Rachel Rudinger

“You are grounded!”: Latent Name Artifacts in Pre-trained Language Models

2020

Pre-trained language models (LMs) may perpetuate biases originating in their training corpus to downstream models. We focus on artifacts associated with the representation of given names (e.g., Donald), which, depending on the corpus, may be …

What do Large Language Models Learn about Scripts?

2022

Script Knowledge However, such knowledge is expensive to produce manually and difficult to induce from text due to reporting bias In this work, we are interested in the scientific question of whether explicit script knowledge …

SODAPOP: Open-Ended Discovery of Social Biases in Social Commonsense Reasoning Models

2022 · arXiv (Cornell University)

A common limitation of diagnostic tests for detecting social biases in NLP models is that they may only detect stereotypic associations that are pre-specified by the designer of the test. Since enumerating all possible problematic …

Speaking the Right Language: The Impact of Expertise Alignment in User-AI Interactions

2025 · arXiv (Cornell University)

Using a sample of 25,000 Bing Copilot conversations, we study how the agent responds to users of varying levels of domain expertise and the resulting impact on user experience along multiple dimensions. Our findings show …

Arguments that Alter Minds: LLM Rationales Sway Human (and LLM) Notions of Plausibility

2026

We investigate the degree to which human (and LLM) plausibility judgments of multiplechoice commonsense benchmark answers are subject to influence by (im)plausibility arguments for or against an answer, in particular, using rationales generated by LLMs.We …

Social Bias in Elicited Natural Language Inferences

2017

We analyze the Stanford Natural Language Inference (SNLI) corpus in an investigation of bias and stereotyping in NLP data. The human-elicitation protocol employed in the construction of the SNLI makes it prone to amplifying bias …