Picture for Alexis Ross

Alexis Ross

Language Modeling with Editable External Knowledge

Add code
Jun 17, 2024
Viaarxiv icon

Learning Phonotactics from Linguistic Informants

Add code
May 08, 2024
Viaarxiv icon

Toward In-Context Teaching: Adapting Examples to Students' Misconceptions

Add code
May 07, 2024
Viaarxiv icon

Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

Add code
Aug 01, 2023
Viaarxiv icon

ARIES: A Corpus of Scientific Paper Edits Made in Response to Peer Reviews

Add code
Jun 21, 2023
Viaarxiv icon

Inverse Scaling: When Bigger Isn't Better

Add code
Jun 15, 2023
Viaarxiv icon

CREST: A Joint Framework for Rationalization and Counterfactual Text Generation

Add code
May 26, 2023
Viaarxiv icon

Does Self-Rationalization Improve Robustness to Spurious Correlations?

Add code
Oct 24, 2022
Viaarxiv icon

Tailor: Generating and Perturbing Text with Semantic Controls

Add code
Jul 15, 2021
Figure 1 for Tailor: Generating and Perturbing Text with Semantic Controls
Figure 2 for Tailor: Generating and Perturbing Text with Semantic Controls
Figure 3 for Tailor: Generating and Perturbing Text with Semantic Controls
Figure 4 for Tailor: Generating and Perturbing Text with Semantic Controls
Viaarxiv icon

Competency Problems: On Finding and Removing Artifacts in Language Data

Add code
Apr 17, 2021
Figure 1 for Competency Problems: On Finding and Removing Artifacts in Language Data
Figure 2 for Competency Problems: On Finding and Removing Artifacts in Language Data
Figure 3 for Competency Problems: On Finding and Removing Artifacts in Language Data
Figure 4 for Competency Problems: On Finding and Removing Artifacts in Language Data
Viaarxiv icon