Elamur Research⌕
☰
home / papers / 2025 / Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models

Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models

Paper · 2025 · Lennart Stopler, Rufat Asadli, Mitja Nikolaus et al.

Summary

Language models learn by predicting the next token, while children also learn from whether their attempts to communicate succeed. This paper asks whether communicative success can act as a reward for training LMs in a more child-like way. The authors design a text-only reference game. A speaker model, standing in for a child, condenses a passage into a short message. A fixed, fully trained listener must then answer questions about the passage using only that message, and correct answers earn the speaker a reward. A feasibility study shows that listener success drops when its input is ungrammatical, so the reward carries an indirect signal about grammar. The authors then train T5 speakers with reinforcement learning, both from scratch and by fine-tuning. They add a channel cost based on either message length or listener surprisal. This cost changes speaker behaviour in interpretable ways: length pressure produces telegraphic messages that drop function words. However, no configuration improves grammatical ability. The study is a proof of concept for interaction-based, developmentally plausible LM training.

Key points

  • Setup: The game is a single-turn, language-only question–answering task, unlike earlier image–caption reference games. Summarization training is interleaved with likelihood-based training on the CNN Daily Mail dataset.
  • Bottleneck sweep: The penalty weight λ was tested at {0, 0.1, 0.5, 0.9, 1} for both the length and surprisal bottlenecks, with three random seeds per configuration.
    • Reward falls below its starting level at λ ≥ 0.5 for the length bottleneck.
    • For the surprisal bottleneck, this happens only at λ ≥ 0.9, so surprisal costs fit better with good summaries.
  • No-penalty behaviour: With λ = 0, summaries grow from about 50% to over 70% of the original passage's length or surprisal and drift toward copying. No model fully converges on verbatim copying.
  • Grammar evaluation: Neither LanguageTool error counts nor BLiMP improved. T5's BLiMP scores stayed near chance (about 0.5) even before training.
  • Stated limitations: Training ran for only 240 steps, and the QA training data was roughly 500k tokens. The authors propose broader hyperparameter searches, architectures other than T5, length-bottleneck curricula, and multi-turn exchanges.

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 worksPsychology · 1,552 worksDevelopmental and Educational Psychology · 499 works

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

Cite

Cite as Lennart Stopler, Rufat Asadli, Mitja Nikolaus, Ryan Cotterell and Alex Warstadt. 2025. Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models. arXiv:2505.05970.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2505.05970 · arXiv 2505.05970

@misc{stopler2025developmentally,
  title = {{Towards Developmentally Plausible Rewards: Communicative Success as a Learning Signal for Interactive Language Models}},
  author = {Lennart Stopler, Rufat Asadli, Mitja Nikolaus, Ryan Cotterell and Alex Warstadt},
  year = {2025},
  doi = {10.48550/arxiv.2505.05970},
  eprint = {2505.05970},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2505.05970}
}

References

84 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Marwa Abdulhai, Isadora White, Charlie Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, and Sergey Levine. Lmrl gym: Benchmarks for multi-turn reinforcement learning with language models, 2023. find
  2. Marco Baroni. On the proper role of linguistically-oriented deep net analysis in linguistic theorizing. In Shalom Lappin and Jean Philippe Bernardy (eds.), Algebraic Structures in Natural Language, pp. 1–16. CRC Press, 2022. find
  3. Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O’Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, Usvsn Sai Prashanth, Edward Raff, Aviya Skowron, Lintang Sutawika, and Oskar Van Der Wal. Pythia: a suite for analyzing large language models across train… find
  4. Lukas Biewald. Experiment Tracking with Weights and Biases, 2020. URL https://www.wandb.com/. ↗
  5. Lois Bloom. Language Development: Form and Function in Emerging Grammars. MIT Press, 1970. find
  6. Roger Brown and Camille Hanlon. Derivational complexity and order of acquisition in child speech. Cognition and the development of language, 1970. find
  7. Jerome Bruner. Child’s Talk: Learning to Use Language. Child Language Teaching and Therapy, 1 (1):111–114, 1985. ISSN 0265-6590, 1477-0865. doi: 10.1177/026565908500100113. — [doi:10.1177/026565908500100113](https://doi.org/10.1177/026565908500100113) find
  8. Rudolf Carnap. Meaning and necessity. University of Chicago Press, 1947. find
  9. Tyler A. Chang and Benjamin K. Bergen. Word Acquisition in Neural Language Models. Transactions of the Association for Computational Linguistics, 10:1–16, January 2022. ISSN 2307-387X. doi: 10. 1162/tacl_a_00444. URL https://direct.mit.edu/tacl/article/doi/10.1162/ tacl_a_00444/109271/Word-Acquisiti… ↗
  10. Soravit Changpinyo, Piyush Sharma, Nan Ding, and Radu Soricut. Conceptual 12M: Pushing web-scale image-text pre-training to recognize long-tail visual concepts. In 2021 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp. 3557–3567, June 2021. doi: 10.1109/CVPR46437.2021.00356.… — [doi:10.1109/cvpr46437.2021.00356](https://doi.org/10.1109/cvpr46437.2021.00356) find
  11. Lucas Georges Gabriel Charpentier and David Samuel. Not all layers are equally as important: Every Layer Counts BERT. In Proceedings of the BabyLM Challenge. Association for Computational Linguistics (ACL), December 2023. find
  12. Michelle M. Chouinard and Eve V. Clark. Adult reformulations of child errors as negative evidence. Journal of Child Language, 30(3):637–669, 2003. ISSN 1469-7602, 0305-0009. doi: 10.1017/ S0305000903005701. find
  13. Eve V. Clark. Conversation and Language Acquisition: A Pragmatic Approach. Language Learning and Development, 14(3):170–185, 2018. ISSN 1547-5441. doi: 10.1080/15475441.2017.1340843. — [doi:10.1080/15475441.2017.1340843](https://doi.org/10.1080/15475441.2017.1340843) find
  14. Eve V. Clark. Conversational Repair and the Acquisition of Language. Discourse Processes, 57(5-6): 441–459, 2020. ISSN 0163-853X. doi: 10.1080/0163853X.2020.1719795. — [doi:10.1080/0163853x.2020.1719795](https://doi.org/10.1080/0163853x.2020.1719795) find
  15. Wafaa S El-Kassas, Cherif R Salama, Ahmed A Rafea, and Hoda K Mohamed. Automatic text summarization: A comprehensive survey. Expert systems with applications, 165:113679, 2021. find
  16. Jeffrey Elman, Elizabeth Bates, Mark H. Johnson, Annette Karmiloff-Smith, Domenico Parisi, and Kim Plunkett. Rethinking innateness: a connectionist perspective on development. The MIT Press, October 1996. ISBN 978-0-262-27229-2. doi: 10.7551/mitpress/5929.001.0001. URL https://doi.org/10.7551/mitpre… — [doi:10.7551/mitpress/5929.001.0001](https://doi.org/10.7551/mitpress/5929.001.0001) ↗
  17. Jeffrey L Elman. Finding structure in time. Cognitive science, 14(2):179–211, 1990. Publisher: Wiley Online Library. find
  18. Filippo Ficarra, Ryan Cotterell, and Alex Warstadt. A distributional perspective on word learning in neural language models. arXiv preprint arXiv:2502.05892, 2025. find
  19. Michael C. Frank. Bridging the data gap between children and large language models. Trends in Cognitive Sciences, 27(11):990–992, November 2023. ISSN 1364-6613, 1879-307X. doi: 10.1016/ j.tics.2023.08.007. URL https://www.cell.com/trends/cognitive-sciences/ abstract/S1364-6613(23)00203-6. Publisher:… ↗
  20. Jill Gilkerson, Jeffrey A. Richards, Steven F. Warren, Judith K. Montgomery, Charles R. Greenwood, D. Kimbrough Oller, John H. L. Hansen, and Terrance D. Paul. Mapping the Early Language Environment Using All-Day Recordings and Automated Analysis. American Journal of Speech-Language Pathology, 26(2)… — [doi:10.1044/2016_ajslp-15-0169](https://doi.org/10.1044/2016_ajslp-15-0169) find
  21. Mario Giulianelli. Towards pragmatic production strategies for natural language generation tasks, 2022.
  22. E Mark Gold. Language identification in the limit. Information and Control, 10(5):447–474, May 1967. ISSN 0019-9958. doi: 10.1016/S0019-9958(67)91165-5. URL https://www.sciencedirect.com/science/article/pii/S0019995867911655. ↗
  23. H. P. Grice. Logic and Conversation. Brill, December 1975. ISBN 978-90-04-36881-1. doi: 10.1163/9789004368811_003. Pages: 41-58 Section: Speech Acts. find
  24. Abhinav Gupta, Marc Lanctot, and Angeliki Lazaridou. Dynamic population-based meta-learning for multi-agent communication with natural language. In Advances in Neural Information Processing Systems, volume 34, pp. 16899–16912, 2021. find
  25. Sarah Hiller and Raquel Fernandez. A Data-driven Investigation of Corrective Feedback on Subject Omission Errors in First Language Acquisition. In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, pp. 105–114, Berlin, Germany, 2016. Association for Computational L… find
  26. Yanping Huang and Rajesh P. N. Rao. Predictive coding. WIREs Cognitive Science, 2(5):580– 593, September 2011. ISSN 1939-5078, 1939-5086. doi: 10.1002/wcs.142. URL https://wires.onlinelibrary.wiley.com/doi/10.1002/wcs.142. — [doi:10.1002/wcs.142](https://doi.org/10.1002/wcs.142) ↗
  27. Athul Paul Jacob, Mike Lewis, and Jacob Andreas. Multitasking inhibits semantic drift, 2021. find
  28. Roni Katzir. Why Large Language Models Are Poor Theories of Human Linguistic Cognition: A Reply to Piantadosi. Biolinguistics, 17(Article e13153), 2023. doi: https://doi.org/10.5964/bioling. 13153. URL https://bioling.psychopen.eu/index.php/bioling/article/ view/13153. — [doi:10.5964/bioling](https://doi.org/10.5964/bioling) ↗
  29. Daniel Khashabi, Sewon Min, Tushar Khot, Ashish Sabharwal, Oyvind Tafjord, Peter Clark, and Hannaneh Hajishirzi. Unifiedqa: Crossing format boundaries with a single qa system, 2020.
  30. Daniel Khashabi, Yeganeh Kordi, and Hannaneh Hajishirzi. Unifiedqa-v2: Stronger generalization via broader cross-format training, 2022. find
  31. Silvia Kouwenberg and John Victor Singler. The handbook of pidgin and creole studies. John Wiley & Sons, 2009. find
  32. Nur Lan, Emmanuel Chemla, and Roni Katzir. Large language models and the argument from the poverty of the stimulus. Linguistic Inquiry, pp. 1–28, August 2024. ISSN 0024-3892. doi: 10.1162/ling_a_00533. URL https://doi.org/10.1162/ling_a_00533. — [doi:10.1162/ling_a_00533](https://doi.org/10.1162/ling_a_00533) ↗
  33. Jey Han Lau, Alexander Clark, and Shalom Lappin. Grammaticality, acceptability, and probability: A probabilistic view of linguistic knowledge. Cognitive Science, 41(5):1202–1241, 2017. Publisher: Wiley Online Library. find
  34. Angeliki Lazaridou, Anna Potapenko, and Olivier Tieleman. Multi-agent communication meets natural language: Synergies between functional and structural language learning, 2020a. find
  35. Angeliki Lazaridou, Anna Potapenko, and Olivier Tieleman. Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7663–7674, Online, July 2020b. As… find
  36. Roger Levy. Expectation-based syntactic comprehension. Cognition, 106(3):1126–1177, March 2008. ISSN 00100277. doi: 10.1016/j.cognition.2007.05.006. URL https://linkinghub.elsevier.com/retrieve/pii/S0010027707001436. — [doi:10.1016/j.cognition.2007.05.006](https://doi.org/10.1016/j.cognition.2007.05.006) ↗
  37. Roger Levy and T. Florian Jaeger. Speakers optimize information density through syntactic reduction. In Bernhard Schölkopf, John Platt, and Thomas Hofmann (eds.), Advances in Neural Information Processing Systems 19, pp. 849–856. The MIT Press, September 2007. ISBN 978-0-262-25691-9. doi: 10.7551/mi… — [doi:10.7551/mitpress/7503.003](https://doi.org/10.7551/mitpress/7503.003) find
  38. David K. Lewis. On the Plurality of Worlds. Wiley-Blackwell, Malden, Mass., 1986. find
  39. David Kellogg Lewis. Convention: A Philosophical Study. Wiley-Blackwell, Cambridge, MA, USA, 1969. find
  40. Chin-Yew Lin. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pp. 74–81, Barcelona, Spain, July 2004. Association for Computational Linguistics. URL https://aclanthology.org/W04-1013. ↗
  41. Tal Linzen. What can linguistics and deep learning contribute to each other? Response to Pater. Language, 95(1):e99–e108, 2019. Publisher: Linguistic Society of America. find
  42. Andy Liu, Hao Zhu, Emmy Liu, Yonatan Bisk, and Graham Neubig. Computational Language Acquisition with Theory of Mind, March 2023. URL http://arxiv.org/abs/2303.01502. arXiv:2303.01502 [cs]. ↗
  43. Ryan Lowe, Abhinav Gupta, Jakob Foerster, Douwe Kiela, and Joelle Pineau. On the interaction between supervision and self-play in emergent communication, 2020. find
  44. Yuchen Lu, Soumye Singhal, Florian Strub, Olivier Pietquin, and Aaron Courville. Countering language drift with seeded iterated learning, 2020. find
  45. Gary Lupyan and Andy Clark. Words and the World: Predictive Coding and the Language-Perception-Cognition Interface. Current Directions in Psychological Science, 24(4):279–284, August 2015. ISSN 0963-7214, 1467-8721. doi: 10.1177/0963721415570732. URL https://journals. sagepub.com/doi/10.1177/0963721… — [doi:10.1177/0963721415570732](https://doi.org/10.1177/0963721415570732) find
  46. Gary F. Marcus. Negative evidence in language acquisition. Cognition, 46(1):53–85, 1993. ISSN 0010-0277. doi: 10.1016/0010-0277(93)90022-N. — [doi:10.1016/0010-0277(93)90022-n](https://doi.org/10.1016/0010-0277%2893%2990022-n) find
  47. Richard Diehl Martinez, Hope McGovern, Zebulon Goriely, Christopher Davis, Andrew Caines, Paula Buttery, and Lisa Beinborn. CLIMB – curriculum learning for infant-inspired model building. In Proceedings of the BabyLM Challenge. Association for Computational Linguistics (ACL), December 2023. find
  48. AI @ Meta. The llama 3 herd of models. arXiv preprint arXiv:2407.21783, 2024. URL https://arxiv.org/abs/2407.21783. ↗
  49. Raphaël Millière. Language Models as Models of Language. In R. Nefdt, G. Dupre, and K. Stanton (eds.), The Oxford Handbook of the Philosophy of Linguistics. Oxford University Press, forthcoming. URL http://arxiv.org/abs/2408.07144. arXiv:2408.07144 [cs]. Piotr Nawrot. nanot5: A pytorch framework for… ↗
  50. Mitja Nikolaus and Abdellah Fourtassi. Modeling the interaction between perception-based and production-based learning in children’s early acquisition of semantic knowledge. In Arianna Bisazza and Omri Abend (eds.), Proceedings of the 25th Conference on Computational Natural Language Learning, pp. 3… find
  51. Mitja Nikolaus and Abdellah Fourtassi. Communicative Feedback in Language Acquisition. New Ideas in Psychology, 2023. doi: 10.1016/j.newideapsych.2022.100985. — [doi:10.1016/j.newideapsych.2022.100985](https://doi.org/10.1016/j.newideapsych.2022.100985) find
  52. Mitja Nikolaus, Laurent Prévot, and Abdellah Fourtassi. Communicative Feedback as a Mechanism Supporting the Production of Intelligible Speech in Early Childhood. In Proceedings of the 44th Annual Meeting of the Cognitive Science Society, 2022. doi: DOI:10.31234/osf.io/sg5mv. — [doi:10.31234/osf.io/sg5mv](https://doi.org/10.31234/osf.io/sg5mv) find
  53. Mitja Nikolaus, Laurent Prévot, and Abdellah Fourtassi. Communicative Feedback in Response to Children’s Grammatical Errors. In Proceedings for the 45th Annual Meeting of the Cognitive Science Society, 2023. find
  54. Anat Ninio and Catherine Snow. Language acquisition through language use: The functional sources of children’s early utterances. Categories and Processes in Language Acquisition, 1988. find
  55. OpenAI. ChatGPT: Optimizing language models for dialogue, 2022. URL https://openai.com/blog/chatgpt/. ↗
  56. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll 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… — Training language models to follow instructions with human feedback
  57. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll 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… — Training language models to follow instructions with human feedback
  58. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, pp. 311–318, USA, 2002. Association for Computational Linguistics. doi: 10.311…
  59. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. Exploring the limits of transfer learning with a unified text-to-text transformer, 2023. find
  60. Pranav Rajpurkar, Robin Jia, and Percy Liang. Know what you don’t know: Unanswerable questions for SQuAD. In Iryna Gurevych and Yusuke Miyao (eds.), Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 784–789, Melbourne, Australia, Ju… — Know What You Don't Know: Unanswerable Questions for SQuAD
  61. Mathieu Rita, Paul Michel, Rahma Chaabouni, Olivier Pietquin, Emmanuel Dupoux, and Florian Strub. Language evolution with deep learning. arXiv preprint arXiv:2403.11958, 2024. — [arXiv:2403.11958](https://arxiv.org/abs/2403.11958) find
  62. Craige Roberts. Information structure: Towards an integrated formal theory of pragmatics. Semantics and Pragmatics, 5:6–1, 1996. find
  63. Matthew Saxton. The Contrast Theory of negative input. Journal of Child Language, 24(1):139–161, 1997. ISSN 1469-7602, 0305-0009. doi: 10.1017/S030500099600298X. — [doi:10.1017/s030500099600298x](https://doi.org/10.1017/s030500099600298x) find
  64. Emanuel A. Schegloff. Repair after next turn: The last structurally provided defense of intersubjectivity in conversation. American Journal of Sociology, 97(5):1295–1345, 1992. doi: 10.1086/229903. URL https://doi.org/10.1086/229903. tex.eprint: https://doi.org/10.1086/229903. — [doi:10.1086/229903](https://doi.org/10.1086/229903) ↗
  65. Ted Schoneberger. Three Myths from the Language Acquisition Literature. The Analysis of Verbal Behavior, 26(1):107–131, April 2010. ISSN 0889-9401, 2196-8926. doi: 10.1007/BF03393086. URL http://link.springer.com/10.1007/BF03393086. — [doi:10.1007/bf03393086](https://doi.org/10.1007/bf03393086) ↗
  66. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms, 2017. find
  67. John Rogers Searle. Speech Acts: An Essay in the Philosophy of Language. Cambridge University Press, January 1969. ISBN 978-0-521-09626-3. Google-Books-ID: t3_WhfknvF0C. find
  68. Abigail See, Peter J. Liu, and Christopher D. Manning. Get to the point: Summarization with pointer-generator networks. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1073–1083, Vancouver, Canada, July 2017. Association for Com… find
  69. Ann Senghas and Marie Coppola. Children creating language: How nicaraguan sign language acquired a spatial grammar. Psychological Science, 12(4):323–328, 2001. doi: 10.1111/ 1467-9280.00359. URL https://doi.org/10.1111/1467-9280.00359. tex.eprint: https://doi.org/10.1111/1467-9280.00359. — [doi:10.1111/1467-9280.00359](https://doi.org/10.1111/1467-9280.00359) ↗
  70. Krijn F. Dignum Sepulveda. Towards pragmatic efficiency in natural language generation: Optimizing communication costs and utility in summarization tasks. [Unpublished Bachelor’s thesis], 2023. find
  71. Cory Shain, Idan Asher Blank, Marten van Schijndel, William Schuler, and Evelina Fedorenko. fMRI reveals language-specific predictive coding during naturalistic sentence comprehension. Neuropsychologia, 138:107307, 2020. ISSN 0028-3932. doi: https://doi.org/10.1016/j.neuropsychologia. 2019.107307. U… — [doi:10.1016/j.neuropsychologia](https://doi.org/10.1016/j.neuropsychologia) ↗
  72. C. E. Shannon. A Mathematical Theory of Communication. Bell System Technical Journal, 27(3): 379–423, 1948. ISSN 1538-7305. doi: 10.1002/j.1538-7305.1948.tb01338.x. — [doi:10.1002/j.1538-7305.1948.tb01338.x](https://doi.org/10.1002/j.1538-7305.1948.tb01338.x) find
  73. Mandyam Veerambudi Srinivasan, Simon Barry Laughlin, and Andreas Dubs. Predictive coding: a fresh view of inhibition in the retina. Proceedings of the Royal Society of London. Series B. Biological Sciences, 216(1205):427–459, 1982. Publisher: The Royal Society London. find
  74. Robert C. Stalnaker. Assertion. Pragmatics, pp. 315–332, December 1978. doi: 10.1163/ 9789004368873_013. find
  75. Michael Tomasello. Constructing a Language: A Usage-Based Theory of Language Acquisition. Harvard University Press, 2003. ISBN 978-0-674-01764-1. find
  76. Wai Keen Vong, Wentao Wang, A. Emin Orhan, and Brenden M. Lake. Grounded language acquisition through the eyes and ears of a single child. Science, 383(6682):504–511, 2024. doi: 10.1126/science.adi1374. URL https://www.science.org/doi/abs/10.1126/ science.adi1374. — [doi:10.1126/science.adi1374](https://doi.org/10.1126/science.adi1374) ↗
  77. Alex Warstadt and Samuel R Bowman. What artificial neural networks can tell us about human language acquisition. In Shalom Lappin and Jean-Philippe Bernardy (eds.), Algebraic Structures in Natural Language, pp. 17–60. CRC Press, 2022. Publisher: CRC Press.
  78. Alex Warstadt, Alicia Parrish, Haokun Liu, Anhad Mohananey, Wei Peng, Sheng-Fu Wang, and Samuel R. Bowman. BLiMP: The Benchmark of Linguistic Minimal Pairs for English. Transactions of the Association for Computational Linguistics, 8:377–392, July 2020. ISSN 2307-387X.
  79. Alex Warstadt, Leshem Choshen, Aaron Mueller, Adina Williams, Ethan Wilcox, and Chengxu Zhuang. Call for papers – the babylm challenge: Sample-efficient pretraining on a developmentally plausible corpus. Computing Research Repository, arXiv:2301.11796, 2023. find
  80. Ethan Gotlieb Wilcox, Richard Futrell, and Roger Levy. Using computational models to test syntactic learnability. Linguistic Inquiry, pp. 1–44, April 2023. ISSN 0024-3892. doi: 10.1162/ling_a_00491. URL https://doi.org/10.1162/ling_a_00491. — [doi:10.1162/ling_a_00491](https://doi.org/10.1162/ling_a_00491) ↗
  81. Xiaohan Xu, Ming Li, Chongyang Tao, Tao Shen, Reynold Cheng, Jinyang Li, Can Xu, Dacheng Tao, and Tianyi Zhou. A survey on knowledge distillation of large language models, 2024. find
  82. Daniel Yurovsky. A communicative approach to early word learning. New Ideas in Psychology, 50: 73–79, August 2018. ISSN 0732-118X. doi: 10.1016/j.newideapsych.2017.09.001. URL https://www.sciencedirect.com/science/article/pii/S0732118X17300077. — [doi:10.1016/j.newideapsych.2017.09.001](https://doi.org/10.1016/j.newideapsych.2017.09.001) ↗
  83. Yian Zhang, Alex Warstadt, Xiaocheng Li, and Samuel R. Bowman. When Do You Need Billions of Words of Pretraining Data? In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long… find
  84. Surprisal Bottleneck λ Response Reward 0.0 find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/stopler-2025-towards-developmentally-plausible-rewards-communicative/