{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:29:00Z","timestamp":1767677340935,"version":"3.48.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376144"],"award-info":[{"award-number":["62376144"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272285"],"award-info":[{"award-number":["62272285"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906111"],"award-info":[{"award-number":["61906111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Language Processing Innovation Team"},{"name":"Project of Shanxi Province"},{"name":"Science and Technology Cooperation and Exchange Special Project of Shanxi Province","award":["202204041101016"],"award-info":[{"award-number":["202204041101016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tkde.2025.3638864","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:25:37Z","timestamp":1764613537000},"page":"1159-1173","source":"Crossref","is-referenced-by-count":0,"title":["Learnable Game-Theoretic Policy Optimization for Data-Centric Self-Explanation Rationalization"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9133-7324","authenticated-orcid":false,"given":"Yunxiao","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer and Information Technology, Shanxi University, Taiyuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9269-3988","authenticated-orcid":false,"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Shanxi University, Taiyuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2884-8578","authenticated-orcid":false,"given":"Xingtong","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer and Information Systems, Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0762-6562","authenticated-orcid":false,"given":"Xiaoli","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5887-9327","authenticated-orcid":false,"given":"Jiye","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Shanxi University, Taiyuan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1545-5553","authenticated-orcid":false,"given":"Ru","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer and Information Technology, Shanxi University, Taiyuan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.386"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.5"},{"volume-title":"Applied Machine Learning Explainability Techniques: Make ML Models Explainable and Trustworthy for Practical Applications Using LIME, SHAP, and More","year":"2022","author":"Bhattacharya","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref6","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lundberg"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.832"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-4158-4_14"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1420"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00758"},{"article-title":"Adversarial cooperative rationalization: The risk of spurious correlations in even clean datasets","year":"2025","author":"Liu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1011"},{"article-title":"Towards faithful explanations: Boosting rationalization with shortcuts discovery","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yue","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-short.47"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00176"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29783"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.655"},{"key":"ref19","first-page":"41715","article-title":"Towards trustworthy explanation: On causal rationalization","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.707"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599299"},{"key":"ref22","first-page":"6954","article-title":"FR: Folded rationalization with a unified encoder","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2022.103828"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3028783"},{"key":"ref25","first-page":"19620","article-title":"Parameterized explainer for graph neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luo"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3387580"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095063"},{"key":"ref28","first-page":"12822","article-title":"Understanding interlocking dynamics of cooperative rationalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref29","first-page":"117636","article-title":"Is the MMI criterion necessary for explanation? Degenerating non-causal features to plain noise","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.715"},{"key":"ref31","first-page":"1448","article-title":"Invariant rationalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.700"},{"key":"ref33","first-page":"43620","article-title":"D-separation for causal self-explanation","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17547"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.408"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1371"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21342"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00511"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1216"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1284"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.153"},{"key":"ref42","first-page":"26603","article-title":"DARE: Disentanglement-augmented rationale extraction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yue"},{"key":"ref43","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.557"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.378"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.702"},{"key":"ref47","article-title":"Causal reasoning and large language models: Opening a new frontier for causality","volume":"2024","author":"Kiciman","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"article-title":"Chain-of-thought reasoning in the wild is not always faithful","year":"2025","author":"Arcuschin","key":"ref49"},{"key":"ref50","first-page":"74952","article-title":"Language models don\u2019t always say what they think: Unfaithful explanations in chain-of-thought prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Turpin"},{"key":"ref51","first-page":"17506","article-title":"Pretraining language models with human preferences","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Korbak"},{"article-title":"TrustLLM: Trustworthiness in large language models","year":"2024","author":"Huang","key":"ref52"},{"article-title":"A survey of large language models","year":"2023","author":"Zhao","key":"ref53"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709212"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"ref57","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref58","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref59","first-page":"586","article-title":"Deep learning without poor local minima","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kawaguchi"},{"key":"ref60","first-page":"192","article-title":"The loss surfaces of multilayer networks","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Choromanska"},{"article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Karras","key":"ref61"},{"article-title":"Global optimality conditions for deep neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yun","key":"ref62"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2012.110"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835903"},{"article-title":"Discovering invariant rationales for graph neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","key":"ref65"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","key":"ref68"},{"key":"ref69","first-page":"9240","article-title":"GNNExplainer: Generating explanations for graph neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref70","first-page":"10055","article-title":"A game theoretic approach to class-wise selective rationalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chang"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11329113\/11271751.pdf?arnumber=11271751","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:26:25Z","timestamp":1767677185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271751\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":70,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3638864","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"type":"print","value":"1041-4347"},{"type":"electronic","value":"1558-2191"},{"type":"electronic","value":"2326-3865"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}