{"type":"ScholarlyArticle","title":"TaD: A Plug-and-Play Task-Aware Decoding Method to Better Adapt LLMs on Downstream Tasks","authors":[{"name":"Xinhao Xu","slug":"xinhao-xu","given":"Xinhao","family":"Xu","affiliation":"School of Software , Tsinghua University; Beijing National Research Center for Information Science and Technology (BNRist )"},{"name":"Hui Chen","slug":"hui-chen","given":"Hui","family":"Chen","affiliation":"Beijing National Research Center for Information Science and Technology (BNRist )"},{"name":"Zijia Lin","slug":"zijia-lin","given":"Zijia","family":"Lin","affiliation":"School of Software , Tsinghua University"},{"name":"Jungong Han","slug":"jungong-han","given":"Jungong","family":"Han","affiliation":"Department of Computer Science , University of Sheffield"},{"name":"Lixing Gong","slug":"lixing-gong","given":"Lixing","family":"Gong","affiliation":""},{"name":"Guoxin Wang","slug":"guoxin-wang","given":"Guoxin","family":"Wang","affiliation":""},{"name":"Yongjun Bao","slug":"yongjun-bao","given":"Yongjun","family":"Bao","affiliation":""},{"name":"Guiguang Ding","slug":"guiguang-ding","given":"Guiguang","family":"Ding","affiliation":"School of Software , Tsinghua University; Beijing National Research Center for Information Science and Technology (BNRist )"}],"abstract":"Fine-tuning pre-trained models on downstream tasks is a common practice in leveraging large language models (LLMs) today. A critical issue is how to adapt pre-trained models to downstream tasks better, thereby enhancing their performance. This paper introduces Task-aware Decoding (TaD), a plug-and-play method that exploits the difference in probability distributions before and after fine-tuning to boost the performance of LLMs on downstream tasks. The proposed TaD argues that the difference between the pre-finetuning probability distribution and the post-finetuning one represents the direction from common knowledge towards specific downstream-task knowledge. Aligning the final output probability distribution to that direction can probably result in superior downstream task performance, compared to the original fine-tuned model. Experiments on various datasets across four different task categories well demonstrate TaD's effectiveness on different LLMs, i.e., GPT, BLOOM, and LLaMA, with different fine-tuning methods. Moreover, further experiments reveal that TaD better enhances model performance in data-scarce scenarios.","doi":"10.24963/ijcai.2024/728","url":"https://ijcai.org/proceedings/2024/728","pdf":"https://ijcai.org/proceedings/2024/0728.pdf","markdown":"https://ijcai.org/proceedings/2024/728.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/728","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":728,"pages":{"first":6587,"last":6596},"keywords":["Natural Language Processing: NLP: Language generation","Natural Language Processing: NLP: Applications","Natural Language Processing: NLP: Language models"],"videos":[],"references":[{"position":1,"raw":"[Bisk et al., 2020] Yonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao, and Yejin Choi. Piqa: Reason- ing about physical commonsense in natural language. In Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020.","title":"Piqa: Reason-ing about physical commonsense in natural language","authors":"Yonatan Bisk, Rowan Zellers, Le Ronan, Jianfeng Bras, Yejin Gao, Choi","year":"2020","venue":"Thirty-Fourth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Brown et al., 2020] Tom Brown, Benjamin Mann, Nick Ry- der, Melanie Subbiah, Jared D Kaplan, Prafulla Dhari- wal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing sys- tems, 33:1877-1901, 2020.","title":"Language models are few-shot learners","authors":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2020] Hui Chen, Guiguang Ding, Xudong Liu, Zijia Lin, Ji Liu, and Jungong Han. Imram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval. In Proceedings of the IEEE/CVF con- ference on computer vision and pattern recognition, pages 12655-12663, 2020.","title":"Imram: Iterative matching with recurrent attention memory for cross-modal image-text retrieval","authors":"Hui Chen, Guiguang Ding, Xudong Liu, Zijia Lin, Ji Liu, Jungong Han","year":"2020","venue":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Christiano et al., 2017] Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. Deep reinforcement learning from human preferences. Advances in neural information processing systems, 30, 2017.","title":"Deep reinforcement learning from human preferences","authors":"Jan Paul F Christiano, Tom Leike, Miljan Brown, Shane Martic, Dario Legg, Amodei","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chuang et al., 2023] Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, and Pengcheng He. Dola: Decoding by contrasting layers improves factuality in large language models. arXiv preprint arXiv:2309.03883, 2023.","title":"Dola: Decoding by contrasting layers improves factuality in large language models","authors":"Yung-Sung Chuang, Yujia Xie, Hongyin Luo, Yoon Kim, James Glass, Pengcheng He","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Clark et al., 2019] Christopher Clark, Kenton Lee, Ming- Wei Chang, Tom Kwiatkowski, Michael Collins, and Kristina Toutanova. BoolQ: Exploring the surprising dif- ficulty of natural yes/no questions. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Lan- guage Technologies, Volume 1 (Long and Short Papers), pages 2924-2936, Minneapolis, Minnesota, June 2019. Association for Computational Linguistics.","title":"BoolQ: Exploring the surprising difficulty of natural yes/no questions","authors":"Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, Kristina Toutanova","year":"2019","venue":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cobbe et al., 2021] Karl Cobbe, Vineet Kosaraju, Moham- mad Bavarian, Jacob Hilton, Reiichiro Nakano, Christo- pher Hesse, and John Schulman. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021.","title":"Training verifiers to solve math word problems","authors":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, John Schulman","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Ding et al., 2021] Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, and Jian Sun. Repvgg: Making vgg-style convnets great again. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13733-13742, 2021.","title":"Repvgg: Making vgg-style convnets great again","authors":"Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, Jian Sun","year":"2021","venue":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Ding et al., 2023] Ning Ding, Yujia Qin, Guang Yang, Fuchao Wei, Yang Zonghan, Yusheng Su, Shengding Hu, Yulin Chen, Chi-Min Chan, Weize Chen, Jing Yi, Weilin Zhao, Xiaozhi Wang, Zhiyuan Liu, Hai-Tao Zheng, Jianfei Chen, Yang Liu, Jie Tang, Juanzi Li, and Maosong Sun. Parameter-efficient fine-tuning of large-scale pre-trained language models. Nature Machine Intelligence, 5:1-16, 03 2023.","title":"Parameter-efficient fine-tuning of large-scale pre-trained language models","authors":"Ning Ding, Yujia Qin, Guang Yang, Fuchao Wei, Yang Zonghan, Yusheng Su, Shengding Hu, Yulin Chen, Chi-Min Chan, Weize Chen, Jing Yi, Weilin Zhao, Xiaozhi Wang, Zhiyuan Liu, Hai-Tao Zheng, Jianfei Chen, Yang Liu, Jie Tang, Juanzi Li, Maosong Sun","year":"2023","venue":"Nature Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fan et al., 2018] Angela Fan, Mike Lewis, and Yann Dauphin. Hierarchical neural story generation. In Pro- ceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 2018.","title":"Hierarchical neural story generation","authors":"Angela Fan, Mike Lewis, Yann Dauphin","year":"2018","venue":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gera et al., 2023] Ariel Gera, Roni Friedman, Ofir Arviv, Chulaka Gunasekara, Benjamin Sznajder, Noam Slonim, and Eyal Shnarch. The benefits of bad advice: Autocon- trastive decoding across model layers. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Pro- ceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10406-10420, Toronto, Canada, July 2023. Associ- ation for Computational Linguistics.","title":"The benefits of bad advice: Autocontrastive decoding across model layers","authors":"Ariel Gera, Roni Friedman, Ofir Arviv, Chulaka Gunasekara, Benjamin Sznajder, Noam Slonim, Eyal Shnarch","year":"2023","venue":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He et al., 2022] Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, and Graham Neubig. Towards a unified view of parameter-efficient transfer learning. In International Conference on Learning Representations, 2022.","title":"Towards a unified view of parameter-efficient transfer learning","authors":"He","year":"2022","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hernandez et al., 2023] Evan Hernandez, Belinda Z Li, and Jacob Andreas. Measuring and manipulating knowl- edge representations in language models. arXiv preprint arXiv:2304.00740, 2023.","title":"Measuring and manipulating knowledge representations in language models","authors":"Evan Hernandez, Belinda Z Li, Jacob Andreas","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Holtzman et al., 2019] Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. The curious case of neural text degeneration. In International Conference on Learning Representations, 2019.","title":"The curious case of neural text degeneration","authors":"Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, Yejin Choi","year":"2019","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Houlsby et al., 2019] Neil Houlsby, Andrei Giurgiu, Stanis- law Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. Parameter-efficient transfer learning for nlp. In Interna- tional Conference on Machine Learning, 2019.","title":"Parameter-efficient transfer learning for nlp","authors":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, Sylvain Gelly","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Hu et al., 2021] Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021.","title":"Lora: Low-rank adaptation of large language models","authors":"J Edward, Yelong Hu, Phillip Shen, Zeyuan Wallis, Yuanzhi Allen-Zhu, Shean Li, Lu Wang, Weizhu Wang, Chen","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Hu et al., 2023] Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Sou- janya Poria, and Roy Lee. LLM-adapters: An adapter fam- ily for parameter-efficient fine-tuning of large language models. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5254- 5276, Singapore, December 2023. Association for Com- putational Linguistics.","title":"LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models","authors":"Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, Roy Lee","year":"2023","venue":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Kadavath et al., 2022] Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield Dodds, Nova Das- Sarma, Eli Tran-Johnson, et al. Language models (mostly) know what they know. arXiv preprint arXiv:2207.05221, 2022.","title":"Language models (mostly) know what they know","authors":"Saurav Kadavath, Tom Conerly, Amanda Askell, Tom Henighan, Dawn Drain, Ethan Perez, Nicholas Schiefer, Zac Hatfield Dodds, Nova Das-Sarma, Eli Tran-Johnson","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lester et al., 2021] Brian Lester, Rami Al-Rfou, and Noah Constant. The power of scale for parameter-efficient prompt tuning. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih, editors, Pro- ceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021, pages 3045-3059. Association for Computational Linguistics, 2021.","title":"The power of scale for parameter-efficient prompt tuning","authors":"Brian Lester, Rami Al-Rfou, Noah Constant","year":"2021","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Li and Liang, 2021] Xiang Lisa Li and Percy Liang. Prefix- tuning: Optimizing continuous prompts for generation. In Chengqing Zong, Fei Xia, Wenjie Li, and Roberto Navigli, editors, Proceedings of the 59th Annual Meeting of the As- sociation for Computational Linguistics and the 11th In- ternational Joint Conference on Natural Language Pro- cessing, ACL/IJCNLP 2021, (Volume 1: Long Papers), Virtual Event, August 1-6, 2021, pages 4582-4597. As- sociation for Computational Linguistics, 2021.","title":"Prefixtuning: Optimizing continuous prompts for generation","authors":"Lisa Xiang, Percy Li, Liang","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, ACL/IJCNLP 2021","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Li et al., 2022] Yuchao Li, Fuli Luo, Chuanqi Tan, Mengdi Wang, Songfang Huang, Shen Li, and Junjie Bai. Parameter-effcient sparsity for large language models fine- tuning. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022, pages 4223-4229. ij- cai.org, 2022.","title":"Parameter-effcient sparsity for large language models finetuning","authors":"Li","year":"2022","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Li et al., 2023a] Kenneth Li, Aspen K Hopkins, David Bau, Fernanda Viégas, Hanspeter Pfister, and Martin Watten- berg. Emergent world representations: Exploring a se- quence model trained on a synthetic task. In The Eleventh International Conference on Learning Representations, 2023.","title":"Emergent world representations: Exploring a sequence model trained on a synthetic task","authors":"Li","year":"2023","venue":"The Eleventh International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Li et al., 2023b] Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. Inference-time intervention: Eliciting truthful answers from a language model. arXiv preprint arXiv:2306.03341, 2023.","title":"Inference-time intervention: Eliciting truthful answers from a language model","authors":"Li","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Li et al., 2023c] Xiang Lisa Li, Ari Holtzman, Daniel Fried, Percy Liang, Jason Eisner, Tatsunori Hashimoto, Luke Zettlemoyer, and Mike Lewis. Contrastive decoding: Open-ended text generation as optimization. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, edi- tors, Proceedings of the 61st Annual Meeting of the As- sociation for Computational Linguistics (Volume 1: Long Papers), pages 12286-12312, Toronto, Canada, July 2023. Association for Computational Linguistics.","title":"Contrastive decoding: Open-ended text generation as optimization","authors":"Li","year":"2023","venue":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Lin et al., 2022] Stephanie Lin, Jacob Hilton, and Owain Evans. Truthfulqa: Measuring how models mimic human falsehoods. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3214-3252, 2022.","title":"Truthfulqa: Measuring how models mimic human falsehoods","authors":"Stephanie Lin, Jacob Hilton, Owain Evans","year":"2022","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Muennighoff et al., 2022] Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Bider- man, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng- Xin Yong, Hailey Schoelkopf, et al. Crosslingual gen- eralization through multitask finetuning. arXiv preprint arXiv:2211.01786, 2022. [","title":"Crosslingual generalization through multitask finetuning","authors":"Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[OpenAI, 2023] OpenAI. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.","title":null,"authors":"Openai","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Ouyang et al., 2022] Long Ouyang, Jeff 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. Training language models to follow instructions with human feed- back. CoRR, abs/2203.02155, 2022.","title":"Training language models to follow instructions with human feedback","authors":"Long Ouyang, Jeff 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, Ryan Lowe","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Pfeiffer et al., 2020] Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, and Sebastian Ruder. MAD-X: An Adapter- Based Framework for Multi-Task Cross-Lingual Transfer. In Bonnie Webber, Trevor Cohn, Yulan He, and Yang Liu, editors, Proceedings of the 2020 Conference on Empiri- cal Methods in Natural Language Processing (EMNLP), pages 7654-7673, Online, November 2020. Association for Computational Linguistics.","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","authors":"Pfeiffer","year":"2020","venue":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Roy and Roth, 2016] Subhro Roy and Dan Roth. Solv- ing general arithmetic word problems. arXiv preprint arXiv:1608.01413, 2016.","title":"Solving general arithmetic word problems","authors":"Roy, Roth ;, Subhro Roy, Dan Roth","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Sanh et al., 2022] Victor Sanh, Albert Webson, Colin Raf- fel, Stephen Bach, Lintang Sutawika, Zaid Alyafeai, An- toine Chaffin, Arnaud Stiegler, Arun Raja, Manan Dey, et al. Multitask prompted training enables zero-shot task generalization. In International Conference on Learning Representations, 2022.","title":"Multitask prompted training enables zero-shot task generalization","authors":"Victor Sanh, Albert Webson, Colin Raffel, Stephen Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Arun Raja, Manan Dey","year":"2022","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Subramani et al., 2022] Nishant Subramani, Nivedita Suresh, and Matthew E Peters. Extracting latent steering vectors from pretrained language models. arXiv preprint arXiv:2205.05124, 2022.","title":"Extracting latent steering vectors from pretrained language models","authors":"Nishant Subramani, Nivedita Suresh, Matthew E Peters","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks. Advances in neural information processing sys- tems, 27, 2014.","title":"Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Touvron et al., 2023] Hugo Touvron, Thibaut Lavril, Gau- tier Izacard, Xavier Martinet, Marie-Anne Lachaux, Tim- othée Lacroix, Baptiste Rozière, Naman Goyal, Eric Ham- bro, Faisal Azhar, et al. Llama: Open and efficient founda- tion language models. arXiv preprint arXiv:2302.13971, 2023.","title":"Hugo Touvron, Thibaut Lavril, Gautier Izacard","authors":"Touvron","year":"2023","venue":"Llama: Open and efficient foundation language models","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Turner et al., 2023] Alex Turner, Monte M, David Udell, Lisa Theirgart, and Ulisse Mini. Steering gpt-2-xl by adding an activation vector, May 2023.","title":"Steering gpt-2-xl by adding an activation vector","authors":"Alex Turner, Monte M, David Udell, Lisa Theirgart, Ulisse Mini","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Wang and Komatsuzaki, 2021] Ben Wang and Aran Ko- matsuzaki. GPT-J-6B: A 6 Billion Parameter Autore- gressive Language Model. https://github.com/kingoflolz/ mesh-transformer-jax, May 2021.","title":"GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model","authors":"Ben Wang, Aran Komatsuzaki","year":"2021","venue":null,"doi":null,"url":"https://github.com/kingoflolz/mesh-transformer-jax","internal_url":null},{"position":37,"raw":"[Wang et al., 2023] Ao Wang, Hui Chen, Zijia Lin, Hengjun Pu, and Guiguang Ding. Repvit: Revisiting mobile cnn from vit perspective. arXiv preprint arXiv:2307.09283, 2023.","title":"Repvit: Revisiting mobile cnn from vit perspective","authors":"Ao Wang, Hui Chen, Zijia Lin, Hengjun Pu, Guiguang Ding","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Wei et al., 2021] Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, An- drew M Dai, and Quoc V Le. Finetuned language mod- els are zero-shot learners. In International Conference on Learning Representations, 2021.","title":"Finetuned language models are zero-shot learners","authors":"Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, Quoc V Le","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Xiong et al., 2024] Yizhe Xiong, Hui Chen, Tianxiang Hao, Zijia Lin, Jungong Han, Yuesong Zhang, Guoxin Wang, Yongjun Bao, and Guiguang Ding. Pyra: Parallel yield- ing re-activation for training-inference efficient task adap- tation. arXiv preprint arXiv:2403.09192, 2024.","title":"Pyra: Parallel yielding re-activation for training-inference efficient task adaptation","authors":"Xiong","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}