Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
Why Some Models Shatter and Others Don’t: The Geometry of Emergent Misalignment Across Architectures
Published:
Authors: Huy Nghiem
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
Child Protection Involvement among Homeless Families
Published in Journal of Public Child Welfare, 14(5), 2020
Detecting Cryptocurrency Pump-and-Dump Frauds Using Market and Social Signals
Published in Expert Systems with Applications, 182, 2021
Strategies for Constructing Household and Family Units with Linked Administrative Records
Published in Children and Youth Services Review, 120, 2021
A Population-based Study of Mental Health Diagnoses and Child Protection System Involvement among Medicaid-insured Children
Published in The Journal of Pediatrics, 252, 2023
A Decade of Tweets: Visualizing Racial Sentiments towards Minoritized Groups in the United States between 2011 and 2021
Published in Epidemiology, 35(1), 2024
You Gotta be a Doctor, Lin
Published in EMNLP 2024, 2024
Our empirical results indicate a preference among these models for hiring candidates with White female-sounding names over other demographic groups across 40 occupations
HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models
Published in EMNLP 2024, Findings, 2024
Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency through Chain-of-Thought Fine-tuning and Alignment
Published in AAAI 2025, PDLM Workshop, 2025
A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
Published in CVPR Workshop 2025, 2025
A survey on Large Vision-Langauge Models.
‘Rich Dad, Poor Lad’: How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?
Published in EMNLP 2025, 2025
How LLMs contextualize socioeconomic factors in college admissions.
Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment
Published in ML4H 2025, 2025
Simple and modular iterative frameworks to improve safety of healthcare AI assistants post-deployment via preference optimization
ResearchRubrics: A Benchmark of Prompts and Rubrics for Deep Research Agents
Published in ICLR 2026, 2026
SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
Published in ACL 2026, 2026
Data-efficient toxicity detection via LLM-based synthetic explanations.
Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring
Published in EMNLP 2026, 2026
Subtle race-gender evaluative framing in LLM-generated resume summaries undermines hiring fairness.
SoundnessBench: Can LLMs Judge Scientific Soundness?
Published in Under submission, 2026
Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning
Published in COLM 2026, Actionable Interpretability Workshop, 2026
CAIT: Mitigating and Certifying Counterfactual Sensitivity via Activation Editing
Published in Under submission, ICLR, 2026
HireWatch: Evaluating LLM Compliance with U.S. Employment Law under Contextual Pressure
Published in NeurIPS 2026, Evaluation & Datasets Track, 2026
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.