Elamur Research⌕
☰
home / papers / 2025 / Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual Disabilities

Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual Disabilities

Paper · 2025 · Yingqiang Gao, Kaede Johnson, David Froehlich et al.

Summary

German automatic text simplification (ATS) models are usually trained on data curated by experts. The people they are meant to serve, persons with intellectual disabilities, rarely influence how these systems are built. This paper tests whether direct preference optimization (DPO) can steer LLM-based ATS systems toward that group's own preferences. DPO is a cheap alignment method that needs no separate reward model.

The authors built a low-effort web tool in which target-group members and simplification experts chose the better of two LLM-generated simplifications. The result is HF4ATS, a German preference dataset. Their pipeline has four steps:

  • filter sentence-level complex–simple pairs from two corpora;
  • run SFT on German-specific and multilingual open LLMs;
  • post-train with DPO;
  • compare DPO outputs against their SFT predecessors through human judgment.

Checkpoints trained on expert preferences from the two German-tuned backbones were preferred with statistical significance. No checkpoint trained on target-group preferences was. The takeaway is that DPO depends on consistent preference signals, which are hard to collect from this group. Better elicitation tools and noise-tolerant alignment objectives are therefore needed.

Key points

  • HF4ATS is presented as the largest German human-preference dataset of LLM-generated simplification pairs, with labels from both target-group and expert annotators. Code and data are at github.com/ZurichNLP/HF4ATS.
  • Three DPO post-trained ATS models were open-sourced. The base models include open LLMs such as Llama and Mistral.
  • The evaluation uses "DPO supremacy": the share of human judgments that prefer the DPO output over the SFT output. A checkpoint counts as successful if this share is above 0.50 with p < 0.05 in a binomial test (run with SciPy).
  • For experts, results are reported both with and without an outlier annotator (ea02). The target-group checkpoints also included data from eight annotators whose intra-annotator agreement was lower than that of the four most consistent ones (ta04, ta05, ta10, ta12).
  • As future work, the authors propose KTO, which needs only "desirable/undesirable" labels on single outputs. This removes pairwise comparison and the cognitive load it places on annotators.

Interesting ideas

  • I1. Measure each annotator's self-consistency on repeated items and use it to decide whose labels enter training, since mixing in inconsistent labelers diluted the signal here.
  • I2. Judge a post-trained model only head-to-head against its own predecessor, and accept it only if its win rate is significantly above 0.5 under a binomial test.
  • I3. Switch from comparing two outputs to rating one output as good or bad (the KTO idea). This is cheaper per label and avoids forcing choices between near-identical options.
  • I4. Report results both with and without an identified outlier evaluator, so readers can see how much one person drives the conclusion.
  • I5. Tune a generator on human or teacher preferences between two candidate realizations of the same content, aimed at a specific reader group.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (learn): Score each LLM teacher tier or witness parser by how stably it labels repeated or paraphrased inputs, and down-weight unstable witnesses when building silver data.
  • I2 (learn): Adopt a new self-induced repair rule or retrained parser only after pairwise checks against the previous version show significant wins, with negative controls alongside.
  • I3 (learn): Ask LLM teachers for binary accept/reject verdicts on single parses or frames instead of pairwise rankings, which cuts cost and avoids noisy forced choices.
  • I4 (learn): Show evaluation results with and without suspicious witness parsers or test subsets, making it explicit how robust a gain is.
  • I5 (back): Produce two texts from the same meaning graph, collect preferences on which is clearer for a target audience, and use them to rank surface-realization choices in an explainable way.

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 6The 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 worksSocial Sciences · 1,772 worksHuman Factors and Ergonomics · 4 works

🧭 Topics 1Research subjects and languages the work is about.Evaluation & benchmarks · 1,220 works

Cite

Cite as Yingqiang Gao, Kaede Johnson, David Froehlich, Luisa Carrer and Sarah Ebling. 2025. Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual Disabilities. arXiv:2507.01479.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2507.01479 · arXiv 2507.01479

@misc{gao2025evaluating,
  title = {{Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual Disabilities}},
  author = {Yingqiang Gao, Kaede Johnson, David Froehlich, Luisa Carrer and Sarah Ebling},
  year = {2025},
  doi = {10.48550/arxiv.2507.01479},
  eprint = {2507.01479},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2507.01479}
}

References

78 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sweta Agrawal and Marine Carpuat. 2024. Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension. Transactions of the Association for Computational Linguistics 12 (2024), 432–448. find
  2. Suha S Al-Thanyyan and Aqil M Azmi. 2021. Automated Text Simplification: A Survey. ACM Computing Surveys (CSUR) 54, 2 (2021), 1–36. find
  3. Fernando Alva-Manchego, Louis Martin, Antoine Bordes, Carolina Scarton, Benoît Sagot, and Lucia Specia. 2020. ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 4668–4679.
  4. Miriam Anschütz, Joshua Oehms, Thomas Wimmer, Bartłomiej Jezierski, and Georg Groh. 2023. Language Models for German Text Simplification: Overcoming Parallel Data Scarcity through Style-specific Pre-training. In Findings of the Association for Computational Linguistics: ACL 2023. 1147–1158. find
  5. Dennis Aumiller and Michael Gertz. 2022. Klexikon: A German Dataset for Joint Summarization and Simplification. In Proceedings of the Thirteenth Language Resources and Evaluation Conference. 2693–2701. find
  6. Nguyen Bach, Qin Gao, Stephan Vogel, and Alex Waibel. 2011. TriS: A Statistical Sentence Simplifier with Log-linear Models and Margin-based Discriminative Training. In Proceedings of 5th International Joint Conference on Natural Language Processing. 474–482. ↗
  7. Richard Bamberger and Erich Vanacek. 1984. Lesen-Verstehen-Lernen-Schreiben. Diesterweg. find
  8. Alessia Battisti, Dominik Pfütze, Andreas Säuberli, Marek Kostrzewa, and Sarah Ebling. 2020. A Corpus for Automatic Readability Assessment and Text Simplification of German. In Proceedings of the Twelfth Language Resources and Evaluation Conference. 3302–3311. ↗
  9. Abeba Birhane, William Isaac, Vinodkumar Prabhakaran, Mark Diaz, Madeleine Clare Elish, Iason Gabriel, and Shakir Mohamed. 2022. Power to the people? Opportunities and challenges for participatory AI. In Proceedings of the 2nd ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization. 1–8. find
  10. Ralph Allan Bradley and Milton E Terry. 1952. Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons. Biometrika 39, 3/4 (1952), 324–345. ↗
  11. Andrew Cashin, Julia Morphet, Nathan J Wilson, and Amy Pracilio. 2024. Barriers to Communication with People with Developmental Disabilities: A Reflexive Thematic Analysis. Nursing & health sciences 26, 1 (2024), e13103. ↗
  12. Yanda Chen, Ruiqi Zhong, Sheng Zha, George Karypis, and He He. 2022. Meta-learning via Language Model In-context Tuning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 719–730. find
  13. Paul F Christiano, Jan Leike, Tom B Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep Reinforcement Learning from Human Preferences. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 4302–4310. ↗
  14. Jacob Cohen. 1960. A Coefficient of Agreement for Nominal Scales. Educational and psychological measurement 20, 1 (1960), 37–46. ↗
  15. Liam Cripwell, Joël Legrand, and Claire Gardent. 2023. Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 12053–12059. find
  16. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. 2024. The LLaMA 3 Herd of Models. arXiv preprint arXiv:2407.21783 (2024). ↗
  17. Sarah Ebling, Alessia Battisti, Marek Kostrzewa, Dominik Pfütze, Annette Rios, Andreas Säuberli, and Nicolas Spring. 2022. Automatic Text Simplification for German. Frontiers in Communication 7 (2022), 706718. ↗
  18. Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, and Douwe Kiela. 2024. Model alignment as prospect theoretic optimization. In Forty-first International Conference on Machine Learning. find
  19. Federal Ministry of Social Affairs, Health, Care and Consumer Protection (BMS-GPK). 2022. National Action Plan on Disability 2022–2030. Vienna: BMSGPK (2022). find
  20. Adam Fisch, Jacob Eisenstein, Vicky Zayats, Alekh Agarwal, Ahmad Beirami, Chirag Nagpal, Pete Shaw, and Jonathan Berant. 2024. Robust Preference Optimization Through Reward Model Distillation. arXiv preprint arXiv:2405.19316 (2024). ↗
  21. Rudolph Flesch. 1948. A New Readability Yardstick. Journal of applied psychology 32, 3 (1948), 221. ↗
  22. Annette Rios Gonzales, Nicolas Spring, Tannon Kew, Marek Kostrzewa, Andreas Säuberli, Mathias Müller, and Sarah Ebling. 2021. A New Dataset and Efficient Baselines for Document-level Text Simplification in German. In Proceedings of the Third Workshop on New Frontiers in Summarization. 152–161. find
  23. Silvia Hansen-Schirra, Walter Bisang, Arne Nagels, Silke Gutermuth, Julia Fuchs, Liv Borghardt, Silvana Deilen, Anne-Kathrin Gros, Laura Schiffl, and Johanna Sommer. 2020. Intralingual Translation into Easy Language–or How to Reduce Cognitive Processing Costs. Easy Language Research: Text and User Perspectives. Berlin: Frank & Timme (2020), 197–225. find
  24. Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, and Graham Neubig. 2022. Towards a Unified View of Parameter-Efficient Transfer Learning. In Proceedings of the Tenth International Conference on Learning Representations. ↗
  25. David Heineman, Yao Dou, Mounica Maddela, and Wei Xu. 2023. Dancing Between Success and Failure: Edit-level Simplification Evaluation using SALSA. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 3466–3495. find
  26. Freya Hewett, Hadi Asghari, and Manfred Stede. 2024. Elaborative Simplification for German-language Texts. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue. 29–39. find
  27. Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In Proceedings of the Tenth International Conference on Learning Representations.
  28. Xiangkun Hu, Tong He, and David Wipf. [n. d.]. New Desiderata for Direct Preference Optimization. In ICML 2024 Workshop on Models of Human Feedback for AI Alignment. find
  29. Hamish Ivison, Yizhong Wang, Jiacheng Liu, Zeqiu Wu, Valentina Pyatkin, Nathan Lambert, Noah A Smith, Yejin Choi, and Hannaneh Hajishirzi. 2024. Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback. In Proceedings of the 38st International Conference on Neural Information Processing Systems.
  30. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023). ↗
  31. J Peter Kincaid, Robert P Fishburne Jr, Richard L Rogers, and Brad S Chissom. 1975. Derivation of New Readability Formulas (Automated Readability Index, Fog Count and Flesch Reading Ease Formula) for Navy Enlisted Personnel. (1975). ↗
  32. David Klaper, Sarah Ebling, and Martin Volk. 2013. Building a German/Simple German Parallel Corpus for Automatic Text Simplification. In Proceedings of the Second Workshop on Predicting and Improving Text Readability for Target Reader Populations. 11–19. find
  33. Lars Klöser, Mika Beele, Jan-Niklas Schagen, and Bodo Kraft. 2024. German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Data. In Proceedings of the Fourth Workshop on Language Technology for Equality, Diversity, Inclusion. 63–72. find
  34. Klaus Krippendorff. 2004. Reliability in Content Analysis: Some Common Misconceptions and Recommendations. Human communication research 30, 3 (2004), 411–433. ↗
  35. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 7871–7880.
  36. Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. Association for Computational Linguistics, 74–81.
  37. Jiahong Liu, Zexuan Qiu, Zhongyang Li, Quanyu Dai, Jieming Zhu, Minda Hu, Menglin Yang, and Irwin King. 2025. A Survey of Personalized Large Language Models: Progress and Future Directions. arXiv preprint arXiv:2502.11528 (2025). ↗
  38. Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, and Luke Zettlemoyer. 2020. Multilingual Denoising Pre-training for Neural Machine Translation. (2020), 726–742. find
  39. Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In Proceedings of the Seventh International Conference on Learning Representations (ICLR 2019). find
  40. Ilya Loshchilov and Frank Hutter. 2022. SGDR: Stochastic Gradient Descent with Warm Restarts. In Proceedings of the Tenth International Conference on Learning Representations (ICLR 2022). find
  41. Christiane Maaß. 2015. Leichte Sprache. Das Regelbuch. Deutsche Nationalbibliothek. find
  42. Mounica Maddela, Fernando Alva-Manchego, and Wei Xu. 2021. Controllable Text Simplification with Explicit Paraphrasing. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 3536–3553.
  43. Mounica Maddela, Yao Dou, David Heineman, and Wei Xu. 2023. LENS: A Learnable Evaluation Metric for Text Simplification. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 16383–16408.
  44. Marius Mosbach, Tiago Pimentel, Shauli Ravfogel, Dietrich Klakow, and Yanai Elazar. 2023. Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation. In Findings of the Association for Computational Linguistics: ACL 2023. 12284–12314.
  45. Eduardo Mosqueira-Rey, Elena Hernández-Pereira, David Alonso-Ríos, José Bobes-Bascarán, and Ángel Fernández-Leal. 2023. Human-in-the-loop Machine Learning: A State of the Art. Artificial Intelligence Review 56, 4 (2023), 3005–3054. ↗
  46. Akifumi Nakamachi, Tomoyuki Kajiwara, and Yuki Arase. 2020. Text Simplification with Reinforcement Learning using Supervised Rewards on Grammaticality, Meaning Preservation, and Simplicity. In Proceedings of the 1st conference of the Asia-Pacific chapter of the association for computational linguistics and the 10th international joint conference on natural language processing: Student research workshop. 153–159. find
  47. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training Language Models to Follow Instructions with Human Feedback. In Proceedings of the 36st International Conference on Neural Information Processing Systems, Vol. 35. 27730–27744.
  48. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: A Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311–318.
  49. Venkatesh Balavadhani Parthasarathy, Ahtsham Zafar, Aafaq Khan, and Arsalan Shahid. 2024. The Ultimate Guide to Fine-tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities. arXiv preprint arXiv:2408.13296 (2024). ↗
  50. Biqing Qi, Pengfei Li, Fangyuan Li, Junqi Gao, Kaiyan Zhang, and Bowen Zhou. 2024. Online DPO: Online Direct Preference Optimization with Fast-slow Chasing. arXiv preprint arXiv:2406.05534 (2024). ↗
  51. Jipeng Qiang and Xindong Wu. 2019. Unsupervised Statistical Text Simplification. IEEE Transactions on Knowledge and Data Engineering 33, 4 (2019), 1802–1806. ↗
  52. Rafael Rafailov, Archit Sharma, Eric Mitchell, Stefano Ermon, Christopher D Manning, and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly A Reward Model. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 53728–53741. ↗
  53. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the Limits of Transfer Learning with A Unified Text-to-text Transformer. Journal of machine learning research 21, 140 (2020), 1–67. ↗
  54. Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 3982–3992.
  55. Horacio Saggion, Sanja Štajner, Stefan Bott, Simon Mille, Luz Rello, and Biljana Drndarevic. 2015. Making it Simplext: Implementation and Evaluation of A Text Simplification System for Spanish. ACM Transactions on Accessible Computing (TACCESS) 6, 4 (2015), 1–36. find
  56. Andreas Säuberli, Sarah Ebling, and Martin Volk. 2020. Benchmarking Data-driven Automatic Text Simplification for German. In Proceedings of the 1st workshop on tools and resources to empower people with reading dIfficulties (READI). 41–48. find
  57. Andreas Säuberli, Franz Holzknecht, Patrick Haller, Silvana Deilen, Laura Schiffl, Silvia Hansen-Schirra, and Sarah Ebling. 2024. Digital Comprehensibility Assessment of Simplified Texts among Persons with Intellectual Disabilities. In Proceedings of the CHI Conference on Human Factors in Computing Systems. 1–11. find
  58. Carolina Scarton and Lucia Specia. 2018. Learning Simplifications for Specific Target Audiences. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 712–718.
  59. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv preprint arXiv:1707.06347 (2017). ↗
  60. Laura Seiffe, Fares Kallel, Sebastian Möller, Babak Naderi, and Roland Roller. 2022. Subjective text complexity assessment for German. In Proceedings of the Thirteenth Language Resources and Evaluation Conference. 707–714. find
  61. Kim Cheng Sheang and Horacio Saggion. 2021. Controllable Sentence Simplification with a Unified Text-to-Text Transfer Transformer. In Proceedings of the 14th International Conference on Natural Language Generation. 341–352. find
  62. Zhengyan Shi, Adam X Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, and Aldo Lipani. 2024. Instruction Tuning with Loss Over Instructions. In Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2024). find
  63. Advaith Siddharthan and Angrosh Mandya. 2014. Hybrid Text Simplification Using Synchronous Dependency Grammars with Hand-written and Automatically Harvested Rules. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics. 722–731.
  64. Nicolas Spring, Annette Rios Gonzales, and Sarah Ebling. 2021. Exploring German Multi-Level Text Simplification. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021). 1339–1349. find
  65. Nicolas Spring, Marek Kostrzewa, David Fröhlich, Annette Rios, Dominik Pfütze, Alessia Battisti, and Sarah Ebling. 2023. Analyzing Sentence Alignment for Automatic Simplification of German Texts. In Emerging Fields in Easy Language and Accessible Communication Research. Springer, 339–369. ↗
  66. Nicolas Spring, Marek Kostrzewa, Annette Rios, and Sarah Ebling. 2022. Ensembling and Score-Based Filtering in Sentence Alignment for Automatic Simplification of German Texts. In International Conference on Human-Computer Interaction. 137–149. find
  67. Regina Stodden, Omar Momen, and Laura Kallmeyer. 2023. DEplain: A German Parallel Corpus with Intralingual Translations into Plain Language for Sentence and Document Simplification. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 16441–16463. find
  68. Julia Suter, Sarah Ebling, and Martin Volk. 2016. Rule-based Automatic Text Simplification for German. In Proceedings of the 13th Conference on Natural Language Processing (KONVENS 2016). 279–287. find
  69. Vanessa Toborek, Moritz Busch, Malte Boßert, Christian Bauckhage, and Pascal Welke. 2023. A New Aligned Simple German Corpus. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 11393–11412. ↗
  70. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971 (2023). ↗
  71. Xingjiao Wu, Luwei Xiao, Yixuan Sun, Junhang Zhang, Tianlong Ma, and Liang He. 2022. A Survey of Human-in-the-loop for Machine Learning. Future Generation Computer Systems 135 (2022), 364–381. ↗
  72. 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 (2016), 401–415. ↗
  73. Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A Massively Multilingual Pre-trained Text-to-Text Transformer. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 483–498. ↗
  74. Daichi Yamaguchi, Rei Miyata, Sayuka Shimada, and Satoshi Sato. 2023. Gauging the Gap Between Human and Machine Text Simplification Through Analytical Evaluation of Simplification Strategies and Errors. In Findings of the Association for Computational Linguistics: EACL 2023. 359–375. find
  75. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2019. BERTScore: Evaluating Text Generation with Bert. In Proceedings of the Seventh International Conference on Learning Representations (ICLR 2019). ↗
  76. Xingxing Zhang and Mirella Lapata. 2017. Sentence Simplification with Deep Reinforcement Learning. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. 584–594.
  77. Siyan Zhao, Mingyi Hong, Yang Liu, Devamanyu Hazarika, and Kaixiang Lin. 2025. Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs. In Proceedings of the 15th International Conference on Learning Representations (ICLR 2025). find
  78. Chunting Zhou, Pengfei Liu, Puxin Xu, Srini Iyer, Jiao Sun, Yuning Mao, Xuezhe Ma, Avia Efrat, Ping Yu, Lili Yu, et al. 2023. LIMA: Less is More for Alignment. In Proceedings of the 37th International Conference on Neural Information Processing Systems. 55006–55021. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/gao-2025-evaluating-effectiveness-direct-preference-optimization/