CHART-6: Human-Centered Evaluation of Data Visualization Understanding in Vision-Language Models.
CoRR, May, 2025
MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations.
CoRR, April, 2025
ContextRef: Evaluating Referenceless Metrics for Image Description Generation.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Updating CLIP to Prefer Descriptions Over Captions.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
CommVQA: Situating Visual Question Answering in Communicative Contexts.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
Characterizing Image Accessibility on Wikipedia across Languages.
CoRR, 2023
Context-VQA: Towards Context-Aware and Purposeful Visual Question Answering.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
A Semantics for Causing, Enabling, and Preventing Verbs Using Structural Causal Models.
Proceedings of the 45th Annual Meeting of the Cognitive Science Society, 2023
Causal Distillation for Language Models.
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022
Inducing Causal Structure for Interpretable Neural Networks.
Proceedings of the International Conference on Machine Learning, 2022
Concadia: Towards Image-Based Text Generation with a Purpose.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics.
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022
Color Overmodification Emerges from Data-Driven Learning and Pragmatic Reasoning.
Proceedings of the 44th Annual Meeting of the Cognitive Science Society, 2022
Concadia: Tackling image accessibility with context.
CoRR, 2021
ReaSCAN: Compositional Reasoning in Language Grounding.
Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021
Modeling Subjective Assessments of Guilt in Newspaper Crime Narratives.
Proceedings of the 24th Conference on Computational Natural Language Learning, 2020
Production expectations modulate contrastive inference.
Proceedings of the 42th Annual Meeting of the Cognitive Science Society, 2020
When redundancy is rational: A Bayesian approach to 'overinformative' referring expressions.
CoRR, 2019
Uncertain evidence statements and guilt perception in iterative reproductions of crime stories.
Proceedings of the 41th Annual Meeting of the Cognitive Science Society, 2019
Mentioning atypical properties of objects is communicatively efficient.
Proceedings of the 39th Annual Meeting of the Cognitive Science Society, 2017