2,21]]},"assertion":[{"value":"2026-02-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}