63 citations · 215 across the 16 of their papers we have counts for
17 papers
Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability
Krishnapriya Vishnubhotla, Hillary Dawkins, Isar Nejadgholi +1
Adapting foundation large language models to a user's task or preferred style through fine-tuning can result in compromising the model's safety. Previous works examined the effects…
Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency
Kathleen C. Fraser, Hillary Dawkins, Isar Nejadgholi +1
Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove th…
Gender-Neutral Machine Translation Strategies in Practice
Hillary Dawkins, Isar Nejadgholi, Chi-kiu Lo
Gender-inclusive machine translation (MT) should preserve gender ambiguity in the source to avoid misgendering and representational harms. While gender ambiguity often occurs natur…
When Detection Fails: The Power of Fine-Tuned Models to Generate Human-Like Social Media Text
Hillary Dawkins, Kathleen C. Fraser, Svetlana Kiritchenko
Detecting AI-generated text is a difficult problem to begin with; detecting AI-generated text on social media is made even more difficult due to the short text length and informal,…
WMT24 Test Suite: Gender Resolution in Speaker-Listener Dialogue Roles
Hillary Dawkins, Isar Nejadgholi, Chi-kiu Lo
We assess the difficulty of gender resolution in literary-style dialogue settings and the influence of gender stereotypes. Instances of the test suite contain spoken dialogue inter…
Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender Discourse
Rongchen Guo, Isar Nejadgholi, Hillary Dawkins +2
This work provides an explanatory view of how LLMs can apply moral reasoning to both criticize and defend sexist language. We assessed eight large language models, all of which dem…
Detecting AI-Generated Text: Factors Influencing Detectability with Current Methods
Kathleen C. Fraser, Hillary Dawkins, Svetlana Kiritchenko
Large language models (LLMs) have advanced to a point that even humans have difficulty discerning whether a text was generated by another human, or by a computer. However, knowing…
Projective Methods for Mitigating Gender Bias in Pre-trained Language Models
Hillary Dawkins, Isar Nejadgholi, Daniel Gillis +1
Mitigation of gender bias in NLP has a long history tied to debiasing static word embeddings. More recently, attention has shifted to debiasing pre-trained language models. We stud…
Second Order WinoBias (SoWinoBias) Test Set for Latent Gender Bias Detection in Coreference Resolution
Hillary Dawkins
We observe an instance of gender-induced bias in a downstream application, despite the absence of explicit gender words in the test cases. We provide a test set, SoWinoBias, for th…
Marked Attribute Bias in Natural Language Inference
Hillary Dawkins
Reporting and providing test sets for harmful bias in NLP applications is essential for building a robust understanding of the current problem. We present a new observation of gend…
Combining and estimation with randomized benchmarking and bounding the diamond distance
Hillary Dawkins, Joel Wallman, Joseph Emerson
The characterization of errors in a quantum system is a fundamental step for two important goals. First, learning about specific sources of error is essential for optimizing experi…
Data science for urban equity: Making gentrification an accessible topic for data scientists, policymakers, and the community
Bernease Herman, Gundula Proksch, Rachel Berney +5
The University of Washington eScience Institute runs an annual Data Science for Social Good (DSSG) program that selects four projects each year to train students from a wide range…
The impact of scaffolding and question structure on the gender gap
Hillary Dawkins, Holly Hedgeland, Sally Jordan
We address previous hypotheses about possible factors influencing the gender gap in attainment in physics. Specifically, previous studies claim that male advantage may arise from m…
Small Codes for Magic State Distillation
Mark Howard, Hillary Dawkins
Magic state distillation is a critical component in leading proposals for fault-tolerant quantum computation. Relatively little is known, however, about how to construct a magic st…
Diffusion Monte Carlo study of strongly interacting two-dimensional Fermi gases
Alexander Galea, Hillary Dawkins, Stefano Gandolfi +1
Ultracold atomic Fermi gases have been a popular topic of research, with attention being paid recently to two-dimensional (2D) gases. In this work, we perform T=0 ab initio diffusi…
Qutrit Magic State Distillation Tight in Some Directions
Hillary Dawkins, Mark Howard
Magic state distillation is a crucial component in the leading approaches to implementing universal fault tolerant quantum computation, with existing protocols for both qubit and h…
Uniqueness of Quantum States Compatible with Given Measurement Results
Jianxin Chen, Hillary Dawkins, Zhengfeng Ji +4
We discuss the uniqueness of quantum states compatible with given results for measuring a set of observables. For a given pure state, we consider two different types of uniqueness:…