Publications
Jump to: preprints, peer-reviewed publications in ‘25, ‘24, ‘23, ‘22, ‘21, ‘20, ‘19, ‘18, ‘17, ‘16, blogs.
Preprints
- Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasović, Yonatan Belinkov
Measuring Faithfulness of Chains of Thought by Unlearning Reasoning Steps
Paper
Peer-Reviewed Publications
2025
- Karolina Stanczak, Nicholas Meade, Mehar Bhatia, Hattie Zhou, Konstantin Böttinger, Jeremy Barnes, Jason Stanley, Nicolas Papernot, Nicolas Chapados, Denis Therien, Timothy P Lillicrap, Ana Marasović, Sylvie Delacroix, Gillian K Hadfield, Siva Reddy
Societal Alignment Frameworks Can Improve LLM Alignment
ICLR 2025 Workshop on Bidirectional Human-AI Alignment
Paper
2024
-
Fateme Hashemi Chaleshtori, Atreya Ghosal, Alexander Gill, Purbid Bambroo, and Ana Marasović
On Evaluating Explanation Utility for Human-AI Decision Making in NLP
EMNLP Findings 2024
Paper -
Oliver Bentham*, Nathan Stringham*, and Ana Marasović
Chain-of-Thought Unfaithfulness as Disguised Accuracy
TMLR
Paper -
Ashim Gupta, Rishanth Rajendhran, Nathan Stringham, Vivek Srikumar, and Ana Marasović
Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness
NAACL
Paper
2023
-
Fateme Hashemi Chaleshtori, Atreya Ghosal, and Ana Marasović
On Evaluating Explanation Utility for Human-AI Decision-Making in NLP
The workshop “XAI in Action: Past, Present, and Future Applications” co-colated with NeurIPS 2023
Paper -
Jacob K. Johnson and Ana Marasović
How Much Consistency Is Your Accuracy Worth?
BlackboxNLP
Paper -
Jack Hessel, Ana Marasović, Jena D Hwang, Lillian Lee, Jeff Da, Rowan Zellers, Robert Mankoff, Yejin Choi
Do Androids Laugh at Electric Sheep? Humor “Understanding” Benchmarks from The New Yorker Caption Contest
ACL (best paper award 🌟)
Paper
2022
-
Abhilasha Ravichander, Matt Gardner, Ana Marasović
CondaQA: A Contrastive Reading Comprehension Dataset for Reasoning about Negation
EMNLP
(SoCal NLP Symposium best paper award)
Paper Dataset -
Alexis Ross, Matthew E. Peters, Ana Marasović
Does Self-Rationalization Improve Robustness to Spurious Correlations
EMNLP
Paper -
Shruti Palaskar, Akshita Bhagia, Yonatan Bisk, Florian Metze, Alan W Black, Ana Marasović
On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization
Findings of EMNLP
Paper -
Ana Marasović*, Iz Beltagy*, Doug Downey, Matthew E. Peters
Few-Shot Self-Rationalization with Natural Language Prompts
Findings of NAACL
Paper Code
2021
-
Sarah Wiegreffe* and Ana Marasović*
Teach Me to Explain: A Review of Datasets for Explainable NLP
NeurIPS
Paper Website -
Sarah Wiegreffe, Ana Marasović, Noah A. Smith
Measuring Association Between Labels and Free-Text Rationales
EMNLP
Paper -
Jesse Dodge, Maarten Sap, Ana Marasović, William Agnew, Gabriel Ilharco, Dirk Groeneveld, Matt Gardner
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus
EMNLP
Paper Demo Repo -
Kaiser Sun and Ana Marasović
Effective Attention Sheds Light On Interpretability
Findings of ACL
Paper Code -
Alexis Ross, Ana Marasović, Matthew E. Peters
Explaining NLP Models via Minimal Contrastive Editing (MiCE)
Findings of ACL
Paper -
Alexander M. Hoyle, Ana Marasović, Noah A. Smith
Promoting Graph Awareness in Linearized Graph-to-Text Generation
Findings of ACL
Paper -
Alon Jacovi, Ana Marasović, Tim Miller, Yoav Goldberg
Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI
ACM FAccT
Paper
2020
-
Ana Marasović, Chandra Bhagavatula, Jae Sung Park, Ronan Le Bras, Noah A. Smith, Yejin Choi
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
Findings of EMNLP
Paper Code -
Qiang Ning, Hao Wu, Pradeep Dasigi, Dheeru Dua, Matt Gardner, Robert L. Logan IV, Ana Marasović, Zhen Nie
Easy, Reproducible and Quality-Controlled Data Collection with CrowdAQ
EMNLP Demo
Paper Demo -
Suchin Gururangan, Ana Marasović, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, Noah A. Smith
Don’t Stop Pretraining: Adapt Language Models to Domains and Tasks
ACL (honorable mention for best paper)
Paper Code
2019
-
Pradeep Dasigi, Nelson F. Liu, Ana Marasović, Noah A. Smith, Matt Gardner
Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning
EMNLP
Paper Dataset -
Ana Marasović
Deep Learning With Sentiment Inference For Discourse-Oriented Opinion Analysis
PhD Thesis
PDF
2018
-
Ana Marasović and Anette Frank
SRL4ORL: Improving Opinion Role Labelling using Multi-task Learning with Semantic Role Labeling
NAACL-HLT
Paper Code -
Markus Zopf, Teresa Botschen, Tobias Falke, Benjamin Heinzerling, Ana Marasović, Todor Mihaylov, Avinesh PVS, Eneldo Mencia Loza, Johannes Fuernkranz, Anette Frank
What’s Important in a Text? An Extensive Evaluation of Linguistic Annotations for Summarization
SNAMS
Paper
2017
- Ana Marasović, Leo Born, Juri Opitz, Anette Frank
A Mention-Ranking Model for Abstract Anaphora Resolution
EMNLP
Paper Code
2016
-
Ana Marasović and Anette Frank
Multilingual Modal Sense Classification using a Convolutional Neural Network
Repl4NLP Workshop
Paper Code -
Ana Marasović, Mengfei Zhou, Alexis Palmer, Anette Frank
Linguistic Issues in Language Technology, Volume 14—Modality: Logic, Semantics, Annotation, and Machine Learning
Modal Sense Classification at Large: Paraphrase-Driven Sense Projection, Semantically Enriched Classification Models and Cross-Genre Evaluations
Paper
Blogs
-
I wrote for The Gradient about generalization in NLP. You can find the article here.