Elamur Research⌕
☰
home / papers / 2026 / Intention-Adaptive LLM Fine-Tuning for Text Revision Generation

Intention-Adaptive LLM Fine-Tuning for Text Revision Generation

Paper · 2026 · Zhexiong Liu and Diane Litman

Summary

Revision generation requires output that reflects what the writer meant to change, such as clarity, fluency or meaning. These intentions are often several and intertwined in a single edit. Prior approaches either lack the capacity to handle multi-intent edits or need more annotated data than revision corpora usually provide. Those approaches include seq2seq models like BART, few-shot prompting of LLMs, and PEFT on large instruction sets.

The authors propose Intention-Tuning, a layer-wise PEFT framework that runs two tasks one after the other:

  • Intention prediction. An LLM learns to classify the intention behind an original/revised text pair. At each step, only layers with high gradient-norm importance scores are updated, following Liu and Litman (2025); the remaining layers stay frozen.
  • Revision generation. How often each layer was selected during prediction determines which layers are tuned for generation. The predictor's LoRA weights are then passed to the generator.

On small corpora such as ITERATER, the method beats several PEFT baselines while remaining efficient. This suggests that knowledge about intentions can be transferred cheaply to low-resource revision generation.

Key points

  • Task formulation. Intention prediction is T_pre = f(I; X, Y), and generation is T_gen = f(Y; X, I). The two tasks are trained sequentially rather than jointly, which keeps the extra cost low compared with standard PEFT.
  • Layer selection and alignment. Each layer's selection frequency over k fine-tuning steps defines the important set for generation. A layer alignment ratio, r = |S_pre ∩ S_gen| / |S_gen|, measures how many layers the two tasks share.
  • Baselines. LISA-Baseline uses 4 randomly chosen layers and IST-Baseline uses the top 8 layers. Generality is also tested across different PEFT adapters (RQ3).
  • Data and models. Data includes ITERATER and ITERATER-sent, plus argumentative essay revisions; example outputs come from Llama3.1-8B. Only lightweight LLMs were used, results are single-run with no significance tests, and evaluation relies on edit-based metrics rather than LLM-as-a-Judge.
  • Missing scores and code. The results section is missing from the provided text, so exact scores cannot be reported here. Code is available at github.com/ZhexiongLiu/Intention-Tuning.

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

 Institutions

🎓University of PittsburghPittsburgh · United States59 works · 22,324 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Zhexiong Liu and Diane Litman. 2026. Intention-Adaptive LLM Fine-Tuning for Text Revision Generation. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-eacl.65

@inproceedings{liu2026intention,
  title = {{Intention-Adaptive LLM Fine-Tuning for Text Revision Generation}},
  author = {Zhexiong Liu and Diane Litman},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.65},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.65}
}

References

58 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Tazin Afrin and Diane Litman. 2018. Annotation and classification of sentence-level revision improvement. In Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications, pages 240–246, New Orleans, Louisiana. find
  2. Tazin Afrin and Diane Litman. 2023. Predicting desirable revisions of evidence and reasoning in argumentative writing. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2550– 2561, Dubrovnik, Croatia. Association for Computational Linguistics. find
  3. Tazin Afrin, Elaine Lin Wang, Diane Litman, Lindsay Clare Matsumura, and Richard Correnti. 2020. Annotation and classification of evidence and reasoning revisions in argumentative writing. In Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications, Seattl… find
  4. Ahmed Agiza, Marina Neseem, and Sherief Reda. 2024. Mtlora: Low-rank adaptation approach for efficient multi-task learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16196–16205. find
  5. Talita Anthonio, Irshad Bhat, and Michael Roth. 2020. wikiHowToImprove: A resource and analyses on edits in instructional texts. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5721–5729, Marseille, France. European Language Resources Association. find
  6. Seungmin Baek, Soyul Lee, Hayeon Jo, Hyesong Choi, and Dongbo Min. 2025. Tadformer: Task-adaptive dynamic transformer for efficient multi-task learning. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 14858–14868. find
  7. Tiancong Cheng, Ying Zhang, Rajiv Ratn Shah, Roger Zimmermann, Zhiwen Yu, and Bin Guo. 2025. Compmtl: Layer-wise competitive multi-task learning. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1–5. IEEE. find
  8. Ruining Chong, Cunliang Kong, Liu Wu, Zhenghao Liu, Ziye Jin, Liner Yang, Yange Fan, Hanghang Fan, and Erhong Yang. 2023. Leveraging prefix transfer for multi-intent text revision. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pa… find
  9. Mike D’Arcy, Alexis Ross, Erin Bransom, Bailey Kuehl, Jonathan Bragg, Tom Hope, and Doug Downey. 2024. ARIES: A corpus of scientific paper edits made in response to peer reviews. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages…
  10. Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2023. Qlora: efficient finetuning of quantized llms. In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS ’23, Red Hook, NY, USA. Curran Associates Inc.
  11. Wanyu Du, Zae Myung Kim, Vipul Raheja, Dhruv Kumar, and Dongyeop Kang. 2022a. Read, revise, repeat: A system demonstration for human-in-the-loop iterative text revision. In Proceedings of the First Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2022), pages 96–108, Dublin, Ir… find
  12. Wanyu Du, Vipul Raheja, Dhruv Kumar, Zae Myung Kim, Melissa Lopez, and Dongyeop Kang. 2022b. Understanding iterative revision from human-written text. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3573–3590, Dublin, Ireland.… find
  13. Jane Dwivedi-Yu, Timo Schick, Zhengbao Jiang, Maria Lomeli, Patrick Lewis, Gautier Izacard, Edouard Grave, Sebastian Riedel, and Fabio Petroni. 2024. EditEval: An instruction-based benchmark for text improvements. In Proceedings of the 28th Conference on Computational Natural Language Learning, page… find
  14. Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil Hosmer, Bram Wasti, Liangzhen Lai, Anas Mahmoud, Bilge Acun, Saurabh Agarwal, Ahmed Roman, Ahmed Aly, Beidi Chen, and Carole-Jean Wu. 2024. LayerSkip: Enabling early exit inference and self-speculative decoding. In Proceedings of the 62nd…
  15. Jill Fitzgerald. 1987. Research on revision in writing. Review of educational research, 57(4):481–506. find
  16. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 542 o… — The Llama 3 Herd of Models
  17. Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In Proceedings of the 36th International Conference on Machine Learning. find
  18. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, and 1 others. 2022. Lora: Low-rank adaptation of large language models. ICLR, 1(2):3.
  19. Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, and Roy Lee. 2023. LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language models. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing,…
  20. Robert Iv, Alexandre Passos, Sameer Singh, and Ming-Wei Chang. 2022. FRUIT: Faithfully reflecting updated information in text. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3670–3686, Seattle,… find
  21. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix,… find
  22. Chao Jiang, Wei Xu, and Samuel Stevens. 2022. arXivEdits: Understanding the human revision process in scientific writing. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 9420–9435, Abu Dhabi, United Arab Emirates. Association for Computational Linguis… find
  23. Jeff Johnson, Matthijs Douze, and Hervé Jégou. 2019. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, 7(3):535–547.
  24. Léane Jourdan, Florian Boudin, Nicolas Hernandez, and Richard Dufour. 2024. CASIMIR: A corpus of scientific articles enhanced with multiple author-integrated revisions. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COL… find
  25. Gal Kaplun, Andrey Gurevich, Tal Swisa, Mazor David, Shai Shalev-Shwartz, and Eran Malach. 2023. Less is more: Selective layer finetuning with subtuning. arXiv preprint arXiv:2302.06354. — [arXiv:2302.06354](https://arxiv.org/abs/2302.06354) find
  26. Omid Kashefi, Tazin Afrin, Meghan Dale, Christopher Olshefski, Amanda Godley, Diane Litman, and Rebecca Hwa. 2022. Argrewrite v. 2: an annotated argumentative revisions corpus. Language Resources and Evaluation, pages 1–35. find
  27. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, and Luke Zettlemoyer. 2019. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461.
  28. Nianqi Li, Jingping Liu, Sihang Jiang, Haiyun Jiang, Yanghua Xiao, Jiaqing Liang, Zujie Liang, Feng Wei, Jinglei Chen, Zhenghong Hao, and 1 others. 2024. Cr-llm: A dataset and optimization for concept reasoning of large language models. In Findings of the Association for Computational Linguistics AC… find
  29. Bingchang Liu, Chaoyu Chen, Zi Gong, Cong Liao, Huan Wang, Zhichao Lei, Ming Liang, Dajun Chen, Min Shen, Hailian Zhou, and 1 others. 2024a. Mftcoder: Boosting code llms with multitask fine-tuning. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 5430–54… find
  30. Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, and Min-Hung Chen. 2024b. DoRA: Weight-decomposed low-rank adaptation. In Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Research, p… find
  31. Zhexiong Liu and Diane Litman. 2025. Efficient layer-wise LLM fine-tuning for revision intention prediction. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 15319– 15334, Suzhou, China. Association for Computational Linguistics. find
  32. Zhexiong Liu, Diane Litman, Elaine Wang, Lindsay Matsumura, and Richard Correnti. 2023a. Predicting the quality of revisions in argumentative writing. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 275–287, Toronto, Canada. Associ… find
  33. Zhexiong Liu, Diane Litman, Elaine L Wang, Tianwen Li, Mason Gobat, Lindsay Clare Matsumura, and Richard Correnti. 2025. eRevise+RF: A writing evaluation system for assessing student essay revisions and providing formative feedback. In Proceedings of the 2025 Conference of the Nations of the America… find
  34. Zhexiong Liu, Licheng Liu, Yiqun Xie, Zhenong Jin, and Xiaowei Jia. 2023b. Task-adaptive meta-learning framework for advancing spatial generalizability. Proceedings of the AAAI Conference on Artificial Intelligence, 37(12):14365–14373. find
  35. Masato Mita, Keisuke Sakaguchi, Masato Hagiwara, Tomoya Mizumoto, Jun Suzuki, and Kentaro Inui. 2024. Towards automated document revision: Grammatical error correction, fluency edits, and beyond. In Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA… find
  36. Courtney Napoles, Keisuke Sakaguchi, Matt Post, and Joel Tetreault. 2015. Ground truth for grammatical error correction metrics. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volum… find
  37. Rui Pan, Xiang Liu, Shizhe Diao, Renjie Pi, Jipeng Zhang, Chi Han, and Tong Zhang. 2024. Lisa: layer-wise importance sampling for memory-efficient large language model fine-tuning. Advances in Neural Information Processing Systems, 37:57018–57049. find
  38. Yixing Peng, Quan Wang, Licheng Zhang, Yi Liu, and Zhendong Mao. 2024. Chain-of-question: A progressive question decomposition approach for complex knowledge base question answering. In ACL (Findings). find
  39. Vipul Raheja, Dhruv Kumar, Ryan Koo, and Dongyeop Kang. 2023. CoEdIT: Text editing by task-specific instruction tuning. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5274–5291, Singapore. Association for Computational Linguistics. find
  40. Qian Ruan, Ilia Kuznetsov, and Iryna Gurevych. 2024a. Are large language models good classifiers? a study on edit intent classification in scientific document revisions. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15049–15067, Miami, Florida, USA.… find
  41. Qian Ruan, Ilia Kuznetsov, and Iryna Gurevych. 2024b. Re3: A holistic framework and dataset for modeling collaborative document revision. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4635–4655, Bangkok, Thailand. Associatio… find
  42. Lei Shu, Liangchen Luo, Jayakumar Hoskere, Yun Zhu, Yinxiao Liu, Simon Tong, Jindong Chen, and Lei Meng. 2024. Rewritelm: An instruction-tuned large language model for text rewriting. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18970–18980. find
  43. Gabriella Skitalinskaya, Maximilian Spliethöver, and Henning Wachsmuth. 2023. Claim optimization in computational argumentation. In Proceedings of the 16th International Natural Language Generation Conference, pages 134–152, Prague, Czechia. Association for Computational Linguistics. find
  44. Gabriella Skitalinskaya and Henning Wachsmuth. 2023. To revise or not to revise: Learning to detect improvable claims for argumentative writing support. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15799–15816, Toronto, Can… find
  45. Nancy Sommers. 1980. Revision strategies of student writers and experienced adult writers. College Composition & Communication, 31(4):378–388. find
  46. Alexander Spangher, Xiang Ren, Jonathan May, and Nanyun Peng. 2022. NewsEdits: A news article revision dataset and a novel document-level reasoning challenge. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolo… find
  47. Sotaro Takeshita, Tommaso Green, Ines Reinig, Kai Eckert, and Simone Ponzetto. 2024. ACLSum: A new dataset for aspect-based summarization of scientific publications. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language T… find
  48. Nandan Thakur, Nils Reimers, Johannes Daxenberger, and Iryna Gurevych. 2021. Augmented SBERT: Data augmentation method for improving bi-encoders for pairwise sentence scoring tasks. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics:…
  49. Chenxing Wei, Yao Shu, Ying Tiffany He, and Fei Yu. 2025. Flexora: Flexible low-rank adaptation for large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14643– 14682, Vienna, Austria. Association for Computat… find
  50. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Proceedings of the 36th International Conference on Neural Information Processing Systems, NIPS ’22, R…
  51. Yiqun Xie, Erhu He, Xiaowei Jia, Han Bao, Xun Zhou, Rahul Ghosh, and Praveen Ravirathinam. 2021. A statistically-guided deep network transformation and moderation framework for data with spatial heterogeneity. In 2021 IEEE International Conference on Data Mining (ICDM), pages 767–776. IEEE. find
  52. Wei Xu, Courtney Napoles, Ellie Pavlick, Quanze Chen, and Chris Callison-Burch. 2016. Optimizing statistical machine translation for text simplification. Transactions of the Association for Computational Linguistics, 4:401–415.
  53. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, and 22 others. 2024. Qwen2.5 technical report. arXiv preprint arXi… find
  54. Kai Yao, Penglei Gao, Lichun Li, Yuan Zhao, Xiaofeng Wang, Wei Wang, and Jianke Zhu. 2024. Layer-wise importance matters: Less memory for better performance in parameter-efficient fine-tuning of large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 19… find
  55. Kaiyan Zhang, Ning Ding, Biqing Qi, Xuekai Zhu, Xinwei Long, and Bowen Zhou. 2023. CRaSh: Clustering, removing, and sharing enhance fine-tuning without full large language model. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 9612–9637, Singapore. As… find
  56. Zheng Zhao, Yftah Ziser, and Shay B Cohen. 2024. Layer by layer: Uncovering where multi-task learning happens in instruction-tuned large language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15195–15214, Miami, Florida, USA. Association for… find
  57. Ligeng Zhu, Lanxiang Hu, Ji Lin, and Song Han. 2024. Lift: Efficient layer-wise fine-tuning for large model models. find
  58. Timon Ziegenbein, Gabriella Skitalinskaya, Alireza Bayat Makou, and Henning Wachsmuth. 2024. LLM-based rewriting of inappropriate argumentation using reinforcement learning from machine feedback. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Lo… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/liu-2026-intention-adaptive-llm-fine-tuning/