Alexis Ross
Alexis Ross
Allen Institute for Artificial Intelligence
Verified email at - Homepage
Cited by
Cited by
Explaining nlp models via minimal contrastive editing (mice)
A Ross, A Marasović, ME Peters
arXiv preprint arXiv:2012.13985, 2020
Probing What Different NLP Tasks Teach Machines about Function Word Comprehension
N Kim, R Patel, A Poliak, A Wang, P Xia, RT McCoy, I Tenney, A Ross, ...
arXiv preprint arXiv:1904.11544, 2019
Competency Problems: On Finding and Removing Artifacts in Language Data
M Gardner, W Merrill, J Dodge, ME Peters, A Ross, S Singh, N Smith
arXiv preprint arXiv:2104.08646, 2021
Tailor: Generating and Perturbing Text with Semantic Controls
A Ross, T Wu, H Peng, ME Peters, M Gardner
arXiv preprint arXiv:2107.07150, 2021
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
Z Wu, L Qiu, A Ross, E Akyürek, B Chen, B Wang, N Kim, J Andreas, ...
arXiv preprint arXiv:2307.02477, 2023
How well do NLI models capture verb veridicality?
A Ross, E Pavlick
Proceedings of the 2019 Conference on Empirical Methods in Natural Language …, 2019
Inverse Scaling: When Bigger Isn't Better
IR McKenzie, A Lyzhov, M Pieler, A Parrish, A Mueller, A Prabhu, ...
arXiv preprint arXiv:2306.09479, 2023
Learning Models for Actionable Recourse
A Ross, H Lakkaraju, O Bastani
Advances in Neural Information Processing Systems 34, 2021
Does Self-Rationalization Improve Robustness to Spurious Correlations?
A Ross, ME Peters, A Marasović
arXiv preprint arXiv:2210.13575, 2022
ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews
M D'Arcy, A Ross, E Bransom, B Kuehl, J Bragg, T Hope, D Downey
arXiv preprint arXiv:2306.12587, 2023
CREST: A Joint Framework for Rationalization and Counterfactual Text Generation
M Treviso, A Ross, NM Guerreiro, AFT Martins
arXiv preprint arXiv:2305.17075, 2023
Using Linear Approximations to Explain Complex, Blackbox Classifiers
AJ Ross
The system can't perform the operation now. Try again later.
Articles 1–12