Elisa Kreiss

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 26

Top Topics

Method For Automatically Generating

Causal Structure

Image Description

Question Answering

Top Venues

Publications

Elisa Kreiss, Eric Zelikman, Christopher Potts, Nick Haber
ContextRef: Evaluating Referenceless Metrics for Image Description Generation. ICLR (2024)
Amir Zur, Elisa Kreiss, Karel D'Oosterlinck, Christopher Potts, Atticus Geiger
Updating CLIP to Prefer Descriptions Over Captions. CoRR (2024)
Nandita Shankar Naik, Christopher Potts, Elisa Kreiss
CommVQA: Situating Visual Question Answering in Communicative Contexts. CoRR (2024)
Elisa Kreiss, Eric Zelikman, Christopher Potts, Nick Haber
ContextRef: Evaluating Referenceless Metrics For Image Description Generation. CoRR (2023)
Nandita Naik, Christopher Potts, Elisa Kreiss
Context-VQA: Towards Context-Aware and Purposeful Visual Question Answering. CoRR (2023)
Elisa Kreiss, Krishna Srinivasan, Tiziano Piccardi, Jesus Adolfo Hermosillo, Cynthia L. Bennett, Michael S. Bernstein, Meredith Ringel Morris, Christopher Potts
Characterizing Image Accessibility on Wikipedia across Languages. CoRR (2023)
Nandita Naik, Christopher Potts, Elisa Kreiss
Context-VQA: Towards Context-Aware and Purposeful Visual Question Answering. ICCV (Workshops) (2023)
Angela Cao, Atticus Geiger, Elisa Kreiss, Thomas Icard, Tobias Gerstenberg
A Semantics for Causing, Enabling, and Preventing Verbs Using Structural Causal Models. CogSci (2023)
Fei Fang, Kunal Sinha, Noah D. Goodman, Christopher Potts, Elisa Kreiss
Color Overmodification Emerges from Data-Driven Learning and Pragmatic Reasoning. CoRR (2022)
Elisa Kreiss, Cynthia L. Bennett, Shayan Hooshmand, Eric Zelikman, Meredith Ringel Morris, Christopher Potts
Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics. EMNLP (2022)
Elisa Kreiss, Cynthia L. Bennett, Shayan Hooshmand, Eric Zelikman, Meredith Ringel Morris, Christopher Potts
Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics. CoRR (2022)
Zhengxuan Wu, Atticus Geiger, Joshua Rozner, Elisa Kreiss, Hanson Lu, Thomas Icard, Christopher Potts, Noah D. Goodman
Causal Distillation for Language Models. NAACL-HLT (2022)
Elisa Kreiss, Fei Fang, Noah D. Goodman, Christopher Potts
Concadia: Towards Image-Based Text Generation with a Purpose. EMNLP (2022)
Atticus Geiger, Zhengxuan Wu, Hanson Lu, Josh Rozner, Elisa Kreiss, Thomas Icard, Noah D. Goodman, Christopher Potts
Inducing Causal Structure for Interpretable Neural Networks. ICML (2022)
Fei Fang, Kunal Sinha, Noah D. Goodman, Christopher Potts, Elisa Kreiss
Color Overmodification Emerges from Data-Driven Learning and Pragmatic Reasoning. CogSci (2022)
Zhengxuan Wu, Atticus Geiger, Josh Rozner, Elisa Kreiss, Hanson Lu, Thomas Icard, Christopher Potts, Noah D. Goodman
Causal Distillation for Language Models. CoRR (2021)
Elisa Kreiss, Noah D. Goodman, Christopher Potts
Concadia: Tackling image accessibility with context. CoRR (2021)
Atticus Geiger, Zhengxuan Wu, Hanson Lu, Josh Rozner, Elisa Kreiss, Thomas Icard, Noah D. Goodman, Christopher Potts
Inducing Causal Structure for Interpretable Neural Networks. CoRR (2021)
Zhengxuan Wu, Elisa Kreiss, Desmond C. Ong, Christopher Potts
ReaSCAN: Compositional Reasoning in Language Grounding. NeurIPS Datasets and Benchmarks (2021)
Zhengxuan Wu, Elisa Kreiss, Desmond C. Ong, Christopher Potts
ReaSCAN: Compositional Reasoning in Language Grounding. CoRR (2021)
Elisa Kreiss, Judith Degen
Production expectations modulate contrastive inference. CogSci (2020)
Elisa Kreiss, Zijian Wang, Christopher Potts
Modeling Subjective Assessments of Guilt in Newspaper Crime Narratives. CoNLL (2020)
Elisa Kreiss, Zijian Wang, Christopher Potts
Modeling subjective assessments of guilt in newspaper crime narratives. CoRR (2020)
Elisa Kreiss, Michael Franke, Judith Degen
Uncertain evidence statements and guilt perception in iterative reproductions of crime stories. CogSci (2019)
Judith Degen, Robert X. D. Hawkins, Caroline Graf, Elisa Kreiss, Noah D. Goodman
When redundancy is rational: A Bayesian approach to 'overinformative' referring expressions. CoRR (2019)
Elisa Kreiss, Robert X. D. Hawkins, Judith Degen, Noah D. Goodman
Mentioning atypical properties of objects is communicatively efficient. CogSci (2017)