{"type":"ScholarlyArticle","title":"Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialogue","authors":[{"name":"Shixuan Fan","slug":"shixuan-fan","given":"Shixuan","family":"Fan","affiliation":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory , School of Computer Science and Technology , Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"},{"name":"Wei Wei","slug":"wei-wei","given":"Wei","family":"Wei","affiliation":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory , School of Computer Science and Technology , Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"},{"name":"Wendi Li","slug":"wendi-li","given":"Wendi","family":"Li","affiliation":"Cognitive Computing and Intelligent Information Processing (CCIIP) Laboratory , School of Computer Science and Technology , Huazhong University of Science and Technology; Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL)"},{"name":"Xian-Ling Mao","slug":"xian-ling-mao","given":"Xian-Ling","family":"Mao","affiliation":"Department of Computer Science and Technology , Beijing Institute of Technology"},{"name":"Wenfeng Xie","slug":"wenfeng-xie","given":"Wenfeng","family":"Xie","affiliation":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL); Ping An Property & Casualty Insurance Company of China , Ltd"},{"name":"Dangyang Chen","slug":"dangyang-chen","given":"Dangyang","family":"Chen","affiliation":"Joint Laboratory of HUST and Pingan Property & Casualty Research (HPL); Ping An Property & Casualty Insurance Company of China , Ltd"}],"abstract":"The core of the dialogue system is to generate relevant, informative, and human-like responses based on extensive dialogue history. Recently, dialogue generation domain has seen mainstream adoption of large language models (LLMs), due to its powerful capability in generating utterances. However, there is a natural deficiency for such models, that is, inherent position bias, which may lead them to pay more attention to the nearby utterances instead of causally relevant ones, resulting in generating irrelevant and generic responses in long-term dialogue. To alleviate such problem, in this paper, we propose a novel method, named Causal Perception long-term Dialogue framework (CPD), which employs perturbation-based causal variable discovery method to extract casually relevant utterances from the dialogue history and enhances model causal perception during fine-tuning. Specifically, a local-position awareness method is proposed in CPD for inter-sentence position correlation elimination, which helps models extract causally relevant utterances based on perturbations. Then, a casual-perception fine-tuning strategy is also proposed, to enhance the capability of discovering the causal invariant factors, by differently perturbing causally relevant and non-casually relevant ones for response generation. Experimental results on two datasets prove that our proposed method can effectively alleviate the position bias for multiple LLMs and achieve significant progress compared with existing baselines.","doi":"10.24963/ijcai.2024/692","url":"https://ijcai.org/proceedings/2024/692","pdf":"https://ijcai.org/proceedings/2024/0692.pdf","markdown":"https://ijcai.org/proceedings/2024/692.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/692","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":"Natural Language Processing","track":"Main Track","number":692,"pages":{"first":6261,"last":6269},"keywords":["Natural Language Processing: NLP: Dialogue and interactive systems"],"videos":[],"references":[{"position":1,"raw":"[Abraham et al., 2022] Eldar D Abraham, Karel D'Oosterlinck, Amir Feder, Yair Gat, Atticus Geiger, Christopher Potts, Roi Reichart, and Zhengxuan Wu. Ce- bab: Estimating the causal effects of real-world concepts on nlp model behavior. Advances in Neural Information Processing Systems, 35:17582-17596, 2022.","title":"Cebab: Estimating the causal effects of real-world concepts on nlp model behavior","authors":"Karel D' Eldar D Abraham, Amir Oosterlinck, Yair Feder, Atticus Gat, Christopher Geiger, Roi Potts, Zhengxuan Reichart, Wu","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Alaa and Van Der Schaar, 2019] Ahmed Alaa and Mihaela Van Der Schaar. Validating causal inference models via influence functions. In International Conference on Ma- chine Learning, pages 191-201. PMLR, 2019.","title":"Validating causal inference models via influence functions","authors":"Alaa, Van Der, Schaar, Ahmed Alaa, Mihaela Van, Der Schaar","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Amor et al., 2023] Mehdi Ben Amor, Michael Granitzer, and Jelena Mitrović. Technical report on token position bias in transformers, 2023.","title":"Technical report on token position bias in transformers","authors":"Mehdi Ben Amor, Michael Granitzer, Jelena Mitrović","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Arjovsky et al., 2019] Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, and David Lopez-Paz. Invariant risk minimization. arXiv preprint arXiv:1907.02893, 2019.","title":"Invariant risk minimization","authors":"Martin Arjovsky, Léon Bottou, Ishaan Gulrajani, David Lopez-Paz","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Austin, 2011] Peter C Austin. An introduction to propensity score methods for reducing the effects of confounding in observational studies. Multivariate behavioral research, 46(3):399-424, 2011.","title":"An introduction to propensity score methods for reducing the effects of confounding in observational studies","authors":"Peter C Austin","year":"2011","venue":"Multivariate behavioral research","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chang et al., 2020] Shiyu Chang, Yang Zhang, Mo Yu, and Tommi Jaakkola. Invariant rationalization. In Inter- national Conference on Machine Learning, pages 1448- 1458. PMLR, 2020.","title":"Invariant rationalization","authors":"Shiyu Chang, Yang Zhang, Mo Yu, Tommi Jaakkola","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dawid, 1980] A Philip Dawid. Conditional independence for statistical operations. The Annals of Statistics, 8(3):598-617, 1980.","title":"Conditional independence for statistical operations","authors":"Dawid Philip","year":"1980","venue":"The Annals of Statistics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dettmers et al., 2022] Tim Dettmers, Mike Lewis, Younes Belkada, and Luke Zettlemoyer. Gpt3. int8 (): 8-bit ma- trix multiplication for transformers at scale. Advances in Neural Information Processing Systems, 35:30318-30332, 2022.","title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","authors":"Tim Dettmers, Mike Lewis, Younes Belkada, Luke Zettlemoyer","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Feng et al., 2023] Tao Feng, Lizhen Qu, and Gholamreza Haffari. Less is more: Mitigate spurious correlations for open-domain dialogue response generation models by causal discovery. Transactions of the Association for Com- putational Linguistics, 11:511-530, 2023.","title":"Less is more: Mitigate spurious correlations for open-domain dialogue response generation models by causal discovery","authors":"Tao Feng, Lizhen Qu, Gholamreza Haffari","year":"2023","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[He et al., 2023] Junqing He, Kunhao Pan, Xiaoqun Dong, Zhuoyang Song, Yibo Liu, Yuxin Liang, Hao Wang, Qian- guo Sun, Songxin Zhang, Zejian Xie, et al. Never lost in the middle: Improving large language models via attention strengthening question answering. arXiv e-prints, pages arXiv-2311, 2023.","title":"Never lost in the middle: Improving large language models via attention strengthening question answering","authors":"He","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Horgan, 1995] J. Horgan. From complexity to perplexity. Scientific American, 272(6):104-109, 1995.","title":"From complexity to perplexity","authors":"J Horgan","year":"1995","venue":"Scientific American","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hu et al., 2021] Edward J Hu, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. Lora: Low-rank adaptation of large language models. In International Conference on Learning Representations, 2021.","title":"Lora: Low-rank adaptation of large language models","authors":"J Edward, Phillip Hu, Zeyuan Wallis, Yuanzhi Allen-Zhu, Shean Li, Lu Wang, Weizhu Wang, Chen","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ivgi et al., 2023] Maor Ivgi, Uri Shaham, and Jonathan Be- rant. Efficient long-text understanding with short-text models. Transactions of the Association for Computa- tional Linguistics, 11:284-299, 2023.","title":"Efficient long-text understanding with short-text models","authors":"Maor Ivgi, Uri Shaham, Jonathan Berant","year":"2023","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Yoshua Bengio and Yann LeCun, editors, 3rd International Con- ference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Pro- ceedings, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"3rd International Conference on Learning Representations, ICLR 2015","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ko et al., 2020] Miyoung Ko, Jinhyuk Lee, Hyunjae Kim, Gangwoo Kim, and Jaewoo Kang. Look at the first sen- tence: Position bias in question answering. In Bonnie Webber, Trevor Cohn, Yulan He, and Yang Liu, editors, Proceedings of the 2020 Conference on Empirical Meth- ods in Natural Language Processing, EMNLP 2020, On- line, November 16-20, 2020, pages 1109-1121. Associa- tion for Computational Linguistics, 2020.","title":"Look at the first sentence: Position bias in question answering","authors":"Miyoung Ko, Jinhyuk Lee, Hyunjae Kim, Gangwoo Kim, Jaewoo Kang","year":"2020","venue":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Krishna and Murty, 1999] K Krishna and M Narasimha Murty. Genetic k-means algorithm. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 29(3):433-439, 1999.","title":"Genetic k-means algorithm","authors":"K Krishna, M Narasimha, Murty","year":"1999","venue":"IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lee et al., 2023] Gibbeum Lee, Volker Hartmann, Jongho Park, Dimitris Papailiopoulos, and Kangwook Lee. Prompted llms as chatbot modules for long open-domain conversation. In Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki, editors, Findings of the Associa- tion for Computational Linguistics: ACL 2023, Toronto, Canada, July 9-14, 2023, pages 4536-4554. Association for Computational Linguistics, 2023.","title":"Prompted llms as chatbot modules for long open-domain conversation","authors":"Lee","year":"2023","venue":"Findings of the Association for Computational Linguistics: ACL 2023","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li et al., 2016] Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A diversity-promoting objective function for neural conversation models. In Kevin Knight, Ani Nenkova, and Owen Rambow, editors, NAACL HLT 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego California, USA, June 12-17, 2016, pages 110-119. The Association for Computational Linguistics, 2016.","title":"A diversity-promoting objective function for neural conversation models","authors":"Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan","year":"2016","venue":"NAACL HLT 2016, The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Li et al., 2023] Zongjie Li, Chaozheng Wang, Pingchuan Ma, Daoyuan Wu, Shuai Wang, Cuiyun Gao, and Yang Liu. Split and merge: Aligning position biases in large language model based evaluators. arXiv preprint arXiv:2310.01432, 2023.","title":"Split and merge: Aligning position biases in large language model based evaluators","authors":"Li","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Lin and Och, 2004] Chin-Yew Lin and Franz Josef Och. Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In Proceedings of the 42nd Annual Meeting of the Associ- ation for Computational Linguistics (ACL-04), pages 605- 612, 2004.","title":"Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics","authors":"Lin, Och ; ] Chin-Yew Lin, Franz Josef, Och","year":"2004","venue":"Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Liu et al., 2021] Siyang Liu, Chujie Zheng, Orianna De- masi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang, and Minlie Huang. Towards emotional support dialog systems. In Proceedings of the 59th Annual Meeting of the Associ- ation for Computational Linguistics and the 11th Interna- tional Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3469-3483, 2021.","title":"Towards emotional support dialog systems","authors":"Siyang Liu, Chujie Zheng, Orianna Demasi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang, Minlie Huang","year":"2021","venue":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Liu et al., 2022a] Jiayi Liu, Wei Wei, Zhixuan Chu, Xing Gao, Ji Zhang, Tan Yan, and Yulin Kang. Incorporating causal analysis into diversified and logical response gener- ation. In Proceedings of the 29th International Conference on Computational Linguistics, pages 378-388, 2022.","title":"Incorporating causal analysis into diversified and logical response generation","authors":"Liu","year":"2022","venue":"Proceedings of the 29th International Conference on Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Liu et al., 2022b] Yifan Liu, Wei Wei, Jiayi Liu, Xianling Mao, Rui Fang, and Dangyang Chen. Improving per- sonality consistency in conversation by persona extending. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pages 1350- 1359, 2022.","title":"Improving personality consistency in conversation by persona extending","authors":"Liu","year":"2022","venue":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Liu et al., 2023a] Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. Lost in the middle: How language mod- els use long contexts. arXiv preprint arXiv:2307.03172, 2023.","title":"Lost in the middle: How language models use long contexts","authors":"Liu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Liu et al., 2023b] Yijin Liu, Xianfeng Zeng, Fandong Meng, and Jie Zhou. Instruction position matters in se- quence generation with large language models. arXiv preprint arXiv:2308.12097, 2023.","title":"Instruction position matters in sequence generation with large language models","authors":"Liu","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Liu et al., 2024] Zhongkun Liu, Zheng Chen, Mengqi Zhang, Zhaochun Ren, Zhumin Chen, and Pengjie Ren. Zero-shot position debiasing for large language models. arXiv preprint arXiv:2401.01218, 2024.","title":"Zero-shot position debiasing for large language models","authors":"Zhongkun Liu, Zheng Chen, Mengqi Zhang, Zhaochun Ren, Zhumin Chen, Pengjie Ren","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Lu et al., 2023] Zhenyi Lu, Wei Wei, Xiaoye Qu, Xian-Ling Mao, Dangyang Chen, and Jixiong Chen. Miracle: To- wards personalized dialogue generation with latent-space multiple personal attribute control. In Findings of the As- sociation for Computational Linguistics: EMNLP 2023, pages 5933-5957, 2023.","title":"Miracle: Towards personalized dialogue generation with latent-space multiple personal attribute control","authors":"Zhenyi Lu, Wei Wei, Xiaoye Qu, Xian-Ling Mao, Dangyang Chen, Jixiong Chen","year":"2023","venue":"Findings of the Association for Computational Linguistics: EMNLP 2023","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Madhavan et al., 2023] Rahul Madhavan, Rishabh Garg, Kahini Wadhawan, and Sameep Mehta. Cfl: Causally fair language models through token-level attribute controlled generation. In Findings of the Association for Computa- tional Linguistics: ACL 2023, pages 11344-11358, 2023.","title":"Cfl: Causally fair language models through token-level attribute controlled generation","authors":"Rahul Madhavan, Rishabh Garg, Kahini Wadhawan, Sameep Mehta","year":"2023","venue":"Findings of the Association for Computational Linguistics: ACL 2023","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Marshall et al., 2005] William L Marshall, Tony Ward, Ruth E Mann, Heather Moulden, Yolanda M Fernandez, Geris Serran, and Liam E Marshall. Working positively with sexual offenders: Maximizing the effectiveness of treatment. Journal of interpersonal violence, 20(9):1096- 1114, 2005.","title":"Working positively with sexual offenders: Maximizing the effectiveness of treatment","authors":"Tony William L Marshall, Ruth E Ward, Heather Mann, Yolanda M Moulden, Geris Fernandez, Liam E Serran, Marshall","year":"2005","venue":"Journal of interpersonal violence","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Papineni et al., 2002] Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for au- tomatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Com- putational Linguistics, July 6-12, 2002, Philadelphia, PA, USA, pages 311-318. ACL, 2002.","title":"Bleu: a method for automatic evaluation of machine translation","authors":"Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu","year":"2002","venue":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Pearl et al., 2016] Judea Pearl, Madelyn Glymour, and Nicholas P Jewell. Causal inference in statistics: A primer. John Wiley & Sons, 2016.","title":"Causal inference in statistics: A primer","authors":"Pearl","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Peysakhovich and Lerer, 2023] Alexander Peysakhovich and Adam Lerer. Attention sorting combats recency bias in long context language models. arXiv preprint arXiv:2310.01427, 2023.","title":"Attention sorting combats recency bias in long context language models","authors":"Lerer Peysakhovich, Alexander Peysakhovich, Adam Lerer","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Rafetseder et al., 2013] Eva Rafetseder, Maria Schwitalla, and Josef Perner. Counterfactual reasoning: From child- hood to adulthood. Journal of experimental child psychol- ogy, 114(3):389-404, 2013.","title":"Counterfactual reasoning: From childhood to adulthood","authors":"Rafetseder","year":"2013","venue":"Journal of experimental child psychology","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Shanmugam, 2001] Ram Shanmugam. Causality: Models, reasoning, and inference : Judea pearl; cambridge uni- versity press, cambridge, uk, 2000, pp 384, ISBN 0-521- 77362-8. Neurocomputing, 41(1-4):189-190, 2001.","title":"Causality: Models, reasoning, and inference : Judea pearl; cambridge university press, cambridge","authors":"Ram Shanmugam","year":"2000","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Wang et al., 2021] Benyou Wang, Lifeng Shang, Christina Lioma, Xin Jiang, Hao Yang, Qun Liu, and Jakob Grue Si- monsen. On position embeddings in BERT. In 9th Inter- national Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenRe- view.net, 2021.","title":"On position embeddings in BERT","authors":"Wang","year":"2021","venue":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Wang et al., 2023] Qingyue Wang, Liang Ding, Yanan Cao, Zhiliang Tian, Shi Wang, Dacheng Tao, and Li Guo. Recursively summarizing enables long-term dialogue memory in large language models. arXiv preprint arXiv:2308.15022, 2023.","title":"Recursively summarizing enables long-term dialogue memory in large language models","authors":"Qingyue Wang, Liang Ding, Yanan Cao, Zhiliang Tian, Shi Wang, Dacheng Tao, Li Guo","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Wei et al., 2021] Wei Wei, Jiayi Liu, Xianling Mao, Guib- ing Guo, Feida Zhu, Pan Zhou, Yuchong Hu, and Shanshan Feng. Target-guided emotion-aware chat ma- chine. ACM Transactions on Information Systems (TOIS), 39(4):1-24, 2021.","title":"Target-guided emotion-aware chat machine","authors":"Wei Wei, Jiayi Liu, Xianling Mao, Guibing Guo, Feida Zhu, Pan Zhou, Yuchong Hu, Shanshan Feng","year":"2021","venue":"ACM Transactions on Information Systems (TOIS)","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Xu et al., 2022a] Jing Xu, Arthur Szlam, and Jason Weston. Beyond goldfish memory: Long-term open-domain con- versation. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio, editors, Proceedings of the 60th An- nual Meeting of the Association for Computational Lin- guistics (Volume 1: Long Papers), ACL 2022, Dublin, Ire- land, May 22-27, 2022, pages 5180-5197. Association for Computational Linguistics, 2022.","title":"Beyond goldfish memory: Long-term open-domain conversation","authors":"Xu","year":"2022","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Xu et al., 2022b] Xinchao Xu, Zhibin Gou, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Haifeng Wang, and Shihang Wang. Long time no see! open-domain conversation with long-term persona memory. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2639- 2650, 2022.","title":"Long time no see! open-domain conversation with long-term persona memory","authors":"Xu","year":"2022","venue":"Findings of the Association for Computational Linguistics: ACL 2022","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}