Huy Nghiem

Huy Nghiem, Swetasudha Panda, Devashish Khatwani et al.

Large Language Models (LLMs) are increasingly used in healthcare, yet ensuring their safety and trustworthiness remains a barrier to deployment. Conversational medical assistants must avoid unsafe compliance without over-refusing benign queries. We present an iterative post-deployment alignment framework that applies Kahneman-Tversky Optimization (KTO) and Direct Preference Optimization (DPO) to refine models against domain-specific safety signals. Using the CARES-18K benchmark for adversarial robustness, we evaluate four LLMs (Llama-3B/8B, Meditron-8B, Mistral-7B) across multiple cycles. Our results show up to 42% improvement in safety-related metrics for harmful query detection, alongside interesting trade-offs against erroneous refusals, thereby exposing architecture-dependent calibration biases. We also perform ablation studies to identify when self-evaluation is reliable and when external or finetuned judges are necessary to maximize performance gains. Our findings underscore the importance of adopting best practices that balance patient safety, user trust, and clinical utility in the design of conversational medical assistants.

Huy Nghiem, Hal Daumé

The widespread use of social media necessitates reliable and efficient detection of offensive content to mitigate harmful effects. Although sophisticated models perform well on individual datasets, they often fail to generalize due to varying definitions and labeling of "offensive content." In this paper, we introduce HateCOT, an English dataset with over 52,000 samples from diverse sources, featuring explanations generated by GPT-3.5Turbo and curated by humans. We demonstrate that pretraining on HateCOT significantly enhances the performance of open-source Large Language Models on three benchmark datasets for offensive content detection in both zero-shot and few-shot settings, despite differences in domain and task. Additionally, HateCOT facilitates effective K-shot fine-tuning of LLMs with limited data and improves the quality of their explanations, as confirmed by our human evaluation.

Huy Nghiem, Phuong-Anh Nguyen-Le, John Prindle et al.

Large Language Models (LLMs) are increasingly involved in high-stakes domains, yet how they reason about socially sensitive decisions remains underexplored. We present a large-scale audit of LLMs' treatment of socioeconomic status (SES) in college admissions decisions using a novel dual-process framework inspired by cognitive science. Leveraging a synthetic dataset of 30,000 applicant profiles grounded in real-world correlations, we prompt 4 open-source LLMs (Qwen 2, Mistral v0.3, Gemma 2, Llama 3.1) under 2 modes: a fast, decision-only setup (System 1) and a slower, explanation-based setup (System 2). Results from 5 million prompts reveal that LLMs consistently favor low-SES applicants -- even when controlling for academic performance -- and that System 2 amplifies this tendency by explicitly invoking SES as compensatory justification, highlighting both their potential and volatility as decision-makers. We then propose DPAF, a dual-process audit framework to probe LLMs' reasoning behaviors in sensitive applications.

Huy Nghiem, Umang Gupta, Fred Morstatter

The propagation of offensive content through social media channels has garnered attention of the research community. Multiple works have proposed various semantically related yet subtle distinct categories of offensive speech. In this work, we explore meta-earning approaches to leverage the diversity of offensive speech corpora to enhance their reliable and efficient detection. We propose a joint embedding architecture that incorporates the input's label and definition for classification via Prototypical Network. Our model achieves at least 75% of the maximal F1-score while using less than 10% of the available training data across 4 datasets. Our experimental findings also provide a case study of training strategies valuable to combat resource scarcity.

Hieu Tran, Phuong-Anh Nguyen-Le, Huy Nghiem et al.

Machine translation systems fail when processing code-mixed inputs for low-resource languages. We address this challenge by curating VietMix, a parallel corpus of naturally occurring code-mixed Vietnamese text paired with expert English translations. Augmenting this resource, we developed a complementary synthetic data generation pipeline. This pipeline incorporates filtering mechanisms to ensure syntactic plausibility and pragmatic appropriateness in code-mixing patterns. Experimental validation shows our naturalistic and complementary synthetic data boost models' performance, measured by translation quality estimation scores, of up to 71.84 on COMETkiwi and 81.77 on XCOMET. Triangulating positive results with LLM-based assessments, augmented models are favored over seed fine-tuned counterparts in approximately 49% of judgments (54-56% excluding ties). VietMix and our augmentation methodology advance ecological validity in neural MT evaluations and establish a framework for addressing code-mixed translation challenges across other low-resource pairs.

Huy Nghiem, John Prindle, Jieyu Zhao et al.

Social science research has shown that candidates with names indicative of certain races or genders often face discrimination in employment practices. Similarly, Large Language Models (LLMs) have demonstrated racial and gender biases in various applications. In this study, we utilize GPT-3.5-Turbo and Llama 3-70B-Instruct to simulate hiring decisions and salary recommendations for candidates with 320 first names that strongly signal their race and gender, across over 750,000 prompts. Our empirical results indicate a preference among these models for hiring candidates with White female-sounding names over other demographic groups across 40 occupations. Additionally, even among candidates with identical qualifications, salary recommendations vary by as much as 5% between different subgroups. A comparison with real-world labor data reveals inconsistent alignment with U.S. labor market characteristics, underscoring the necessity of risk investigation of LLM-powered systems.

Huy Nghiem, Fred Morstatter

Content warning: This work displays examples of explicit and/or strongly offensive language. Fueled by a surge of anti-Asian xenophobia and prejudice during the COVID-19 pandemic, many have taken to social media to express these negative sentiments. Identifying these posts is crucial for moderation and understanding the nature of hate in online spaces. In this paper, we create and annotate a corpus of tweets to explore anti-Asian hate speech with a finer level of granularity. Our analysis reveals that this emergent form of hate speech often eludes established approaches. To address this challenge, we develop a model and an accompanied efficient training regimen that incorporates agreement between annotators. Our approach produces up to 8.8% improvement in macro F1 scores over a strong established baseline, indicating its effectiveness even in settings where consensus among annotators is low. We demonstrate that we are able to identify hate speech that is systematically missed by established hate speech detectors.