{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:10:12Z","timestamp":1765545012558,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","funder":[{"name":"Guangdong S&T Program","award":["C019"],"award-info":[{"award-number":["C019"]}]},{"name":"National Key Research and Development Program of China Grant","award":["No.2023YFF0725100"],"award-info":[{"award-number":["No.2023YFF0725100"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737109","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:07:39Z","timestamp":1754255259000},"page":"2257-2268","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Rewarding Graph Reasoning Process makes LLMs more Generalized Reasoners"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7063-2014","authenticated-orcid":false,"given":"Miao","family":"Peng","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5880-4712","authenticated-orcid":false,"given":"Nuo","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8449-8609","authenticated-orcid":false,"given":"Zongrui","family":"Suo","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6362-4385","authenticated-orcid":false,"given":"Jia","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2407.21783"},{"key":"e_1_3_2_2_2_1","first-page":"509","volume-title":"Science","volume":"286","author":"Barab\u00e1si Albert-L\u00e1szl\u00f3","year":"1999","unstructured":"Albert-L\u00e1szl\u00f3 Barab\u00e1si and R\u00e9ka Albert. 1999. Emergence of Scaling in Random Networks. Science, Vol. 286, 5439 (1999), 509-512."},{"key":"e_1_3_2_2_3_1","volume-title":"GraphLLM: Boosting Graph Reasoning Ability of Large Language Model. CoRR","author":"Chai Ziwei","year":"2023","unstructured":"Ziwei Chai, Tianjie Zhang, Liang Wu, Kaiqiao Han, Xiaohai Hu, Xuanwen Huang, and Yang Yang. 2023. GraphLLM: Boosting Graph Reasoning Ability of Large Language Model. CoRR, Vol. abs\/2310.05845 (2023)."},{"key":"e_1_3_2_2_4_1","first-page":"353","article-title":"GraphWiz: An Instruction-Following Language Model for Graph Computational Problems. In KDD","author":"Chen Nuo","year":"2024","unstructured":"Nuo Chen, Yuhan Li, Jianheng Tang, and Jia Li. 2024a. GraphWiz: An Instruction-Following Language Model for Graph Computational Problems. In KDD, ACM, 353-364.","journal-title":"ACM"},{"key":"e_1_3_2_2_5_1","volume-title":"Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with Characters. In EMNLP (Findings). Association for Computational Linguistics, 8506-8520","author":"Chen Nuo","year":"2023","unstructured":"Nuo Chen, Yan Wang, Haiyun Jiang, Deng Cai, Yuhan Li, Ziyang Chen, Longyue Wang, and Jia Li. 2023. Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with Characters. In EMNLP (Findings). Association for Computational Linguistics, 8506-8520."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.680"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.411"},{"key":"e_1_3_2_2_8_1","first-page":"4299","article-title":"Deep Reinforcement Learning from Human Preferences","author":"Christiano Paul F.","year":"2017","unstructured":"Paul F. Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep Reinforcement Learning from Human Preferences. In NIPS. 4299-4307.","journal-title":"NIPS."},{"key":"e_1_3_2_2_9_1","volume-title":"Training Verifiers to Solve Math Word Problems. CoRR","author":"Cobbe Karl","year":"2021","unstructured":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021a. Training Verifiers to Solve Math Word Problems. CoRR, Vol. abs\/2110.14168 (2021)."},{"key":"e_1_3_2_2_10_1","volume-title":"Training Verifiers to Solve Math Word Problems. CoRR","author":"Cobbe Karl","year":"2021","unstructured":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021b. Training Verifiers to Solve Math Word Problems. CoRR, Vol. abs\/2110.14168 (2021)."},{"key":"e_1_3_2_2_11_1","unstructured":"Bahare Fatemi Jonathan Halcrow and Bryan Perozzi. 2024. Talk like a Graph: Encoding Graphs for Large Language Models. In ICLR OpenReview.net."},{"key":"e_1_3_2_2_12_1","volume-title":"ICML(Proceedings of Machine Learning Research","volume":"10799","author":"Gao Luyu","year":"2023","unstructured":"Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. PAL: Program-aided Language Models. In ICML(Proceedings of Machine Learning Research, Vol. 202). PMLR, 10764-10799."},{"key":"e_1_3_2_2_13_1","unstructured":"Zhibin Gou Zhihong Shao Yeyun Gong Yelong Shen Yujiu Yang Minlie Huang Nan Duan and Weizhu Chen. 2024. ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving. In ICLR OpenReview.net."},{"key":"e_1_3_2_2_14_1","volume-title":"Collective Relaxation Dynamics of Small-World Networks. CoRR","author":"Grabow Carsten","year":"2015","unstructured":"Carsten Grabow, Stefan Grosskinsky, J\u00fcrgen Kurths, and Marc Timme. 2015. Collective Relaxation Dynamics of Small-World Networks. CoRR, Vol. abs\/1507.04624 (2015)."},{"key":"e_1_3_2_2_15_1","volume-title":"GPT4Graph: Can Large Language Models Understand Graph Structured Data An Empirical Evaluation and Benchmarking. CoRR","author":"Guo Jiayan","year":"2023","unstructured":"Jiayan Guo, Lun Du, and Hengyu Liu. 2023. GPT4Graph: Can Large Language Models Understand Graph Structured Data An Empirical Evaluation and Benchmarking. CoRR, Vol. abs\/2305.15066 (2023)."},{"key":"e_1_3_2_2_16_1","unstructured":"Dan Hendrycks Collin Burns Saurav Kadavath Akul Arora Steven Basart Eric Tang Dawn Song and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. In NeurIPS Datasets and Benchmarks."},{"key":"e_1_3_2_2_17_1","first-page":"37","article-title":"MathPrompter: Mathematical Reasoning using Large Language Models. In ACL (industry)","author":"Imani Shima","year":"2023","unstructured":"Shima Imani, Liang Du, and Harsh Shrivastava. 2023. MathPrompter: Mathematical Reasoning using Large Language Models. In ACL (industry). Association for Computational Linguistics, 37-42.","journal-title":"Association for Computational Linguistics"},{"volume-title":"EMNLP","author":"Jiao Fangkai","key":"e_1_3_2_2_18_1","unstructured":"Fangkai Jiao, Chengwei Qin, Zhengyuan Liu, Nancy F. Chen, and Shafiq Joty. 2024. Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing. In EMNLP, Association for Computational Linguistics."},{"key":"e_1_3_2_2_19_1","volume-title":"Training Language Models to Self-Correct via Reinforcement Learning. CoRR","author":"Kumar Aviral","year":"2024","unstructured":"Aviral Kumar, Vincent Zhuang, Rishabh Agarwal, Yi Su, John D. Co-Reyes, Avi Singh, Kate Baumli, Shariq Iqbal, Colton Bishop, Rebecca Roelofs, Lei M. Zhang, Kay McKinney, Disha Shrivastava, Cosmin Paduraru, George Tucker, Doina Precup, Feryal M. P. Behbahani, and Aleksandra Faust. 2024. Training Language Models to Self-Correct via Reinforcement Learning. CoRR, Vol. abs\/2409.12917 (2024)."},{"key":"e_1_3_2_2_20_1","first-page":"141045","volume-title":"Datasets and Models. In Advances in Neural Information Processing Systems","volume":"37","author":"Li Xin","year":"2024","unstructured":"Xin Li, Weize Chen, Qizhi Chu, Haopeng Li, Zhaojun Sun, Ran Li, Chen Qian, Yiwei Wei, Chuan Shi, Zhiyuan Liu, Maosong Sun, and Cheng Yang. 2024a. Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models. In Advances in Neural Information Processing Systems, Vol. 37. Curran Associates, Inc., 141045-141070."},{"key":"e_1_3_2_2_21_1","first-page":"5315","article-title":"Making Language Models Better Reasoners with Step-Aware Verifier. In ACL (1)","author":"Li Yifei","year":"2023","unstructured":"Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. 2023. Making Language Models Better Reasoners with Step-Aware Verifier. In ACL (1), Association for Computational Linguistics, 5315-5333.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671982"},{"key":"e_1_3_2_2_23_1","volume-title":"Victor Wai Kin Chan, and Jia Li","author":"Li Yuhan","year":"2024","unstructured":"Yuhan Li, Peisong Wang, Xiao Zhu, Aochuan Chen, Haiyun Jiang, Deng Cai, Victor Wai Kin Chan, and Jia Li. 2024c. Glbench: A comprehensive benchmark for graph with large language models. arXiv preprint arXiv:2407.07457(2024)."},{"key":"e_1_3_2_2_24_1","unstructured":"Yuhan Li Xinni Zhang Linhao Luo Heng Chang Yuxiang Ren Irwin King and Jia Li. 2025. G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation. arXiv preprint arXiv:2502.12586(2025)."},{"key":"e_1_3_2_2_25_1","unstructured":"Hunter Lightman Vineet Kosaraju Yuri Burda Harrison Edwards Bowen Baker Teddy Lee Jan Leike John Schulman Ilya Sutskever and Karl Cobbe. 2024. Let's Verify Step by Step. In ICLR OpenReview.net."},{"key":"e_1_3_2_2_26_1","first-page":"11181","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics, COLING 2025, Abu Dhabi, UAE","author":"Liu Ben","year":"2025","unstructured":"Ben Liu, Jihai Zhang, Fangquan Lin, Cheng Yang, and Min Peng. 2025 a. Filter-then-Generate: Large Language Models with Structure-Text Adapter for Knowledge Graph Completion. In Proceedings of the 31st International Conference on Computational Linguistics, COLING 2025, Abu Dhabi, UAE, January 19-24, 2025. Association for Computational Linguistics, 11181-11195."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Ben Liu Jihai Zhang Fangquan Lin Cheng Yang Min Peng and Wotao Yin. 2025 b. SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs. arXiv preprint arXiv:2502.03283(2025).","DOI":"10.1145\/3696410.3714768"},{"key":"e_1_3_2_2_28_1","volume-title":"WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct. CoRR","author":"Luo Haipeng","year":"2023","unstructured":"Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao, Jianguang Lou, Chongyang Tao, Xiubo Geng, Qingwei Lin, Shifeng Chen, and Dongmei Zhang. 2023. WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct. CoRR, Vol. abs\/2308.09583 (2023)."},{"key":"e_1_3_2_2_29_1","volume-title":"Improve Mathematical Reasoning in Language Models by Automated Process Supervision. CoRR","author":"Luo Liangchen","year":"2024","unstructured":"Liangchen Luo, Yinxiao Liu, Rosanne Liu, Samrat Phatale, Harsh Lara, Yunxuan Li, Lei Shu, Yun Zhu, Lei Meng, Jiao Sun, and Abhinav Rastogi. 2024a. Improve Mathematical Reasoning in Language Models by Automated Process Supervision. CoRR, Vol. abs\/2406.06592 (2024)."},{"key":"e_1_3_2_2_30_1","volume-title":"GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability. CoRR","author":"Luo Zihan","year":"2024","unstructured":"Zihan Luo, Xiran Song, Hong Huang, Jianxun Lian, Chenhao Zhang, Jinqi Jiang, and Xing Xie. 2024b. GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability. CoRR, Vol. abs\/2403.04483 (2024)."},{"key":"e_1_3_2_2_31_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR Vol. abs\/2303.08774 (2023)."},{"key":"e_1_3_2_2_32_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul F. Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In NeurIPS."},{"key":"e_1_3_2_2_33_1","volume-title":"NAACL-HLT","author":"Patel Arkil","year":"2080","unstructured":"Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 2021. Are NLP Models really able to Solve Simple Math Word Problems?. In NAACL-HLT, Association for Computational Linguistics, 2080-2094."},{"key":"e_1_3_2_2_34_1","first-page":"1178","article-title":"Deja vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoning. In NAACL-HLT (Findings)","author":"Peng Miao","year":"2024","unstructured":"Miao Peng, Ben Liu, Wenjie Xu, Zihao Jiang, Jiahui Zhu, and Min Peng. 2024. Deja vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoning. In NAACL-HLT (Findings). Association for Computational Linguistics, 1178-1191.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_3_2_2_35_1","unstructured":"Rafael Rafailov Archit Sharma Eric Mitchell Christopher D. Manning Stefano Ermon and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. In NeurIPS."},{"key":"e_1_3_2_2_36_1","volume-title":"Proximal Policy Optimization Algorithms. CoRR","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR, Vol. abs\/1707.06347 (2017)."},{"key":"e_1_3_2_2_37_1","volume-title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters. CoRR","author":"Snell Charlie","year":"2024","unstructured":"Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters. CoRR, Vol. abs\/2408.03314 (2024)."},{"key":"e_1_3_2_2_38_1","first-page":"491","article-title":"GraphGPT: Graph Instruction Tuning for Large Language Models. In SIGIR","author":"Tang Jiabin","year":"2024","unstructured":"Jiabin Tang, Yuhao Yang, Wei Wei, Lei Shi, Lixin Su, Suqi Cheng, Dawei Yin, and Chao Huang. 2024a. GraphGPT: Graph Instruction Tuning for Large Language Models. In SIGIR, ACM, 491-500.","journal-title":"ACM"},{"key":"e_1_3_2_2_39_1","volume-title":"GraphArena: Benchmarking Large Language Models on Graph Computational Problems. CoRR","author":"Tang Jianheng","year":"2024","unstructured":"Jianheng Tang, Qifan Zhang, Yuhan Li, and Jia Li. 2024b. GraphArena: Benchmarking Large Language Models on Graph Computational Problems. CoRR, Vol. abs\/2407.00379 (2024)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.34740\/KAGGLE\/M\/3301"},{"key":"e_1_3_2_2_41_1","unstructured":"Qwen Team. 2024b. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_3_2_2_42_1","volume-title":"Solving math word problems with process- and outcome-based feedback. CoRR","author":"Uesato Jonathan","year":"2022","unstructured":"Jonathan Uesato, Nate Kushman, Ramana Kumar, H. Francis Song, Noah Y. Siegel, Lisa Wang, Antonia Creswell, Geoffrey Irving, and Irina Higgins. 2022. Solving math word problems with process- and outcome-based feedback. CoRR, Vol. abs\/2211.14275 (2022)."},{"key":"e_1_3_2_2_43_1","unstructured":"Heng Wang Shangbin Feng Tianxing He Zhaoxuan Tan Xiaochuang Han and Yulia Tsvetkov. 2023a. Can Language Models Solve Graph Problems in Natural Language?. In NeurIPS."},{"key":"e_1_3_2_2_44_1","volume-title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models. CoRR","author":"Wang Jun","year":"2024","unstructured":"Jun Wang, Meng Fang, Ziyu Wan, Muning Wen, Jiachen Zhu, Anjie Liu, Ziqin Gong, Yan Song, Lei Chen, Lionel M. Ni, Linyi Yang, Ying Wen, and Weinan Zhang. 2024a. OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models. CoRR, Vol. abs\/2410.09671 (2024)."},{"key":"e_1_3_2_2_45_1","first-page":"9426","article-title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations. In ACL (1)","author":"Wang Peiyi","year":"2024","unstructured":"Peiyi Wang, Lei Li, Zhihong Shao, Runxin Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. 2024b. Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations. In ACL (1). Association for Computational Linguistics, 9426-9439.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_3_2_2_46_1","volume-title":"Sharan Narang, Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2023","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023c. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In ICLR. OpenReview.net."},{"key":"e_1_3_2_2_47_1","first-page":"13484","article-title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions. In ACL (1)","author":"Wang Yizhong","year":"2023","unstructured":"Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A. Smith, Daniel Khashabi, and Hannaneh Hajishirzi. 2023b. Self-Instruct: Aligning Language Models with Self-Generated Instructions. In ACL (1). Association for Computational Linguistics, 13484-13508.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_3_2_2_48_1","volume-title":"Quoc V. Le, and Denny Zhou.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In NeurIPS."},{"key":"e_1_3_2_2_49_1","unstructured":"Zeqiu Wu Yushi Hu Weijia Shi Nouha Dziri Alane Suhr Prithviraj Ammanabrolu Noah A. Smith Mari Ostendorf and Hannaneh Hajishirzi. 2023. Fine-Grained Human Feedback Gives Better Rewards for Language Model Training. In NeurIPS."},{"key":"e_1_3_2_2_50_1","first-page":"7790","article-title":"Pre-trained Language Model with Prompts for Temporal Knowledge Graph Completion. In ACL (Findings)","author":"Xu Wenjie","year":"2023","unstructured":"Wenjie Xu, Ben Liu, Miao Peng, Xu Jia, and Min Peng. 2023. Pre-trained Language Model with Prompts for Temporal Knowledge Graph Completion. In ACL (Findings). Association for Computational Linguistics, 7790-7803.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_3_2_2_51_1","unstructured":"Shunyu Yao Dian Yu Jeffrey Zhao Izhak Shafran Tom Griffiths Yuan Cao and Karthik Narasimhan. 2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. In NeurIPS."},{"key":"e_1_3_2_2_52_1","first-page":"858","article-title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning. In NAACL-HLT (Findings)","author":"Yu Fei","year":"2024","unstructured":"Fei Yu, Anningzhe Gao, and Benyou Wang. 2024. OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning. In NAACL-HLT (Findings). Association for Computational Linguistics, 858-875.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_3_2_2_53_1","first-page":"1963","article-title":"Back to the Future","author":"Yuan Chenhan","year":"2024","unstructured":"Chenhan Yuan, Qianqian Xie, Jimin Huang, and Sophia Ananiadou. 2024. Back to the Future: Towards Explainable Temporal Reasoning with Large Language Models. In WWW. ACM, 1963-1974.","journal-title":"Towards Explainable Temporal Reasoning with Large Language Models. In WWW. ACM"},{"key":"e_1_3_2_2_54_1","first-page":"7925","article-title":"GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models","author":"Yuan Zike","year":"2025","unstructured":"Zike Yuan, Ming Liu, Hui Wang, and Bing Qin. 2025. GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models. In COLING. Association for Computational Linguistics, 7925-7948.","journal-title":"COLING. Association for Computational Linguistics"},{"key":"e_1_3_2_2_55_1","volume-title":"Scaling Relationship on Learning Mathematical Reasoning with Large Language Models. CoRR","author":"Yuan Zheng","year":"1825","unstructured":"Zheng Yuan, Hongyi Yuan, Chengpeng Li, Guanting Dong, Chuanqi Tan, and Chang Zhou. 2023. Scaling Relationship on Learning Mathematical Reasoning with Large Language Models. CoRR, Vol. abs\/2308.01825 (2023)."},{"key":"e_1_3_2_2_56_1","unstructured":"Xiang Yue Xingwei Qu Ge Zhang Yao Fu Wenhao Huang Huan Sun Yu Su and Wenhu Chen. 2024. MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning. In ICLR. OpenReview.net."},{"key":"e_1_3_2_2_57_1","first-page":"2289","article-title":"Can LLM Graph Reasoning Generalize beyond Pattern Memorization?. In EMNLP (Findings)","author":"Zhang Yizhuo","year":"2024","unstructured":"Yizhuo Zhang, Heng Wang, Shangbin Feng, Zhaoxuan Tan, Xiaochuang Han, Tianxing He, and Yulia Tsvetkov. 2024. Can LLM Graph Reasoning Generalize beyond Pattern Memorization?. In EMNLP (Findings). Association for Computational Linguistics, 2289-2305.","journal-title":"Association for Computational Linguistics"},{"key":"e_1_3_2_2_58_1","volume-title":"ProcessBench: Identifying Process Errors in Mathematical Reasoning. CoRR","author":"Zheng Chujie","year":"2024","unstructured":"Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2024. ProcessBench: Identifying Process Errors in Mathematical Reasoning. CoRR, Vol. abs\/2412.06559 (2024)."},{"key":"e_1_3_2_2_59_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric P. Xing Hao Zhang Joseph E. Gonzalez and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In NeurIPS."},{"key":"e_1_3_2_2_60_1","volume-title":"Chi","author":"Zhou Denny","year":"2023","unstructured":"Denny Zhou, Nathanael Sch\u00e4rli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc V. Le, and Ed H. Chi. 2023. Least-to-Most Prompting Enables Complex Reasoning in Large Language Models. In ICLR. OpenReview.net."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"],"location":"Toronto ON Canada","acronym":"KDD '25"},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T14:38:48Z","timestamp":1755355128000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":60,"alternative-id":["10.1145\/3711896.3737109","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737109","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}