activity
20202026
most citedPointwise Paraphrase Appraisal is Potentially Problematic

1 citations · 2 across the 8 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2025

Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control

Hannah Cyberey, David Evans

Large language models (LLMs) have transformed the way we access information. These models are often tuned to refuse to comply with requests that are considered harmful and to produ…

cs.CL2025

Unsupervised Concept Vector Extraction for Bias Control in LLMs

Hannah Cyberey, Yangfeng Ji, David Evans

Large language models (LLMs) are known to perpetuate stereotypes and exhibit biases. Various strategies have been proposed to mitigate these biases, but most work studies biases as…

cs.CL2024

Do Prevalent Bias Metrics Capture Allocational Harms from LLMs?

Hannah Cyberey, Yangfeng Ji, David Evans

Allocational harms occur when resources or opportunities are unfairly withheld from specific groups. Many proposed bias measures ignore the discrepancy between predictions, which a…

cs.CL2024

Addressing Both Statistical and Causal Gender Fairness in NLP Models

Hannah Chen, Yangfeng Ji, David Evans

Statistical fairness stipulates equivalent outcomes for every protected group, whereas causal fairness prescribes that a model makes the same prediction for an individual regardles…

cs.CL2022

Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models

Hannah Chen, Yangfeng Ji, David Evans

Traditional (fickle) adversarial examples involve finding a small perturbation that does not change an input's true label but confuses the classifier into outputting a different pr…

cs.CL20201 cited

Finding Friends and Flipping Frenemies: Automatic Paraphrase Dataset Augmentation Using Graph Theory

Hannah Chen, Yangfeng Ji, David Evans

Most NLP datasets are manually labeled, so suffer from inconsistent labeling or limited size. We propose methods for automatically improving datasets by viewing them as graphs with…