← Search

Brendan Kennedy

3 accepted papers

2024

Reinforced Multiple Instance Selection for Speaker Attribute Prediction

NAACL 2024long

Language usage is related to speaker age, gender, moral concerns, political ideology, and other attributes. Current state-of-the-art methods for predicting these attributes take a speaker’s utterances as input and provide a prediction per speaker attribute. Most of these approaches struggle to handl…

2023

Social-Group-Agnostic Bias Mitigation via the Stereotype Content Model

ACL 2023long

Existing bias mitigation methods require social-group-specific word pairs (e.g., “man” – “woman”) for each social attribute (e.g., gender), restricting the bias mitigation to only one specified social attribute. Further, this constraint renders such methods impractical and costly for mitigating bias…

2021

On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning

NAACL 2021long

Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution. Previous works focus on detecting these biases, reducing bias in data representations, and using auxiliary training objectives to…