Elamur Research⌕
☰
home / papers / 2025 / Socially Aware Language Technologies: Perspectives and Practices

Socially Aware Language Technologies: Perspectives and Practices

Paper · 2025 · Diyi Yang, Dirk Hovy, David Jurgens et al.

Summary

This perspective essay from the "Last Words" column of Computational Linguistics argues that many recurring weaknesses of modern NLP, including biased outputs, toxicity, fragile user trust, uneven performance across groups and difficult evaluation, have a single root. Systems largely ignore the social setting in which language is produced and used. The authors call this missing capacity "social awareness." Socially aware language technologies are systems that can detect and respond to social signals carried by language and its surroundings.

The paper offers no new dataset, model or benchmark. Its contribution is conceptual: a three-layer framework. Social factors (speaker, addressee, relationship, norms, culture, goals) inform task and model design. Interaction covers exchanges between people and NLP systems. Implication concerns wider effects on society.

The authors also warn that strong LLM scores on purely linguistic tasks can be mistaken for social competence. The framing matters for community-specific tools such as Ukrainian NLP because it treats cultural and contextual fit as a core research goal.

Key points

  • Authors are Diyi Yang (Stanford), Dirk Hovy (Bocconi), David Jurgens (Michigan) and Barbara Plank (LMU Munich). The paper is published under CC BY-NC-ND 4.0, DOI 10.1162/coli_a_00556, and was accepted in February 2025.
  • The framework is drawn as nested circles: social factors at the core, interaction in the middle, implication on the outside. The authors say these layers overlap and are not a strict partition.
  • The authors connect the concept to Goleman's four-part model of emotional intelligence, to Theory of Mind, and to Pentland's (2005) idea of socially aware computation. They state that social awareness does not require a moral stance, since appropriate perspectives will differ by country and language.
  • Evidence of shallow social ability in LLMs:
    • Sap et al. (2022) consider ToM tests for LLMs ill-posed.
    • Shu et al. (2024) find inconsistent answers to personality questionnaires.
    • LLMs also struggle with dialogue turn-taking (Ivey et al. 2024).
  • Drawing on Moravec's paradox, the authors present social awareness as NLP's next "hard" problem. They note that the challenge applies across roughly 7,000 languages, extends to vision and robotics, and carries risks such as privacy violations, echo chambers and misuse.

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

🎓Stanford UniversityStanford · United States434 works · 314,419 citations🎓Ludwig-Maximilians-Universität MünchenMunich · Germany107 works · 56,478 citations🎓University of MichiganAnn Arbor · United States70 works · 13,693 citations🎓Bocconi UniversityMilan · Italy28 works · 3,077 citations

 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 worksSafety Research · 543 works

Cite

Cite as Diyi Yang, Dirk Hovy, David Jurgens and Barbara Plank. 2025. Socially Aware Language Technologies: Perspectives and Practices. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00556

@article{yang2025socially,
  title = {{Socially Aware Language Technologies: Perspectives and Practices}},
  author = {Diyi Yang, Dirk Hovy, David Jurgens and Barbara Plank},
  journal = {Computational Linguistics},
  year = {2025},
  doi = {10.1162/coli\_a\_00556},
  url = {https://doi.org/10.1162/coli_a_00556}
}

References

22 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abercrombie, Gavin, Amanda Curry, Tanvi Dinkar, Verena Rieser, and Zeerak Talat. 2023. Mirages. On anthropomorphism in dialogue systems. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 4776–4790. https://doi.org/10.18653/v1/2023 .emnlp-main.290 Achlio… — Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions ↗
  2. Bird, Steven and Dean Yibarbuk. 2024. Centering the speech community. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 826–839. find
  3. Blair, Irene V., Jennifer E. Ma, and Alison P. Lenton. 2001. Imagining stereotypes away: The moderation of implicit stereotypes through mental imagery. Journal of Personality and Social Psychology, 81(5):828–841. https://doi.org/10 .1037/0022-3514.81.5.828, PubMed: 11708560 Blodgett, Su Lin, Solon B… — [doi:10.18653/v1/2020](https://doi.org/10.18653/v1/2020) find
  4. Breazeal, Cynthia. 2003. Emotion and sociable humanoid robots. International Journal of Human-computer Studies, 59(1–2):119–155. https://doi.org /10.1016/S1071-5819(03)00018-1 Brown, Tom, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam… — [doi:10.1016/s1071-5819(03)00018-1](https://doi.org/10.1016/s1071-5819%2803%2900018-1) ↗
  5. Choi, Minje, Ceren Budak, Daniel M. Romero, and David Jurgens. 2021. More than meets the tie: Examining the role of interpersonal relationships in social networks. In Proceedings of the International AAAI Conference on Web and Social Media, volume 15, pages 105–116. https://doi.org/10.1609/icwsm.v1… ↗
  6. Dev, Sunipa, Emily Sheng, Jieyu Zhao, Aubrie Amstutz, Jiao Sun, Yu Hou, Mattie Sanseverino, Jiin Kim, Akihiro Nishi, Nanyun Peng, et al. 2022. On measures of biases and harms in NLP. In Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022, pages 246–267. https://doi.org/10.186… find
  7. Gehman, Samuel, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A. Smith. 2020. RealToxicityPrompts: Evaluating neural toxic degeneration in language models. arXiv preprint arXiv:2009.11462. https://doi.org/10.18653/v1/2020.findings-emnlp .301 Goleman, Daniel. 2006. Social Intelligence: The Ne… ↗
  8. Bantam Dell Publishing Group. Gonen, Hila and Yoav Goldberg. 2019. Lipstick on a pig: Debiasing methods cover up systematic gender biases in word embeddings but do not remove them. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: H…
  9. Grant, Erin, Aida Nematzadeh, and Thomas L. Griffiths. 2017. How can memory-augmented neural networks pass a false-belief task? In CogSci. https://api.semanticscholar.org/CorpusID:7340345 Guo, Anhong, Ece Kamar, Jennifer Wortman Vaughan, Hanna Wallach, and Meredith Ringel Morris. 2020. Toward fairn… ↗
  10. Hershcovich, Daniel, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, Constanza Fierro, Katerina Margatina, Phillip Rust, and Anders Søgaard. 2022. Challenges and strategies in cross-cultural… find
  11. Kruk, Julia, Caleb Ziems, and Diyi Yang. 2023. Impressions: Visual semiotics and aesthetic impact understanding. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12273–12291. https://doi.org/10.18653/v1/2023 .emnlp-main.755 Kumar, Deepak, Yousef Anees… ↗
  12. Liu, Yihe, Anushk Mittal, Diyi Yang, and Amy Bruckman. 2022. Will AI console me when I lose my pet? Understanding perceptions of AI mediated email writing. In Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, pages 1–13. https://doi.org/10.1145/3491102.3517731 Ma, Bolei,… ↗
  13. Mittal, Trisha, Pooja Guhan, Uttaran Bhattacharya, Rohan Chandra, Aniket Bera, and Dinesh Manocha. 2020. EmotiCon: Context-aware multimodal emotion recognition using Frege’s Principle. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14234–14243. https://d… find
  14. Pawar, Siddhesh, Junyeong Park, Jiho Jin, Arnav Arora, Junho Myung, Srishti Yadav, Faiz Ghifari Haznitrama, Inhwa Song, Alice Oh, and Isabelle Augenstein. 2024. Survey of cultural awareness in language models: Text and beyond. arXiv preprint arXiv:2411.00860.
  15. Pentland, Alex. 2005. Socially aware computation and communication. In Proceedings of the 7th International Conference on Multimodal Interfaces, pages 199–199. https://doi.org/10 .1145/1088463.1088466 Pinker, Steven. 2003. The Language Instinct: How the Mind Creates Language. Penguin UK. Prabhakaran… find
  16. Premack, David and Guy Woodruff. 1978. Does the chimpanzee have a theory of mind? Behavioral and Brain Sciences, 1(4):515–526. https://doi.org/10.1017/S0140525X00076512 Ranathunga, Surangika and Nisansa de Silva. 2022. Some languages are more equal than others: Probing deeper into the linguistic di… ↗
  17. Sap, Maarten, Ronan Le Bras, Daniel Fried, and Yejin Choi. 2022. Neural theory-of-mind? On the limits of social intelligence in large LMs. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3762–3780. https://doi.org/10 .18653/v1/2022.emnlp-main.248 Shah… find
  18. Song, Yueqi, Catherine Cui, Simran Khanuja, Pengfei Liu, Fahim Faisal, Alissa Ostapenko, Genta Indra Winata, Alham Fikri Aji, Samuel Cahyawijaya, Yulia Tsvetkov, et al. 2023. Globalbench: A benchmark for global progress in natural language processing. arXiv preprint arXiv:2305.14716. https://doi .or… find
  19. Sorensen, Taylor, Jared Moore, Jillian Fisher, Mitchell Gordon, Niloofar Mireshghallah, Christopher Michael Rytting, Andre Ye, Liwei Jiang, Ximing Lu, Nouha Dziri, et al. 2024. A roadmap to pluralistic alignment. arXiv preprint arXiv:2402.05070.
  20. Spangher, Alexander, Nanyun Peng, Sebastian Gehrmann, and Mark Dredze. 2024. Do LLMs plan like human writers? Comparing journalist coverage of press releases with LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 21814–21828. https://doi.org /10.1… ↗
  21. Wright, Dustin, Arnav Arora, Nadav Borenstein, Srishti Yadav, Serge Belongie, and Isabelle Augenstein. 2024. LLM tropes: Revealing fine-grained values and opinions in large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 17085–17112. https://doi.org/1… find
  22. Ziems, Caleb, Omar Shaikh, Zhehao Zhang, William Held, Jiaao Chen, and Diyi Yang. 2023. Can large language models transform computational social science? Computational Linguistics, 50(1):237–291. https://doi.org/10.1162/coli a 00502 ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yang-2025-socially-aware-language-technologies-perspectives/