{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T04:08:53Z","timestamp":1749787733780,"version":"3.41.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council of the Hong Kong SAR","award":["GRF 11217823"],"award-info":[{"award-number":["GRF 11217823"]}]},{"name":"Collaborative Research Fund","award":["C1042-23GF"],"award-info":[{"award-number":["C1042-23GF"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371411"],"award-info":[{"award-number":["62371411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"InnoHK initiative"},{"name":"InnoHK initiative, Government of the HKSAR"},{"name":"Laboratory for AI-Powered Financial Technologies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/jstsp.2024.3414147","type":"journal-article","created":{"date-parts":[[2024,6,13]],"date-time":"2024-06-13T17:50:46Z","timestamp":1718301046000},"page":"32-44","source":"Crossref","is-referenced-by-count":0,"title":["Towards Improving Interpretability of Language Model Generation Through a Structured Knowledge Discovery Approach"],"prefix":"10.1109","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3479-000X","authenticated-orcid":false,"given":"Shuqi","family":"Liu","sequence":"first","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8008-064X","authenticated-orcid":false,"given":"Han","family":"Wu","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9557-5308","authenticated-orcid":false,"given":"Guanzhi","family":"Deng","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]},{"given":"Jianshu","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Seattle, US"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0746-1059","authenticated-orcid":false,"given":"Xiaoyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Seattle, US"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2756-4984","authenticated-orcid":false,"given":"Linqi","family":"Song","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"issue":"1","key":"ref2","first-page":"11324","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","first-page":"20841","article-title":"Black-box tuning for language-model-as-a-service","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun","year":"2022"},{"key":"ref4","article-title":"Black-box prompt learning for pre-trained language models","author":"Diao","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"article-title":"A survey of knowledge-intensive nlp with pre-trained language models","year":"2022","author":"Yin","key":"ref5"},{"key":"ref6","article-title":"Augmented language models: A survey","author":"Mialon","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.45"},{"article-title":"Selection-inference: exploiting large language models for interpretable logical reasoning","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Creswell","key":"ref8"},{"key":"ref9","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guu","year":"2020"},{"article-title":"LaMDA: Language models for dialog applications","year":"2022","author":"Thoppilan","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.39"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.466"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21360"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1310"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3250499"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w19-8639"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.635"},{"key":"ref19","first-page":"3266","article-title":"SuperGlue: A stickier benchmark for general-purpose language understanding systems","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang","year":"2019"},{"key":"ref20","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc.NAACL-HLT","author":"Devlin"},{"issue":"8","key":"ref21","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.4324\/9781003022022-6"},{"issue":"140","key":"ref23","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"article-title":"Passage re-ranking with BERT","year":"2019","author":"Nogueira","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"article-title":"ERNIE: Enhanced representation through knowledge integration","year":"2019","author":"Sun","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16796"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5681"},{"article-title":"Pre-training text-to-text transformers for concept-centric common sense","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Zhou","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21417"},{"article-title":"Teaching language models to support answers with verified quotes","year":"2022","author":"Menick","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.611"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.396"},{"key":"ref34","first-page":"2206","article-title":"Improving language models by retrieving from trillions of tokens","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Borgeaud","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1128"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1239"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00381"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00484"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016908"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.15"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.40"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.123"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.27"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19433-7_19"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlp4convai-1.9"},{"article-title":"Zero-shot fact-checking with semantic triples and knowledge graphs","year":"2023","author":"Yuan","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.521"},{"article-title":"Graph2Seq: Graph to sequence learning with attention-based neural 1004 networks","year":"2018","author":"Xu","key":"ref48"},{"article-title":"Knowledge-consistent dialogue generation with knowledge graphs","volume-title":"Proc. ICML Workshop Knowl. Retrieval Lang. Models","author":"Kang","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1081"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.33"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00302"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21417"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"2023","DOI":"10.18653\/v1\/P19-1195","article-title":"Data-to-text generation with entity modeling","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Puduppully","year":"2019"},{"key":"ref56","article-title":"A neural probabilistic language model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"13","author":"Bengio"},{"key":"ref57","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Sutskever","year":"2014"},{"key":"ref58","first-page":"3776","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","volume-title":"Proc. 13th AAAI Conf. Artif. Intell.","author":"Serban"},{"article-title":"Jieba(Chinese for to stutter) Chinese text segmentation: built to be the best Python Chinese word segmentation module","year":"2020","author":"Sun","key":"ref59"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","key":"ref60"},{"article-title":"BERTScore: Evaluating text generation with BERT","volume-title":"8th Int. Conf. Learn. Representations","author":"Zhang","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3536-5"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4200690\/10906680\/10556590.pdf?arnumber=10556590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T17:42:48Z","timestamp":1749750168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10556590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":62,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2024.3414147","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"type":"print","value":"1932-4553"},{"type":"electronic","value":"1941-0484"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}