{"type":"ScholarlyArticle","title":"LLMs Can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought","authors":[{"name":"Zhuoxuan Jiang","slug":"zhuoxuan-jiang","given":"Zhuoxuan","family":"Jiang","affiliation":"Shanghai Business School , Shanghai , China; Learnable.AI Inc. , Shanghai , China"},{"name":"Haoyuan Peng","slug":"haoyuan-peng","given":"Haoyuan","family":"Peng","affiliation":"Learnable.AI Inc. , Shanghai , China"},{"name":"Shanshan Feng","slug":"shanshan-feng","given":"Shanshan","family":"Feng","affiliation":"Centre for Frontier AI Research , A*STAR , Singapore; Institute of High-Performance Computing , A *STAR , Singapore"},{"name":"Fan Li","slug":"fan-li","given":"Fan","family":"Li","affiliation":"The Hong Kong Polytechnic University , Hong Kong , China"},{"name":"Dongsheng Li","slug":"dongsheng-li","given":"Dongsheng","family":"Li","affiliation":"Microsoft Research Asia , Shanghai , China"}],"abstract":"Self-correction is emerging as a promising approach to mitigate the issue of hallucination in Large Language Models (LLMs). To facilitate effective self-correction, recent research has proposed mistake detection as its initial step. However, current literature suggests that LLMs often struggle with reliably identifying reasoning mistakes when using simplistic prompting strategies. To address this challenge, we introduce a unique prompting strategy, termed the Pedagogical Chain-of-Thought (PedCoT), which is specifically designed to guide the identification of reasoning mistakes, particularly mathematical reasoning mistakes. PedCoT consists of pedagogical principles for prompts (PPP) design, two-stage interaction process (TIP) and grounded PedCoT prompts, all inspired by the educational theory of the Bloom Cognitive Model (BCM). We evaluate our approach on two public datasets featuring math problems of varying difficulty levels. The experiments demonstrate that our zero-shot prompting strategy significantly outperforms strong baselines. The proposed method can achieve the goal of reliable mathematical mistake identification and provide a foundation for automatic math answer grading. The results underscore the significance of educational theory, serving as domain knowledge, in guiding prompting strategy design for addressing challenging tasks with LLMs effectively.","doi":"10.24963/ijcai.2024/381","url":"https://ijcai.org/proceedings/2024/381","pdf":"https://ijcai.org/proceedings/2024/0381.pdf","markdown":"https://ijcai.org/proceedings/2024/381.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/381","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":381,"pages":{"first":3439,"last":3447},"keywords":["Multidisciplinary Topics and Applications: MTA: Education","Knowledge Representation and Reasoning: KRR: Automated reasoning and theorem proving","Knowledge Representation and Reasoning: KRR: Diagnosis and abductive reasoning"],"videos":[],"references":[{"position":1,"raw":"[Anderson and Krathwohl, 2001] Lorin Anderson and David Krathwohl. Taxonomy for Learning, Teaching, and As- sessing: A Revision of Bloom's Taxonomy of Educational Objectives. Longman, New York, 2001.","title":"Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom's Taxonomy of Educational Objectives","authors":"Anderson, Krathwohl ;, Lorin Anderson, David Krathwohl","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Anil et al., 2023] Rohan Anil, Andrew M Dai, Orhan Fi- rat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, et al. Palm 2 technical report. https://arxiv.org/abs/ 2305.10403, 2023. Accessed: 2024-01-05.","title":"Palm 2 technical report","authors":"Rohan Anil, Andrew M Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2305.10403","internal_url":null},{"position":3,"raw":"[Bloom et al., 1984] Benjamin S. Bloom, David R. Krath- wohl, and Bertram B. Masia. Taxonomy of Educational Objectives: The Classification of Educational Goals. Longman, New York, 1984.","title":"Taxonomy of Educational Objectives: The Classification of Educational Goals","authors":"Benjamin S Bloom, David R Krathwohl, Bertram B Masia","year":"1984","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2022] Wenhu Chen, Xueguang Ma, Xinyi Wang, and William W Cohen. Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. https://arxiv.org/abs/2211. 12588, 2022. Accessed: 2024-01-05.","title":"Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks","authors":"Chen","year":"2022","venue":null,"doi":null,"url":"https://arxiv.org/abs/2211.12588","internal_url":null},{"position":5,"raw":"[Chen et al., 2023] Pinzhen Chen, Zhicheng Guo, Barry Haddow, and Kenneth Heafield. Iterative translation re- finement with large language models. https://arxiv.org/abs/ 2306.03856, 2023. Accessed: 2024-01-05.","title":"Iterative translation refinement with large language models","authors":"Chen","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2306.03856,2023","internal_url":null},{"position":6,"raw":"[Cobbe et al., 2021] Karl Cobbe, Vineet Kosaraju, Moham- mad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. Training verifiers to solve math word problems. https://arxiv.org/ abs/2110.14168, 2021. Accessed: 2024-01-05.","title":"Training verifiers to solve math word problems","authors":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, John Schulman","year":"2021","venue":null,"doi":null,"url":"https://arxiv.org/abs/2110.14168","internal_url":null},{"position":7,"raw":"[Erickson et al., 2020] John A. Erickson, Anthony F. Botelho, Steven McAteer, Ashvini Varatharaj, and Neil T. Heffernan. The automated grading of student open responses in mathematics. In Proceedings of the Tenth International Conference on Learning Analytics & Knowledge, LAK '20, pages 615-624, 2020.","title":"The automated grading of student open responses in mathematics","authors":"John A Erickson, Anthony F Botelho, Steven Mcateer, Ashvini Varatharaj, Neil T Heffernan","year":"2020","venue":"Proceedings of the Tenth International Conference on Learning Analytics & Knowledge, LAK '20","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fernandez et al., 2022] Nigel Fernandez, Aritra Ghosh, Naiming Liu, Zichao Wang, Benoît Choffin, Richard Bara- niuk, and Andrew Lan. Automated scoring for reading comprehension via in-context BERT tuning. In 23rd Inter- national Conference on Artificial Intelligence in Education (AIED 2022), 2022.","title":"Automated scoring for reading comprehension via in-context BERT tuning","authors":"Nigel Fernandez, Aritra Ghosh, Naiming Liu, Zichao Wang, Benoît Choffin, Richard Baraniuk, Andrew Lan","year":"2022","venue":"23rd International Conference on Artificial Intelligence in Education (AIED 2022)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fu et al., 2022] Yao Fu, Hao Peng, Ashish Sabharwal, Pe- ter Clark, and Tushar Khot. Complexity-based prompting for multi-step reasoning. https://arxiv.org/abs/2210.00720, 2022. Accessed: 2024-01-05.","title":"Complexity-based prompting for multi-step reasoning","authors":"Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, Tushar Khot","year":"2024","venue":null,"doi":null,"url":"https://arxiv.org/abs/2210.00720,2022","internal_url":null},{"position":10,"raw":"[Gao et al., 2023] Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. PAL: Program-aided language models. In Proceedings of the 40th International Conference on Machine Learning, pages 10764-10799, 2023.","title":"PAL: Program-aided language models","authors":"Gao","year":"2023","venue":"Proceedings of the 40th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hendrycks et al., 2021] Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. Measuring mathe- matical problem solving with the math dataset. https: //arxiv.org/abs/2103.03874, 2021. Accessed: 2024-01-05.","title":"Measuring mathematical problem solving with the math dataset","authors":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, Jacob Steinhardt","year":"2021","venue":null,"doi":null,"url":"https://arxiv.org/abs/2103.03874","internal_url":null},{"position":12,"raw":"[Huang et al., 2023a] Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xiny- ing Song, and Denny Zhou. Large language models can- not self-correct reasoning yet. https://arxiv.org/abs/2310. 01798, 2023. Accessed: 2024-01-05.","title":"Large language models cannot self-correct reasoning yet","authors":"Huang","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2310.01798,2023","internal_url":null},{"position":13,"raw":"[Huang et al., 2023b] Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qiang- long Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, and Ting Liu. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open ques- tions. https://arxiv.org/abs/2311.05232, 2023. Accessed: 2024-01-05.","title":"A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions","authors":"Huang","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2311.05232","internal_url":null},{"position":14,"raw":"[Kim et al., 2023] Geunwoo Kim, Pierre Baldi, and Stephen McAleer. Language models can solve computer tasks. https://arxiv.org/abs/2303.17491, 2023. Accessed: 2024- 01-05.","title":"Language models can solve computer tasks","authors":"Kim","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2303.17491,2023","internal_url":null},{"position":15,"raw":"[Kojima et al., 2022] Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. Large language models are zero-shot reasoners. Advances in neural information processing systems, 35:22199-22213, 2022.","title":"Large language models are zero-shot reasoners","authors":"Takeshi Kojima, Shane Shixiang, Machel Gu, Yutaka Reid, Yusuke Matsuo, Iwasawa","year":"2022","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lightman et al., 2023] Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. Let's verify step by step. https://arxiv.org/abs/2305.20050, 2023. Accessed: 2024-01-05.","title":"Let's verify step by step","authors":"Lightman","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2305.20050","internal_url":null},{"position":17,"raw":"[Ling et al., 2023] Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, and Hao Su. Deductive verification of chain-of-thought reasoning. In Thirty-seventh Conference on Neural Information Pro- cessing Systems, 2023.","title":"Deductive verification of chain-of-thought reasoning","authors":"Zhan Ling, Yunhao Fang, Xuanlin Li, Zhiao Huang, Mingu Lee, Roland Memisevic, Hao Su","year":"2023","venue":"Thirty-seventh Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Madaan et al., 2023] Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Sean Welleck, Bodhisattwa Prasad Majumder, Shashank Gupta, Amir Yazdanbakhsh, and Peter Clark. Self-refine: Iterative refinement with self-feedback. https://arxiv.org/ abs/2303.17651, 2023. Accessed: 2024-01-05.","title":"Self-refine: Iterative refinement with self-feedback","authors":"Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Sean Welleck, Prasad Bodhisattwa, Shashank Majumder, Amir Gupta, Peter Yazdanbakhsh, Clark","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2303.17651","internal_url":null},{"position":19,"raw":"[Miao et al., 2023] Ning Miao, Yee Whye Teh, and Tom Rainforth. Selfcheck: Using llms to zero-shot check their own step-by-step reasoning. https://arxiv.org/abs/2308. 00436, 2023. Accessed: 2024-01-05. [","title":"Selfcheck: Using llms to zero-shot check their own step-by-step reasoning","authors":"Ning Miao, Yee Whye Teh, Tom Rainforth","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2308.00436","internal_url":null},{"position":20,"raw":"[OpenAI, 2023] OpenAI. Gpt-4 technical report. https: //arxiv.org/abs/2303.08774, 2023. Accessed: 2024-01-05.","title":"OpenAI. Gpt-4 technical report","authors":"Openai","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2303.08774","internal_url":null},{"position":21,"raw":"[Pan et al., 2023] Liangming Pan, Michael Saxon, Wenda Xu, Deepak Nathani, Xinyi Wang, and William Yang Wang. Automatically correcting large language models: Surveying the landscape of diverse self-correction strate- gies. https://arxiv.org/abs/2308.03188, 2023. Accessed: 2024-01-05.","title":"Automatically correcting large language models: Surveying the landscape of diverse self-correction strategies","authors":"Pan","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2308.03188","internal_url":null},{"position":22,"raw":"[Saunders et al., 2022] William Saunders, Catherine Yeh, Jeff Wu, Steven Bills, Long Ouyang, Jonathan Ward, and Jan Leike. Self-critiquing models for assisting human eval- uators. https://arxiv.org/abs/2206.05802, 2022. Accessed: 2024-01-05.","title":"Self-critiquing models for assisting human evaluators","authors":"William Saunders, Catherine Yeh, Jeff Wu, Steven Bills, Long Ouyang, Jonathan Ward, Jan Leike","year":"2022","venue":null,"doi":null,"url":"https://arxiv.org/abs/2206.05802","internal_url":null},{"position":23,"raw":"[Shinn et al., 2023] Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. Reflexion: Language agents with verbal reinforcement learning. https://arxiv.org/abs/2303.11366, 2023. Accessed: 2024-01-05.","title":"Reflexion: Language agents with verbal reinforcement learning","authors":"Shinn","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2303.11366","internal_url":null},{"position":24,"raw":"[Srivastava et al., 2023] Aarohi Srivastava, Abhinav Ras- togi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R. Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, and et al. Beyond the imita- tion game: Quantifying and extrapolating the capabilities of language models. Transactions on Machine Learning Research, 2023.","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","authors":"Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal, Md Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso","year":"2023","venue":"Transactions on Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Tyen et al., 2023] Gladys Tyen, Hassan Mansoor, Peter Chen, Tony Mak, and Victor Cȃrbune. Llms cannot find reasoning errors, but can correct them! https://arxiv.org/ abs/2311.08516, 2023. Accessed: 2024-01-05.","title":"Llms cannot find reasoning errors, but can correct them!","authors":"Tyen","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2311.08516","internal_url":null},{"position":26,"raw":"[Wang et al., 2022] Xuezhi Wang, Jason Wei, Dale Schu- urmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. https: //arxiv.org/abs/2203.11171, 2022. Accessed: 2024-01-05.","title":"Self-consistency improves chain of thought reasoning in language models","authors":"Wang","year":"2022","venue":null,"doi":null,"url":"https://arxiv.org/abs/2203.11171","internal_url":null},{"position":27,"raw":"[Wang et al., 2023] Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, and Ee- Peng Lim. Plan-and-solve prompting: Improving zero- shot chain-of-thought reasoning by large language models. https://arxiv.org/abs/2305.04091, 2023. Accessed: 2024- 01-05.","title":"Plan-and-solve prompting: Improving zeroshot chain-of-thought reasoning by large language models","authors":"Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy, Ka-Wei Lee, Ee-Peng Lim","year":"2023","venue":null,"doi":null,"url":"https://arxiv.org/abs/2305.04091","internal_url":null},{"position":28,"raw":"[Wei et al., 2022] Jason Wei, Xuezhi Wang, Dale Schuur- mans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824-24837, 2022.","title":"Chain-of-thought prompting elicits reasoning in large language models","authors":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, V Quoc, Denny Le, Zhou","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Welleck et al., 2022] Sean Welleck, Jiacheng Liu, Ximing Lu, Hannaneh Hajishirzi, and Yejin Choi. Naturalprover: Grounded mathematical proof generation with language models. In Advances in Neural Information Processing Systems, 2022.","title":"Naturalprover: Grounded mathematical proof generation with language models","authors":"Welleck","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Weng et al., 2023] Yixuan Weng, minjun zhu, Fei Xia, Bin Li, Shizhu He, Shengping Liu, Bin Sun, Kang Liu, and Jun Zhao. Large language models are better reasoners with self-verification. In The 2023 Conference on Em- pirical Methods in Natural Language Processing, pages 2550-2575, 2023.","title":"Large language models are better reasoners with self-verification","authors":"Yixuan Weng, Fei Xia, Bin Li, Shizhu He, Shengping Liu, Bin Sun, Kang Liu, Jun Zhao","year":"2023","venue":"The 2023 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Xie et al., 2022] Jiayi Xie, Kaiwei Cai, Li Kong, Junsheng Zhou, and Weiguang Qu. Automated essay scoring via pairwise contrastive regression. In Proceedings of the 29th International Conference on Computational Linguistics, pages 2724-2733, 2022.","title":"Automated essay scoring via pairwise contrastive regression","authors":"Jiayi Xie, Kaiwei Cai, Li Kong, Junsheng Zhou, Weiguang Qu","year":"2022","venue":"Proceedings of the 29th International Conference on Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Yao et al., 2023] Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. ReAct: Synergizing reasoning and acting in language models. In International Conference on Learning Repre- sentations (ICLR), 2023.","title":"ReAct: Synergizing reasoning and acting in language models","authors":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao","year":"2023","venue":"International Conference on Learning Representations (ICLR)","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhang et al., 2022a] Mengxue Zhang, Sami Baral, Neil Heffernan, and Andrew Lan. Automatic short math an- swer grading via in-context meta-learning. In Proceedings of the 15th International Conference on Educational Data Mining (EDM 2022), pages 122-132, 2022.","title":"Automatic short math answer grading via in-context meta-learning","authors":"Zhang","year":"2022","venue":"Proceedings of the 15th International Conference on Educational Data Mining (EDM 2022)","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhang et al., 2022b] Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. Automatic chain of thought prompting in large language models. https://arxiv.org/abs/2210.03493, 2022. Accessed: 2024-01-05.","title":"Automatic chain of thought prompting in large language models","authors":"Zhang","year":"2022","venue":null,"doi":null,"url":"https://arxiv.org/abs/2210.03493,2022","internal_url":null},{"position":35,"raw":"[Zhou et al., 2022] Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuur- mans, Claire Cui, Olivier Bousquet, Quoc Le, et al. Least- to-most prompting enables complex reasoning in large language models. https://arxiv.org/abs/2205.10625, 2022. Accessed: 2024-01-05.","title":"Leastto-most prompting enables complex reasoning in large language models","authors":"Denny Zhou, Nathanael Schärli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc Le","year":"2022","venue":null,"doi":null,"url":"https://arxiv.org/abs/2205.10625","internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}