Elamur Research⌕
☰
home / papers / 2024 / ReFT: Representation Finetuning for Language Models

ReFT: Representation Finetuning for Language Models

Paper · 2024 · Zhengxuan Wu, Aryaman Arora, Zheng Wang et al.

Summary

Most parameter-efficient finetuning (PEFT) techniques, such as LoRA, adapt a model by changing a small set of its weights. Interpretability research suggests that hidden states carry rich, often linearly organised meaning. Building on this, the authors propose Representation Finetuning (ReFT). The base model stays frozen, and small trainable interventions edit hidden representations at selected layers and token positions. The main variant, LoReFT, comes from distributed interchange interventions and distributed alignment search (DAS). It changes a representation only inside a low-rank subspace given by a projection matrix R with orthonormal rows, where the coordinates are set to a learned linear map Wh + b. A cheaper ablation, DiReFT, removes the orthogonality constraint and the difference term, so it resembles LoRA applied to activations. The methods were tested on LLaMA, Llama-2, Llama-3 and RoBERTa models across commonsense reasoning, arithmetic reasoning, instruction-following and GLUE. LoReFT trains 15×–65× fewer parameters than LoRA and matches or beats the strongest PEFTs on most benchmarks. This makes representation editing a practical and interpretable alternative to weight-based adaptation.

Key points

  • Formulation: LoReFT computes Φ(h) = h + Rᵀ(Wh + b − Rh) and learns only R, W and b. DiReFT computes h + W₂ᵀ(W₁h + b), which trains faster but performs somewhat worse.
  • Benchmarks and models: The evaluation covers eight commonsense and four arithmetic reasoning tasks, instruction-tuning, and GLUE. The models are LLaMA 7B/13B, Llama-2 7B, Llama-3 8B, and RoBERTa-base/large.
  • Results: The authors report new state-of-the-art results against leading PEFTs on commonsense reasoning, instruction-following and NLU, but not on arithmetic. On GLUE, LoReFT is comparable to RED at matched parameter counts. DiReFT falls behind most PEFTs on the smaller LMs.
  • Evaluation protocol: Hyperparameters are tuned per task on development data kept separate from the test data. Scores are averaged over five seeds. The GLUE validation sets are split by seed into a model-selection half and a test half. The authors criticise PEFT papers that tune directly on test sets.
  • Resources and limitations: The training library is released as pyreft (github.com/stanfordnlp/pyreft). Experiments focus mainly on the LLaMA family. Other model families, vision–language models such as LLaVA, and automated hyperparameter search are left for future work.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,894 works

Cite

Cite as Zhengxuan Wu, Aryaman Arora, Zheng Wang, Atticus Geiger, Dan Jurafsky, Christopher D. Manning and Christopher Potts. 2024. ReFT: Representation Finetuning for Language Models. arXiv:2404.03592.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2404.03592 · arXiv 2404.03592

@misc{wu2024reft,
  title = {{ReFT: Representation Finetuning for Language Models}},
  author = {Zhengxuan Wu, Aryaman Arora, Zheng Wang, Atticus Geiger, Dan Jurafsky, Christopher D. Manning and Christopher Potts},
  year = {2024},
  doi = {10.48550/arxiv.2404.03592},
  eprint = {2404.03592},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2404.03592}
}

References

96 references, 41 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Afra Amini, Tiago Pimentel, Clara Meister, and Ryan Cotterell. Naturalistic causal probing for morpho-syntax. Transactions of the Association for Computational Linguistics, 11:384–403, 2023. doi: 10.1162/tacl_a_00554. URL https://aclanthology.org/2023.tacl-1.23 . ↗
  2. Aryaman Arora, Dan Jurafsky, and Christopher Potts. CausalGym: Benchmarking causal interpretability methods on linguistic tasks. arXiv:2402.12560, 2024. URL https://arxiv.org/abs/ 2402.12560 . ↗
  3. Matan Avitan, Ryan Cotterell, Yoav Goldberg, and Shauli Ravfogel. What changed? Converting representational interventions to natural language. arXiv:2402.11355, 2024. URL https://arxiv.org/abs/2402.11355 . — [arXiv:2402.11355](https://arxiv.org/abs/2402.11355) ↗
  4. Nora Belrose, David Schneider-Joseph, Shauli Ravfogel, Ryan Cotterell, Edward Raff, and Stella Biderman. LEACE: Perfect linear concept erasure in closed form. Advances in Neural Information Processing Systems, 36, 2023. URL https://proceedings.neurips.cc/paper_files/paper/2023/ file/d066d21c619d0a78… ↗
  5. Elad Ben Zaken, Yoav Goldberg, and Shauli Ravfogel. BitFit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguisti…
  6. Yonatan Bisk, Rowan Zellers, Jianfeng Gao, Yejin Choi, et al. PIQA: Reasoning about physical commonsense in natural language. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 7432–7439, 2020. URL https://arxiv.org/abs/1911.11641 . ↗
  7. Lewis Carroll. Alice’s Adventures in Wonderland. Macmillan, London, 1865. find
  8. Angelica Chen, Ravid Schwartz-Ziv, Kyunghyun Cho, Matthew L. Leavitt, and Naomi Saphra. Sudden drops in the loss: Syntax acquisition, phase transitions, and simplicity bias in MLMs. arXiv:2309.07311, 2023. URL https://arxiv.org/abs/2309.07311v4 . ↗
  9. Abhijith Chintam, Rahel Beloch, Willem Zuidema, Michael Hanna, and Oskar van der Wal. Identifying and adapting transformer-components responsible for gender bias in an English language model. In Yonatan Belinkov, Sophie Hao, Jaap Jumelet, Najoung Kim, Arya Mc-Carthy, and Hosein Mohebbi, editors, Pro…
  10. Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, and Kristina Toutanova. BoolQ: Exploring the surprising difficulty of natural yes/no questions. In Jill Burstein, Christy Doran, and Thamar Solorio, editors, Proceedings of the 2019 Conference of the North American Chap…
  11. Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. Think you have solved question answering? Try ARC, the AI2 reasoning challenge. arXiv:1803.05457, 2018. URL https://arxiv.org/abs/1803.05457 . ↗
  12. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. Training verifiers to solve math word problems. arXiv:2110.14168, 2021. URL https://arxiv.org/abs/2110.14168 . ↗
  13. Ganqu Cui, Lifan Yuan, Ning Ding, Guanming Yao, Wei Zhu, Yuan Ni, Guotong Xie, Zhiyuan Liu, and Maosong Sun. UltraFeedback: Boosting language models with high-quality feedback. arXiv:2310.01377, 2023. URL https://arxiv.org/abs/2310.01377 . ↗
  14. Andrew M. Dai and Quoc V. Le. Semi-supervised sequence learning. In Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc., 2015. URL https://proceedings.neurips.cc/paper/2015/hash/7137debd45ae4d0ab9aa953017286b20-Abstract.html . ↗
  15. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understanding. In Jill Burstein, Christy Doran, and Thamar Solorio, editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Co…
  16. Ning Ding, Yulin Chen, Bokai Xu, Yujia Qin, Shengding Hu, Zhiyuan Liu, Maosong Sun, and Bowen Zhou. Enhancing chat language models by scaling high-quality instructional conversations. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Proceedings of the 2023 Conference on Empirical Methods in Na…
  17. Nelson Elhage, Tristan Hume, Catherine Olsson, Nicholas Schiefer, Tom Henighan, Shauna Kravec, Zac Hatfield-Dodds, Robert Lasenby, Dawn Drain, Carol Chen, Roger Grosse, Sam McCandlish, Jared Kaplan, Dario Amodei, Martin Wattenberg, and Christopher Olah. Toy models of superposition. Transformer Circu… find
  18. Stanislav Fort. Scaling laws for adversarial attacks on language model activations, 2023. URL http://arxiv.org/abs/2312.02780 . — [arXiv:2312.02780](https://arxiv.org/abs/2312.02780) ↗
  19. Cheng Fu, Hanxian Huang, Xinyun Chen, Yuandong Tian, and Jishen Zhao. Learn-to-Share: A hardware-friendly transfer learning framework exploiting computation and parameter sharing. In Marina Meila and Tong Zhang, editors, Proceedings of the 38th International Conference on Machine Learning, ICML 2021… find
  20. PMLR, 2021. URL http://proceedings.mlr.press/v139/fu21a.html . ↗
  21. Peng Gao, Jiaming Han, Renrui Zhang, Ziyi Lin, Shijie Geng, Aojun Zhou, Wei Zhang, Pan Lu, Conghui He, Xiangyu Yue, et al. LLaMA-Adapter v2: Parameter-efficient visual instruction model. arXiv:2304.15010, 2023. URL https://arxiv.org/abs/2304.15010 . ↗
  22. Atticus Geiger, Hanson Lu, Thomas Icard, and Christopher Potts. Causal abstractions of neural networks. In M. Ranzato, A. Beygelzimer, Y. Dauphin, P.S. Liang, and J. Wortman Vaughan, editors, Advances in Neural Information Processing Systems, volume 34, pages 9574–9586. Curran Associates, Inc., 2021… find
  23. Atticus Geiger, Zhengxuan Wu, Hanson Lu, Josh Rozner, Elisa Kreiss, Thomas Icard, Noah Goodman, and Christopher Potts. Inducing causal structure for interpretable neural networks. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato, editors, Proceedings of… find
  24. Atticus Geiger, Chris Potts, and Thomas Icard. Causal abstraction for faithful model interpretation. arXiv:2301.04709, 2023a. URL https://arxiv.org/abs/2301.04709 . ↗
  25. Atticus Geiger, Zhengxuan Wu, Christopher Potts, Thomas Icard, and Noah D. Goodman. Finding alignments between interpretable causal variables and distributed neural representations. arXiv:2303.02536, 2023b. URL https://arxiv.org/abs/2303.02536 . ↗
  26. Clément Guerner, Anej Svete, Tianyu Liu, Alexander Warstadt, and Ryan Cotterell. A geometric notion of causal probing. arXiv:2307.15054, 2023. URL https://arxiv.org/abs/2307.15054 . — [arXiv:2307.15054](https://arxiv.org/abs/2307.15054) ↗
  27. Michael Hanna, Yonatan Belinkov, and Sandro Pezzelle. When language models fall in love: Animacy processing in transformer language models. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12120–12135… find
  28. Sophie Hao and Tal Linzen. Verb conjugation in transformers is determined by linear encodings of subject number. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4531–4539, Singapore, December 2023. Association for Co… find
  29. Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, and Graham Neubig. Towards a unified view of parameter-efficient transfer learning. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 2022a. URL https://openreview.net/ forum?id=0RDcd5Axok . ↗
  30. Shwai He, Liang Ding, Daize Dong, Jeremy Zhang, and Dacheng Tao. SparseAdapter: An easy approach for improving the parameter-efficiency of adapters. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors, Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2184–2190, Ab… find
  31. Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, and Nate Kushman. Learning to solve arithmetic word problems with verb categorization. In Alessandro Moschitti, Bo Pang, and Walter Daelemans, editors, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (…
  32. Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. Parameter-efficient transfer learning for NLP. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on… find
  33. PMLR, 2019. URL http://proceedings.mlr.press/v97/houlsby19a.html . ↗
  34. 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. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 2022. URL https://openreview.net/forum?id=nZ… ↗
  35. Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, and Roy Lee. LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models. In Houda Bouamor, Juan Pino, and Kalika Bali, editors, Proceedings of the 2023 Conference on Empi…
  36. Chengsong Huang, Qian Liu, Bill Yuchen Lin, Tianyu Pang, Chao Du, and Min Lin. LoraHub: Efficient cross-task generalization via dynamic lora composition. arXiv:2307.13269, 2023a. URL https://arxiv.org/abs/2307.13269 . ↗
  37. Jing Huang, Atticus Geiger, Karel D’Oosterlinck, Zhengxuan Wu, and Christopher Potts. Rigorously assessing natural language explanations of neurons. In Yonatan Belinkov, Sophie Hao, Jaap Jumelet, Najoung Kim, Arya McCarthy, and Hosein Mohebbi, editors, Proceedings of the 6th BlackboxNLP Workshop: An…
  38. Jing Huang, Zhengxuan Wu, Kyle Mahowald, and Christopher Potts. Inducing character-level structure in subword-based language models with type-level interchange intervention training. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Findings of the Association for Computational Lingui… find
  39. Jing Huang, Christopher Potts Zhengxuan Wu, Mor Geva, and Atticus Geiger. RAVEL: Evaluating interpretability methods on disentangling language model representations. arXiv:2402.17700, 2024. URL https://arxiv.org/abs/2402.17700 . ↗
  40. Rik Koncel-Kedziorski, Hannaneh Hajishirzi, Ashish Sabharwal, Oren Etzioni, and Siena Dumas Ang. Parsing algebraic word problems into equations. Transactions of the Association for Computational Linguistics, 3:585–597, 2015. doi: 10.1162/tacl_a_00160. URL https://aclanthology.org/ Q15-1042 . ↗
  41. Rik Koncel-Kedziorski, Subhro Roy, Aida Amini, Nate Kushman, and Hannaneh Hajishirzi. MAWPS: A math word problem repository. In Kevin Knight, Ani Nenkova, and Owen Rambow, editors, Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Huma… find
  42. Dawid Jan Kopiczko, Tijmen Blankevoort, and Yuki M Asano. VeRA: Vector-based random matrix adaptation. In The Twelfth International Conference on Learning Representations, ICLR 2024, 2024. URL https://openreview.net/forum?id=NjNfLdxr3A . ↗
  43. Karim Lasri, Tiago Pimentel, Alessandro Lenci, Thierry Poibeau, and Ryan Cotterell. Probing for the usage of grammatical number. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo… find
  44. Hector Levesque, Ernest Davis, and Leora Morgenstern. The Winograd Schema Challenge. In Proceedings of the Thirteenth International Conference on Principles of Knowledge Representation and Reasoning, 2012. URL https://cdn.aaai.org/ocs/4492/4492-21843-1-PB.pdf . ↗
  45. Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, and Martin Wattenberg. Inference-time intervention: Eliciting truthful answers from a language model. Advances in Neural Information Processing Systems, 36, 2024. URL https://proceedings.neurips.cc/paper_files/paper/2023/ hash/81b8390039b730… ↗
  46. Margaret Li, Suchin Gururangan, Tim Dettmers, Mike Lewis, Tim Althoff, Noah A. Smith, and Luke Zettlemoyer. Branch-train-merge: Embarrassingly parallel training of expert language models. arXiv:2208.03306, 2022. URL https://arxiv.org/abs/2208.03306 . ↗
  47. 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 Association for Computational Linguistics and the 11th International Joint Conference on Natu… find
  48. Xuechen Li, Tianyi Zhang, Yann Dubois, Rohan Taori, Ishaan Gulrajani, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. AlpacaEval: An automatic evaluator of instruction-following models. https://github.com/tatsu-lab/alpaca_eval , 2023. ↗
  49. Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. Program induction by rationale generation: Learning to solve and explain algebraic word problems. arXiv:1705.04146, 2017. URL https://arxiv.org/abs/1705.04146 . ↗
  50. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. Visual instruction tuning. Advances in Neural Information Processing Systems, 36, 2024a. URL https://arxiv.org/abs/2304.08485 . ↗
  51. Sheng Liu, Haotian Ye, Lei Xing, and James Zou. In-context vectors: Making in context learning more effective and controllable through latent space steering. arXiv:2311.06668, 2024b. URL https://arxiv.org/abs/2311.06668 . ↗
  52. Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, and Min-Hung Chen. DoRA: Weight-decomposed low-rank adaptation. arXiv:2402.09353, 2024c. URL https://arxiv.org/abs/2402.09353 . ↗
  53. Weiyang Liu, Zeju Qiu, Yao Feng, Yuliang Xiu, Yuxuan Xue, Longhui Yu, Haiwen Feng, Zhen Liu, Juyeon Heo, Songyou Peng, Yandong Wen, Michael J. Black, Adrian Weller, and Bernhard Schölkopf. Parameter-efficient orthogonal finetuning via butterfly factorization. In The Twelfth International Conference… find
  54. URL Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. RoBERTa: A robustly optimized BERT pretraining approach. arXiv:1907.11692, 2019. URL https://arxiv.org/abs/1907.11692 . ↗
  55. James L. McClelland, David E. Rumelhart, and PDP Research Group. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, volume 2: Psychological and Biological Models. MIT Press, 1986. find
  56. Todor Mihaylov, Peter Clark, Tushar Khot, and Ashish Sabharwal. Can a suit of armor conduct electricity? A new dataset for open book question answering. arXiv:1809.02789, 2018. URL https://arxiv.org/abs/1809.02789 . ↗
  57. Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. Linguistic regularities in continuous space word representations. In Lucy Vanderwende, Hal Daumé III, and Katrin Kirchhoff, editors, Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Huma…
  58. Neel Nanda, Andrew Lee, and Martin Wattenberg. Emergent linear representations in world models of self-supervised sequence models. In Yonatan Belinkov, Sophie Hao, Jaap Jumelet, Najoung Kim, Arya McCarthy, and Hosein Mohebbi, editors, Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interp…
  59. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35: 27730–27744, 2022. URL htt…
  60. Kiho Park, Yo Joong Choe, and Victor Veitch. The linear representation hypothesis and the geometry of large language models. arXiv:2311.03658, 2023. URL https://arxiv.org/abs/2311.03658 . ↗
  61. Arkil Patel, Satwik Bhattamishra, and Navin Goyal. Are NLP models really able to solve simple math word problems? In Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, and Yichao Zhou, editors, Proceedings of the 2…
  62. 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 Empirical Methods in Natural Language Processing (EMNLP), p…
  63. Shauli Ravfogel, Michael Twiton, Yoav Goldberg, and Ryan D. Cotterell. Linear adversarial concept erasure. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato, editors, Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proc… find
  64. Subhro Roy and Dan Roth. Solving general arithmetic word problems. In Lluís Màrquez, Chris Callison-Burch, and Jian Su, editors, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1743–1752, Lisbon, Portugal, September 2015. Association for Computational Li…
  65. David E. Rumelhart, James L. McClelland, and PDP Research Group. Parallel Distributed Processing: Explorations in the Microstructure of Cognition, volume 1: Foundations. MIT Press, 1986. find
  66. Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. WinoGrande: An adversarial Winograd Schema Challenge at scale. Communications of the ACM, 64(9):99–106, 2021. URL https://arxiv.org/abs/1907.10641 . ↗
  67. Maarten Sap, Hannah Rashkin, Derek Chen, Ronan Le Bras, and Yejin Choi. Social IQa: Commonsense reasoning about social interactions. In Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan, editors, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th I… find
  68. Shuhua Shi, Shaohan Huang, Minghui Song, Zhoujun Li, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, and Qi Zhang. ResLoRA: Identity residual mapping in low-rank adaption. arXiv:2402.18039, 2024. URL https://arxiv.org/abs/2402.18039 . ↗
  69. Shashwat Singh, Shauli Ravfogel, Jonathan Herzig, Roee Aharoni, Ryan Cotterell, and Ponnurangam Kumaraguru. MiMiC: Minimally modified counterfactuals in the representation space. arXiv:2402.09631, 2024. URL https://arxiv.org/abs/2402.09631 . — [arXiv:2402.09631](https://arxiv.org/abs/2402.09631) ↗
  70. Paul Smolensky. Neural and conceptual interpretation of PDP models. In Parallel Distributed Processing: Explorations in the Microstructure of Cognition, volume 2: Psychological and Biological Models, pages 390–431. MIT Press/Bradford Books, Cambridge, MA, 1986. find
  71. Nishant Subramani, Nivedita Suresh, and Matthew E. Peters. Extracting latent steering vectors from pretrained language models. arXiv:2205.05124, 2022. URL https://arxiv.org/abs/2205.05124 . ↗
  72. Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. Stanford Alpaca: An instruction-following LLaMA model. https://github.com/tatsu-lab/stanford_alpaca , 2023. ↗
  73. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. LLaMA: Open and efficient foundation language models. arXiv:2302.139…
  74. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  75. Alex Turner, Lisa Thiergart, David Udell, Gavin Leech, Ulisse Mini, and Monte MacDiarmid. Activation addition: Steering language models without optimization. arXiv:2308.10248, 2023. URL https://arxiv.org/abs/2308.10248 . ↗
  76. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Sy…
  77. Theia Vogel. repeng, 2024. URL https://github.com/vgel/repeng/ . ↗
  78. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Tal Linzen, Grzegorz Chrupała, and Afra Alishahi, editors, Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and…
  79. Kevin Ro Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, and Jacob Steinhardt. Interpretability in the wild: a circuit for indirect object identification in GPT-2 small. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, 2023. URL https://openr… find
  80. Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, and Jianfeng Gao. AdaMix: Mixture-of-adaptations for parameter-efficient model tuning. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors, Proceedings of the 2022 Conference on Empirical Method…
  81. Jason Wei, Xuezhi Wang, Dale Schuurmans, 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. URL https://arxiv.org/abs/ 2201.11903 . ↗
  82. Muling Wu, Wenhao Liu, Xiaohua Wang, Tianlong Li, Changze Lv, Zixuan Ling, Jianhao Zhu, Cenyuan Zhang, Xiaoqing Zheng, and Xuanjing Huang. Advancing parameter efficiency in fine-tuning via representation editing. arXiv:2402.15179, 2024a. URL https://arxiv.org/abs/2402. 15179 . ↗
  83. Zhengxuan Wu, Atticus Geiger, Joshua Rozner, Elisa Kreiss, Hanson Lu, Thomas Icard, Christopher Potts, and Noah Goodman. Causal distillation for language models. In Marine Carpuat, Marie-Catherine de Marneffe, and Ivan Vladimir Meza Ruiz, editors, Proceedings of the 2022 Conference of the North Amer… find
  84. Zhengxuan Wu, Atticus Geiger, Christopher Potts, and Noah D. Goodman. Interpretability at scale: Identifying causal mechanisms in Alpaca. In Advances in Neural Information Processing Systems, volume 36, 2023. URL https://papers.neurips.cc/paper_files/paper/2023/file/ f6a8b109d4d4fd64c75e94aaf85d9697… ↗
  85. Zhengxuan Wu, Atticus Geiger, Aryaman Arora, Jing Huang, Zheng Wang, Noah D. Goodman, Christopher D. Manning, and Christopher Potts. pyvene: A library for understanding and improving PyTorch models via interventions. In arXiv:2403.07809, 2024b. URL https://arxiv.org/abs/ 2403.07809 . ↗
  86. Zhengxuan Wu, Atticus Geiger, Jing Huang, Aryaman Arora, Thomas Icard, Christopher Potts, and Noah D. Goodman. A reply to Makelov et al. (2023)’s “interpretability illusion” arguments. arXiv:2401.12631, 2024c. URL https://arxiv.org/abs/2401.12631 . ↗
  87. Takateru Yamakoshi, James McClelland, Adele Goldberg, and Robert Hawkins. Causal interventions expose implicit situation models for commonsense language understanding. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Findings of the Association for Computational Linguistics: ACL 2023… find
  88. Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. HellaSwag: Can a machine really finish your sentence? arXiv:1905.07830, 2019. URL https://arxiv.org/abs/1905.07830 . ↗
  89. Feiyu Zhang, Liangzhi Li, Junhao Chen, Zhouqiang Jiang, Bowen Wang, and Yiming Qian. IncreLoRA: Incremental parameter allocation method for parameter-efficient fine-tuning. arXiv:2308.12043, 2023. URL https://arxiv.org/abs/2308.12043 . — [arXiv:2308.12043](https://arxiv.org/abs/2308.12043) ↗
  90. Jinghan Zhang, Shiqi Chen, Junteng Liu, and Junxian He. Composing parameter-efficient modules with arithmetic operation. Advances in Neural Information Processing Systems, 36, 2024a. URL https://arxiv.org/abs/2306.14870 . — [arXiv:2306.14870](https://arxiv.org/abs/2306.14870) ↗
  91. Renrui Zhang, Jiaming Han, Chris Liu, Aojun Zhou, Pan Lu, Hongsheng Li, Peng Gao, and Yu Qiao. LLaMA-Adapter: Efficient fine-tuning of large language models with zero-initialized attention. In The Twelfth International Conference on Learning Representations, Vienna, Austria, 2024b. URL https://openr… find
  92. Ruiyi Zhang, Rushi Qiang, Sai Ashish Somayajula, and Pengtao Xie. AutoLoRA: Automatically tuning matrix ranks in low-rank adaptation based on meta learning. arXiv:2403.09113, 2024c. URL https://arxiv.org/abs/2403.09113 . ↗
  93. Ming Zhong, Yelong Shen, Shuohang Wang, Yadong Lu, Yizhu Jiao, Siru Ouyang, Donghan Yu, Jiawei Han, and Weizhu Chen. Multi-LoRA composition for image generation. arXiv:2402.16843, 2024. URL https://arxiv.org/abs/2402.16843 . — [arXiv:2402.16843](https://arxiv.org/abs/2402.16843) ↗
  94. Yun Zhu, Nevan Wichers, Chu-Cheng Lin, Xinyi Wang, Tianlong Chen, Lei Shu, Han Lu, Canoee Liu, Liangchen Luo, Jindong Chen, et al. SiRa: Sparse mixture of low rank adaptation. arXiv:2311.09179, 2023. URL https://arxiv.org/abs/2311.09179 . — [arXiv:2311.09179](https://arxiv.org/abs/2311.09179) ↗
  95. Zhou Ziheng, Yingnian Wu, Song-Chun Zhu, and Demetri Terzopoulos. Aligner: One global token is worth millions of parameters when aligning large language models. arXiv:2312.05503, 2023. URL https://arxiv.org/abs/2312.05503 . — [arXiv:2312.05503](https://arxiv.org/abs/2312.05503) ↗
  96. Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, and Dan Hendry… — Representation Engineering: A Top-Down Approach to AI Transparency

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wu-2024-reft-representation-finetuning-language-models/