Publications

1. CommVQA: Situating Visual Question Answering in Communicative Contexts. [paper | data & code]
   Nandita Naik, Christopher Potts, Elisa Kreiss.
   EMNLP 2024.

2. Updating CLIP to Prefer Descriptions Over Captions. [paper | data & code]
   Amir Zur, Elisa Kreiss, Karel D'Oosterlinck, Christopher Potts, Atticus Geiger.
   EMNLP 2024.

3. Reference-Based Metrics Are Biased Against Blind and Low-Vision Users' Image Description Preferences. [paper]
   Rhea Kapur, Elisa Kreiss
   EMNLP 2024: Workshop on NLP for Positive Impact. Best paper award.

4. ContextRef: Evaluating referenceless metrics for image description generation. [paper | data & code]
   Elisa Kreiss*, Eric Zelikman*, Christopher Potts, Nick Haber.
   ICLR 2024.

5. Evaluating human and machine understanding of data visualizations. [paper]
   Arnav Verma, Kushin Mukherjee, Christopher Potts, Elisa Kreiss, Judith Fan.
   CogSci 2024.

6. Context-VQA: Towards context-aware and purposeful Visual Question Answering. [paper]
   Nandita Naik, Christopher Potts, Elisa Kreiss.
   ICCV 2023: 5th Workshop On Closing The Loop Between Vision And Language (CLVL).

7. Characterizing image accessibility on Wikipedia across languages. [paper | data & code]
   Elisa Kreiss, Krishna Srinivasan, Tiziano Piccardi, Jesus Adolfo Hermosillo, Cynthia Bennett, Michael S. Bernstein, Meredith Ringel Morris, Christopher Potts.
   WikiWorkshop 2023.

8. A semantics for causing, enabling, and preventing verbs grounded in structural causal models. [paper | data & code]
   Angela Cao*, Atticus Geiger*, Elisa Kreiss*, Thomas Icard, Tobias Gerstenberg.
   CogSci 2023.

9. Practical challenges for investigating abbreviation strategies. [paper]
   Elisa Kreiss, Subhashini Venugopalan, Shaun Kane, Meredith Ringel Morris.
   CHI 2023: The Second Workshop on Intelligent and Interactive Writing Assistants.

10. Context matters for image descriptions for accessibility: Challenges for referenceless evaluation metrics. [paper | data & code]
    Elisa Kreiss, Cynthia Bennett, Shayan Hooshmand, Eric Zelikman, Meredith Ringel Morris, Christopher Potts.
    EMNLP 2022.

11. Concadia: Towards image-based text generation with a purpose. [paper | data & code]
    Elisa Kreiss, Fei Fang, Noah D. Goodman, Christopher Potts.
    EMNLP 2022.

12. Color overmodification emerges from data-driven learning and pragmatic reasoning. [paper | data & code]
    Fei Fang, Kunal Sinha, Noah D. Goodman, Christopher Potts, Elisa Kreiss.
    CogSci 2022.

13. Inducing causal structure for interpretable neural networks
    Atticus Geiger, Zhengxuan Wu, Hanson Lu, Josh Rozner, Elisa Kreiss, Thomas Icard, Noah Goodman, Christopher Potts.
    ICML 2022.

14. Causal Distillation for Language Models
    Zhengxuan Wu, Atticus Geiger, Josh Rozner, Elisa Kreiss, Hanson Lu, Thomas Icard, Christopher Potts, Noah Goodman.
    NAACL 2022.

15. ReaSCAN: Compositional reasoning in language grounding. [paper | data & code | dataset website]
    Zhengxuan Wu*, Elisa Kreiss*, Desmond Ong, Christopher Potts.
    NeurIPS: Datasets & Benchmarks 2021.

16. Intuitive image descriptions are context-sensitive. [paper]
    Shayan Hooshmand, Elisa Kreiss, Christopher Potts.
    NeurIPS 2021: Workshop on Meaning in Context.

17. Modeling subjective assessments of guilt in newspaper crime narratives. [paper | data & code]
    Elisa Kreiss*, Zijian Wang*, Christopher Potts.
    CoNLL 2021.

18. Production expectations modulate contrastive inference. [paper | data & code | explore the data]
    Elisa Kreiss, Judith Degen.
    CogSci 2020.

19. When redundancy is useful: A Bayesian approach to "overinformative" referring expressions. [paper | paper (open access) | data & code]
    Judith Degen, Robert D. Hawkins, Caroline Graf, Elisa Kreiss, Noah D. Goodman.
    Psychological Review 2020.

20. Uncertain evidence statements and guilt perception in iterative reproductions of crime stories. [paper | data & code]
    Elisa Kreiss, Michael Franke, Judith Degen.
    CogSci 2019.