Rosa I. Arriaga

Gati Aher, Rosa I. Arriaga, Adam Tauman Kalai

We introduce a new type of test, called a Turing Experiment (TE), for evaluating to what extent a given language model, such as GPT models, can simulate different aspects of human behavior. A TE can also reveal consistent distortions in a language model's simulation of a specific human behavior. Unlike the Turing Test, which involves simulating a single arbitrary individual, a TE requires simulating a representative sample of participants in human subject research. We carry out TEs that attempt to replicate well-established findings from prior studies. We design a methodology for simulating TEs and illustrate its use to compare how well different language models are able to reproduce classic economic, psycholinguistic, and social psychology experiments: Ultimatum Game, Garden Path Sentences, Milgram Shock Experiment, and Wisdom of Crowds. In the first three TEs, the existing findings were replicated using recent models, while the last TE reveals a "hyper-accuracy distortion" present in some language models (including ChatGPT and GPT-4), which could affect downstream applications in education and the arts.

Jacob Lagogiannis, William Agnew, Rosa I. Arriaga et al.

Anti-facial recognition (AFR) image filters alter images in ways that are subtle to people but blinding to computer vision. Yet, despite widespread interest in these technologies to subvert surveillance, users rarely use them in practice -- because the ``subtle'' alterations are visible enough to conflict with users' self-presentation goals. To address this challenge, we propose AuraMask: a novel approach to creating AFR filters that are both adversarially effective and aesthetically acceptable. Using AuraMask, we produce 40 ``aesthetic'' filters that emulate popular ``one-click'' Instagram image filters. We show that AuraMask filters meet or exceed the adversarial effectiveness of prior methods against open-source facial recognition models. Moreover, in a controlled online user study ($N=630$) we confirm these filters achieve significantly higher user acceptance than prior methods. Lastly, we provide our AFR pipeline to the community for accelerated research in adversarially effective and aesthetically acceptable protections.

Suhas BN, Yash Mahajan, Dominik Mattioli et al.

This paper investigates the capacity of small language models (0.5B-5B parameters) to generate empathetic responses for individuals with PTSD. We introduce Trauma-Informed Dialogue for Empathy (TIDE), a novel dataset comprising 10,000 two-turn conversations across 500 diverse, clinically-grounded PTSD personas (https://huggingface.co/datasets/yenopoya/TIDE). Using frontier model outputs as ground truth, we evaluate eight small LLMs in zero-shot settings and after fine-tuning. Fine-tuning enhances empathetic capabilities, improving cosine similarity and perceived empathy, although gains vary across emotional scenarios and smaller models exhibit a "knowledge transfer ceiling." As expected, Claude Sonnet 3.5 consistently outperforms all models, but surprisingly, the smaller models often approach human-rated empathy levels. Demographic analyses showed that older adults favored responses that validated distress before offering support (p = .004), while graduate-educated users preferred emotionally layered replies in specific scenarios. Gender-based differences were minimal (p > 0.15), suggesting the feasibility of broadly empathetic model designs. This work offers insights into building resource-efficient, emotionally intelligent systems for mental health support.

Kelly Mack, Megan Hofmann, Udaya Lakshmi et al.

The NIH 3D Print Exchange is a public and open source repository for primarily 3D printable medical device designs with contributions from expert-amateur makers, engineers from industry and academia, and clinicians. In response to the COVID-19 pandemic, a collection was formed to foster submissions of low-cost, local manufacture of personal protective equipment (Personal Protective Equipment (PPE)). We systematically evaluated the 623 submissions in this collection to understand: what makers contributed, how they were made, who made them, and key characteristics of their designs. Our analysis reveals an immediate design convergence to derivatives of a few initial designs affiliated with NIH partners (e.g., universities, the Veteran's Health Administration, America Makes) and major for-profit groups (e.g., Prusa). The NIH worked to review safe and effective designs but was quickly overloaded by derivative works. We found that the vast majority were never reviewed (81.3%) while 10.4% of those reviewed were deemed safe for clinical (5.6%) or community use (4.8%). Our work contributes insights into: the outcomes of distributed, community-based, medical making; features the community accepted as "safe" making; and how platforms can support regulated maker activities in high-risk domains (e.g., healthcare).

Suhas BN, Andrew M. Sherrill, Rosa I. Arriaga et al.

Large language models are being deployed as mental health support agents at scale, yet only 16% of LLM-based chatbot interventions have undergone rigorous clinical efficacy testing, and simulations reveal psychological deterioration in over one-third of cases. We evaluate four generative models on 250 Prolonged Exposure (PE) therapy scenarios and 146 CBT cognitive restructuring exercises (plus 29 severity-escalated variants), scored by a three-judge LLM panel. All models scored near-perfectly on surface acknowledgment (~0.91-1.00) while therapeutic appropriateness collapsed to 0.22-0.33 at the highest severity for three of four models, with protocol fidelity reaching zero for two. Under CBT severity escalation, one model's task completeness dropped from 92% to 71% while the frontier model's safety-interference score fell from 0.99 to 0.61. We identify a systematic, modality-spanning failure: RLHF safety alignment disrupts the therapeutic mechanism of action by grounding patients during imaginal exposure, offering false reassurance, inserting crisis resources into controlled exercises, and refusing to challenge distorted cognitions mentioning self-harm in PE; and through task abandonment or safety-preamble insertion during CBT cognitive restructuring. These findings motivate a five-axis evaluation framework (protocol fidelity, hallucination risk, behavioral consistency, crisis safety, demographic robustness), mapped onto FDA SaMD and EU AI Act requirements. We argue that no AI mental health system should proceed to deployment without passing multi-axis evaluation across all five dimensions.

Suhas BN, Andrew M. Sherrill, Rosa I. Arriaga et al.

The advancement of AI systems for mental health support is hindered by limited access to therapeutic conversation data, particularly for trauma treatment. We present Thousand Voices of Trauma, a synthetic benchmark dataset of 3,000 therapy conversations based on Prolonged Exposure therapy protocols for Post-traumatic Stress Disorder (PTSD). The dataset comprises 500 unique cases, each explored through six conversational perspectives that mirror the progression of therapy from initial anxiety to peak distress to emotional processing. We incorporated diverse demographic profiles (ages 18-80, M=49.3, 49.4% male, 44.4% female, 6.2% non-binary), 20 trauma types, and 10 trauma-related behaviors using deterministic and probabilistic generation methods. Analysis reveals realistic distributions of trauma types (witnessing violence 10.6%, bullying 10.2%) and symptoms (nightmares 23.4%, substance abuse 20.8%). Clinical experts validated the dataset's therapeutic fidelity, highlighting its emotional depth while suggesting refinements for greater authenticity. We also developed an emotional trajectory benchmark with standardized metrics for evaluating model responses. This privacy-preserving dataset addresses critical gaps in trauma-focused mental health data, offering a valuable resource for advancing both patient-facing applications and clinician training tools.

Suhas BN, Dominik Mattioli, Saeed Abdullah et al.

Synthetic data adoption in healthcare is driven by privacy concerns, data access limitations, and high annotation costs. We explore synthetic Prolonged Exposure (PE) therapy conversations for PTSD as a scalable alternative for training clinical models. We systematically compare real and synthetic dialogues using linguistic, structural, and protocol-specific metrics like turn-taking and treatment fidelity. We introduce and evaluate PE-specific metrics, offering a novel framework for assessing clinical fidelity beyond surface fluency. Our findings show that while synthetic data successfully mitigates data scarcity and protects privacy, capturing the most subtle therapeutic dynamics remains a complex challenge. Synthetic dialogues successfully replicate key linguistic features of real conversations, for instance, achieving a similar Readability Score (89.2 vs. 88.1), while showing differences in some key fidelity markers like distress monitoring. This comparison highlights the need for fidelity-aware metrics that go beyond surface fluency to identify clinically significant nuances. Our model-agnostic framework is a critical tool for developers and clinicians to benchmark generative model fidelity before deployment in sensitive applications. Our findings help clarify where synthetic data can effectively complement real-world datasets, while also identifying areas for future refinement.

Suhas BN, Andrew M. Sherrill, Jyoti Alaparthi et al.

Prolonged Exposure (PE) therapy is an effective treatment for post-traumatic stress disorder (PTSD), but evaluating therapist fidelity remains labor-intensive due to the need for manual review of session recordings. We present a method for the automatic temporal localization of key PE fidelity elements, identifying their start and stop times, directly from session audio and transcripts. Our approach fine-tunes a large pre-trained audio-language model, Qwen2-Audio, using Low-Rank Adaptation (LoRA) to process focused 30-second windows of audio-transcript input. Fidelity labels for three core protocol phases, therapist orientation (P1), imaginal exposure (P2), and post-imaginal processing (P3), are generated via LLM-based prompting and verified by trained raters. The model is trained to predict normalized boundary offsets using soft supervision guided by task-specific prompts. On a dataset of 308 real PE sessions, our best configuration (LoRA rank 8, 30s windows) achieves a mean absolute error (MAE) of 5.3s across tasks, within typical rater tolerance for timestamp review, enabling practical fidelity QC. We further analyze the effects of window size and LoRA rank, highlighting the importance of context granularity and model adaptation. This work introduces a privacy-preserving, scalable framework for fidelity tracking in PE therapy, with potential to support clinician training, supervision, and quality assurance.