Sarah Wiegreffe

44 papers A* 8Journal 22Unranked 12

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Can you map it to English? The Role of Cross-Lingual Alignment in the Multilingual Performance of LLMs. EACL (Volume 1: Long Papers) Kartik Ravisankar, HyoJung Han, Sarah Wiegreffe, Marine Carpuat
2026	J	`jnl`	Quantifying the Gap between Understanding and Generation within Unified Multimodal Models. CoRR Chenlong Wang, Yuhang Chen, Zhihan Hu, Dongping Chen, Wenhu Chen, Sarah Wiegreffe, Tianyi Zhou
2025	A*	`conf`	Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions. ICLR Sarah Wiegreffe, Oyvind Tafjord, Yonatan Belinkov, Hannaneh Hajishirzi, Ashish Sabharwal
2025	J	`jnl`	Everything is Plausible: Investigating the Impact of LLM Rationales on Human Notions of Plausibility. CoRR Shramay Palta, Peter Rankel, Sarah Wiegreffe, Rachel Rudinger
2025	A*	`conf`	MIB: A Mechanistic Interpretability Benchmark. ICML Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fried Fiotto-Kaufman, Tal Haklay, Michael Hanna, Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, Yonatan Belinkov
2025	J	`jnl`	MIB: A Mechanistic Interpretability Benchmark. CoRR Aaron Mueller, Atticus Geiger, Sarah Wiegreffe, Dana Arad, Iván Arcuschin, Adam Belfki, Yik Siu Chan, Jaden Fiotto-Kaufman, Tal Haklay, Michael Hanna, Jing Huang, Rohan Gupta, Yaniv Nikankin, Hadas Orgad, Nikhil Prakash, Anja Reusch, Aruna Sankaranarayanan, Shun Shao, Alessandro Stolfo, Martin Tutek, Amir Zur, David Bau, Yonatan Belinkov
2025	A*	`conf`	On Linear Representations and Pretraining Data Frequency in Language Models. ICLR Jack Merullo, Noah A. Smith, Sarah Wiegreffe, Yanai Elazar
2025	J	`jnl`	On Linear Representations and Pretraining Data Frequency in Language Models. CoRR Jack Merullo, Noah A. Smith, Sarah Wiegreffe, Yanai Elazar
2024	J	`jnl`	Answer, Assemble, Ace: Understanding How Transformers Answer Multiple Choice Questions. CoRR Sarah Wiegreffe, Oyvind Tafjord, Yonatan Belinkov, Hannaneh Hajishirzi, Ashish Sabharwal
2024	—	`conf`	Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals. EMNLP (Findings) Yanai Elazar, Bhargavi Paranjape, Hao Peng, Sarah Wiegreffe, Khyathi Raghavi Chandu, Vivek Srikumar, Sameer Singh, Noah A. Smith
2024	J	`jnl`	Mechanistic? CoRR Naomi Saphra, Sarah Wiegreffe
2024	—	`conf`	Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoning. EMNLP (Findings) Shramay Palta, Nishant Balepur, Peter Rankel, Sarah Wiegreffe, Marine Carpuat, Rachel Rudinger
2024	J	`jnl`	Plausibly Problematic Questions in Multiple-Choice Benchmarks for Commonsense Reasoning. CoRR Shramay Palta, Nishant Balepur, Peter Rankel, Sarah Wiegreffe, Marine Carpuat, Rachel Rudinger
2024	A*	`conf`	The Art of Saying No: Contextual Noncompliance in Language Models. NeurIPS Faeze Brahman, Sachin Kumar, Vidhisha Balachandran, Pradeep Dasigi, Valentina Pyatkin, Abhilasha Ravichander, Sarah Wiegreffe, Nouha Dziri, Khyathi Raghavi Chandu, Jack Hessel, Yulia Tsvetkov, Noah A. Smith, Yejin Choi, Hanna Hajishirzi
2024	J	`jnl`	The Art of Saying No: Contextual Noncompliance in Language Models. CoRR Faeze Brahman, Sachin Kumar, Vidhisha Balachandran, Pradeep Dasigi, Valentina Pyatkin, Abhilasha Ravichander, Sarah Wiegreffe, Nouha Dziri, Khyathi Raghavi Chandu, Jack Hessel, Yulia Tsvetkov, Noah A. Smith, Yejin Choi, Hannaneh Hajishirzi
2024	—	`conf`	The Unreasonable Effectiveness of Easy Training Data for Hard Tasks. ACL (1) Peter Hase, Mohit Bansal, Peter Clark, Sarah Wiegreffe
2024	J	`jnl`	The Unreasonable Effectiveness of Easy Training Data for Hard Tasks. CoRR Peter Hase, Mohit Bansal, Peter Clark, Sarah Wiegreffe
2023	J	`jnl`	Attentiveness to Answer Choices Doesn't Always Entail High QA Accuracy. CoRR Sarah Wiegreffe, Matthew Finlayson, Oyvind Tafjord, Peter Clark, Ashish Sabharwal
2023	A*	`conf`	Editing Common Sense in Transformers. EMNLP Anshita Gupta, Debanjan Mondal, Akshay Krishna Sheshadri, Wenlong Zhao, Xiang Li, Sarah Wiegreffe, Niket Tandon
2023	J	`jnl`	Editing Commonsense Knowledge in GPT. CoRR Anshita Gupta, Debanjan Mondal, Akshay Krishna Sheshadri, Wenlong Zhao, Xiang Lorraine Li, Sarah Wiegreffe, Niket Tandon
2023	A*	`conf`	Increasing Probability Mass on Answer Choices Does Not Always Improve Accuracy. EMNLP Sarah Wiegreffe, Matthew Finlayson, Oyvind Tafjord, Peter Clark, Ashish Sabharwal
2023	J	`jnl`	Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals. CoRR Yanai Elazar, Bhargavi Paranjape, Hao Peng, Sarah Wiegreffe, Khyathi Chandu Raghavi, Vivek Srikumar, Sameer Singh, Noah A. Smith
2023	A*	`conf`	Self-Refine: Iterative Refinement with Self-Feedback. NeurIPS Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, Peter Clark
2023	J	`jnl`	Self-Refine: Iterative Refinement with Self-Feedback. CoRR Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Sean Welleck, Bodhisattwa Prasad Majumder, Shashank Gupta, Amir Yazdanbakhsh, Peter Clark
2022	—	`conf`	Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes. EMNLP (Findings) Kaige Xie, Sarah Wiegreffe, Mark O. Riedl
2022	J	`jnl`	Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes. CoRR Kaige Xie, Sarah Wiegreffe, Mark O. Riedl
2022	—	`conf`	Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning. EMNLP (Findings) Xiangyu Peng, Siyan Li, Sarah Wiegreffe, Mark O. Riedl
2022	—	`—`	Interpreting Neural Networks for and with Natural Language. Sarah Wiegreffe
2022	—	`ed.`	Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, BlackboxNLP@EMNLP 2022, Abu Dhabi, United Arab Emirates (Hybrid), December 8, 2022 BlackboxNLP@EMNLP Jasmijn Bastings, Yonatan Belinkov, Yanai Elazar, Dieuwke Hupkes, Naomi Saphra, Sarah Wiegreffe
2022	—	`conf`	Reframing Human-AI Collaboration for Generating Free-Text Explanations. NAACL-HLT Sarah Wiegreffe, Jack Hessel, Swabha Swayamdipta, Mark O. Riedl, Yejin Choi
2021	J	`jnl`	Inferring the Reader: Guiding Automated Story Generation with Commonsense Reasoning. CoRR Xiangyu Peng, Siyan Li, Sarah Wiegreffe, Mark O. Riedl
2021	—	`conf`	Measuring Association Between Labels and Free-Text Rationales. EMNLP (1) Sarah Wiegreffe, Ana Marasovic, Noah A. Smith
2021	J	`jnl`	Reframing Human-AI Collaboration for Generating Free-Text Explanations. CoRR Sarah Wiegreffe, Jack Hessel, Swabha Swayamdipta, Mark O. Riedl, Yejin Choi
2021	J	`jnl`	Teach Me to Explain: A Review of Datasets for Explainable NLP. CoRR Sarah Wiegreffe, Ana Marasovic
2021	—	`conf`	Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing. NeurIPS Datasets and Benchmarks Sarah Wiegreffe, Ana Marasovic
2020	A*	`conf`	Learning to Faithfully Rationalize by Construction. ACL Sarthak Jain, Sarah Wiegreffe, Yuval Pinter, Byron C. Wallace
2020	J	`jnl`	Learning to Faithfully Rationalize by Construction. CoRR Sarthak Jain, Sarah Wiegreffe, Yuval Pinter, Byron C. Wallace
2020	J	`jnl`	Measuring Association Between Labels and Free-Text Rationales. CoRR Sarah Wiegreffe, Ana Marasovic, Noah A. Smith
2019	—	`conf`	Attention is not not Explanation. EMNLP/IJCNLP (1) Sarah Wiegreffe, Yuval Pinter
2019	J	`jnl`	Attention is not not Explanation. CoRR Sarah Wiegreffe, Yuval Pinter
2019	—	`conf`	Clinical Concept Extraction for Document-Level Coding. BioNLP@ACL Sarah Wiegreffe, Edward Choi, Sherry Yan, Jimeng Sun, Jacob Eisenstein
2019	J	`jnl`	Clinical Concept Extraction for Document-Level Coding. CoRR Sarah Wiegreffe, Edward Choi, Sherry Yan, Jimeng Sun, Jacob Eisenstein
2018	—	`conf`	Explainable Prediction of Medical Codes from Clinical Text. NAACL-HLT James Mullenbach, Sarah Wiegreffe, Jon Duke, Jimeng Sun, Jacob Eisenstein
2018	J	`jnl`	Explainable Prediction of Medical Codes from Clinical Text. CoRR James Mullenbach, Sarah Wiegreffe, Jon Duke, Jimeng Sun, Jacob Eisenstein