Jeffrey Heer — accepted AI-conference papers

2024

BLADE: Benchmarking Language Model Agents for Data-Driven Science

Ken Gu, Ruoxi Shang, Ruien Jiang, Keying Kuang, Richard-John Lin, Donghe Lyu +10

EMNLP 2024finding

Data-driven scientific discovery requires the iterative integration of scientific domain knowledge, statistical expertise, and an understanding of data semantics to make nuanced analytical decisions, e.g., about which variables, transformations, and statistical models to consider. LM-based agents eq…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2021

Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models

Tongshuang Wu, Marco Tulio Ribeiro, Jeffrey Heer, Daniel Weld

ACL 2021long

While counterfactual examples are useful for analysis and training of NLP models, current generation methods either rely on manual labor to create very few counterfactuals, or only instantiate limited types of perturbations such as paraphrases or word substitutions. We present Polyjuice, a general-p…

Cited by 276 Source ↗PDF ↗code ↗Scholar ↗