William Sheffield

Research

• 2026

  Wugnectives: Novel Entity Inferences of Language Models from Discourse Connectives

  Daniel Brubaker, William Sheffield, Junyi Jessy Li, Kanishka Misra

  Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

  DOI BibTeX

  @inproceedings{brubaker-etal-2026-wugnectives,
    abstract     = {The role of world knowledge has been particularly crucial to predict the discourse connective that marks the discourse relation between two arguments, with language models (LMs) being generally successful at this task. We flip this premise in our work, and instead study the inverse problem of understanding whether discourse connectives can inform LMs about the world. To this end, we present Wugnectives, a dataset of 8,880 stimuli that evaluates LMs' inferences about novel entities in contexts where connectives link the entities to particular attributes. On investigating 17 different LMs at various scales, and training regimens, we found that tuning an LM to show reasoning behavior yields noteworthy improvements on most connectives. At the same time, there was a large variation in LMs' overall performance across connective type, with all models systematically struggling on connectives that express a concessive meaning. Our findings pave the way for more nuanced investigations into the functional role of language cues as captured by LMs.We release Wugnectives at https://github.com/kanishkamisra/wugnectives},
    isbn         = {979-8-89176-380-7},
    pages        = {6109--6127},
    doi          = {10.18653/v1/2026.eacl-long.289},
    url          = {https://aclanthology.org/2026.eacl-long.289/},
    publisher    = {Association for Computational Linguistics},
    address      = {Rabat, Morocco},
    year         = {2026},
    month        = {March},
    booktitle    = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
    editor       = {Demberg, Vera  and
  Inui, Kentaro  and
  Marquez, Lluís},
    author       = {Brubaker, Daniel  and
  Sheffield, William  and
  Li, Junyi Jessy  and
  Misra, Kanishka},
    title        = {Wugnectives: Novel Entity Inferences of Language Models from Discourse Connectives},
  }
  

• 2026

  Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs

  Junyi Jessy Li, Yang Janet Liu, Kanishka Misra, Valentina Pyatkin, William Sheffield

  Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026), 2026

  DOI BibTeX

  @inproceedings{li-etal-2026-course-discourse,
    abstract     = {The field of NLP has undergone vast, continuous transformations over the past few years, sparking debates going beyond discipline boundaries. This begs important questions in education: how do we design courses that bridge sub-disciplines in this shifting landscape? This paper explores this question from the angle of discourse processing, an area with rich linguistic insights and computational models for the intentional, attentional, and coherence structure of language. Discourse is highly relevant for open-ended or long-form text generation, yet this connection is under-explored in existing undergraduate curricula.We present a new course, ``Computational Discourse and Natural Language Generation''. The course is collaboratively designed by a team with complementary expertise and was offered for the first time in Fall 2025 as an upper-level undergraduate course, cross-listed between Linguistics and Computer Science. Our philosophy is to deeply integrate the theoretical and empirical aspects, and create an exploratory mindset inside the classroom and in the assignments. This paper describes the course in detail and concludes with takeaways from an independent survey as well as our vision for future directions.},
    isbn         = {979-8-89176-375-3},
    pages        = {45--58},
    doi          = {10.18653/v1/2026.teachingnlp-1.9},
    url          = {https://aclanthology.org/2026.teachingnlp-1.9/},
    publisher    = {Association for Computational Linguistics},
    address      = {Rabat, Morocco},
    year         = {2026},
    month        = {March},
    booktitle    = {Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026)},
    editor       = {Aßenmacher, Matthias  and
  Biester, Laura  and
  Borg, Claudia  and
  Kovács, György  and
  Mieskes, Margot  and
  Serrano, Sofia},
    author       = {Li, Junyi Jessy  and
  Liu, Yang Janet  and
  Misra, Kanishka  and
  Pyatkin, Valentina  and
  Sheffield, William},
    title        = {Which course? Discourse! Teaching Discourse and Generation in the Era of LLMs},
  }
  

• 2025

  Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs

  William Sheffield, Kanishka Misra, Valentina Pyatkin, Ashwini Deo, Kyle Mahowald, Junyi Jessy Li

  Findings of the Association for Computational Linguistics: ACL 2025, 2025

  DOI BibTeX

  @inproceedings{sheffield-etal-2025-just,
    abstract     = {Discourse particles are crucial elements that subtly shape the meaning of text. These words, often polyfunctional, give rise to nuanced and often quite disparate semantic/discourse effects,as exemplified by the diverse uses of the particle *just* (e.g., exclusive, temporal, emphatic). This work investigates the capacity of LLMs to distinguish the fine-grained senses of English *just*, a well-studied example in formal semantics, using data meticulously created and labeled by expert linguists. Our findings reveal that while LLMs exhibit some ability to differentiate between broader categories, they struggle to fully capture more subtle nuances, highlighting a gap in their understanding of discourse particles.},
    isbn         = {979-8-89176-256-5},
    pages        = {21704--21715},
    doi          = {10.18653/v1/2025.findings-acl.1117},
    url          = {https://aclanthology.org/2025.findings-acl.1117/},
    publisher    = {Association for Computational Linguistics},
    address      = {Vienna, Austria},
    year         = {2025},
    month        = {July},
    booktitle    = {Findings of the Association for Computational Linguistics: ACL 2025},
    editor       = {Che, Wanxiang  and
  Nabende, Joyce  and
  Shutova, Ekaterina  and
  Pilehvar, Mohammad Taher},
    author       = {Sheffield, William  and
  Misra, Kanishka  and
  Pyatkin, Valentina  and
  Deo, Ashwini  and
  Mahowald, Kyle  and
  Li, Junyi Jessy},
    title        = {Is It \textit JUST Semantics? A Case Study of Discourse Particle Understanding in LLMs},
  }
  

• 2023

  Elaborative Simplification as Implicit Questions Under Discussion

  Yating Wu, William Sheffield, Kyle Mahowald, Junyi Jessy Li

  Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

  DOI BibTeX

  @inproceedings{wu-etal-2023-elaborative,
    pages        = {5525--5537},
    doi          = {10.18653/v1/2023.emnlp-main.336},
    url          = {https://aclanthology.org/2023.emnlp-main.336/},
    publisher    = {Association for Computational Linguistics},
    address      = {Singapore},
    year         = {2023},
    month        = {December},
    booktitle    = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing},
    editor       = {Bouamor, Houda  and
  Pino, Juan  and
  Bali, Kalika},
    author       = {Wu, Yating  and
  Sheffield, William  and
  Mahowald, Kyle  and
  Li, Junyi Jessy},
    title        = {Elaborative Simplification as Implicit Questions Under Discussion},
  }
  

• 2022

  Evaluating Factuality in Text Simplification

  Ashwin Devaraj, William Sheffield, Byron Wallace, Junyi Jessy Li

  Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022

  DOI BibTeX

  @inproceedings{devaraj-etal-2022-evaluating,
    pages        = {7331--7345},
    doi          = {10.18653/v1/2022.acl-long.506},
    url          = {https://aclanthology.org/2022.acl-long.506/},
    publisher    = {Association for Computational Linguistics},
    address      = {Dublin, Ireland},
    year         = {2022},
    month        = {May},
    booktitle    = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
    editor       = {Muresan, Smaranda  and
  Nakov, Preslav  and
  Villavicencio, Aline},
    author       = {Devaraj, Ashwin  and
  Sheffield, William  and
  Wallace, Byron  and
  Li, Junyi Jessy},
    title        = {Evaluating Factuality in Text Simplification},
  }
  

About