Annika Marie Schoene

Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar et al.

General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety safeguards remain inadequate and inconsistent across clinical conditions. This study evaluates six proprietary LLMs across 16 DSM-5 conditions using four adversarial attack variants, introducing an eight-dimension harm taxonomy and a multi-dimensional evaluation framework. Results show that safeguards hold reliably only for suicide and self-harm, while conditions such as eating disorders, substance use disorder, and major depressive disorder exhibit failure rates of up to 100%. We argue that ethical design and deployment of these LLMs demand clearly defined harm categories across clinical conditions and implementation of safeguards accordingly. Until such safeguards are in place, these models pose significant risks to vulnerable populations, making their growing integration into educational settings a particularly concerning.

Annika Marie Schoene, John E. Ortega, Rodolfo Joel Zevallos et al.

Recent years have seen a marked increase in research that aims to identify or predict risk, intention or ideation of suicide. The majority of new tasks, datasets, language models and other resources focus on English and on suicide in the context of Western culture. However, suicide is global issue and reducing suicide rate by 2030 is one of the key goals of the UN's Sustainable Development Goals. Previous work has used English dictionaries related to suicide to translate into different target languages due to lack of other available resources. Naturally, this leads to a variety of ethical tensions (e.g.: linguistic misrepresentation), where discourse around suicide is not present in a particular culture or country. In this work, we introduce the 'Lexicography Saves Lives Project' to address this issue and make three distinct contributions. First, we outline ethical consideration and provide overview guidelines to mitigate harm in developing suicide-related resources. Next, we translate an existing dictionary related to suicidal ideation into 200 different languages and conduct human evaluations on a subset of translated dictionaries. Finally, we introduce a public website to make our resources available and enable community participation.

Rodolfo Zevallos, Annika Schoene, John E. Ortega

Suicidal ideation is a serious health problem affecting millions of people worldwide. Social networks provide information about these mental health problems through users' emotional expressions. We propose a multilingual model leveraging transformer architectures like mBERT, XML-R, and mT5 to detect suicidal text across posts in six languages - Spanish, English, German, Catalan, Portuguese and Italian. A Spanish suicide ideation tweet dataset was translated into five other languages using SeamlessM4T. Each model was fine-tuned on this multilingual data and evaluated across classification metrics. Results showed mT5 achieving the best performance overall with F1 scores above 85%, highlighting capabilities for cross-lingual transfer learning. The English and Spanish translations also displayed high quality based on perplexity. Our exploration underscores the importance of considering linguistic diversity in developing automated multilingual tools to identify suicidal risk. Limitations exist around semantic fidelity in translations and ethical implications which provide guidance for future human-in-the-loop evaluations.

Annika M Schoene, Cansu Canca

Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and creative forms of adversarial prompting, including manually generated test cases. In this work, we present two new test cases in mental health for (i) suicide and (ii) self-harm, using multi-step, prompt-level jailbreaking and bypass built-in content and safety filters. We show that user intent is disregarded, leading to the generation of detailed harmful content and instructions that could cause real-world harm. We conduct an empirical evaluation across six widely available LLMs, demonstrating the generalizability and reliability of the bypass. We assess these findings and the multilayered ethical tensions that they present for their implications on prompt-response filtering and context- and task-specific model development. We recommend a more comprehensive and systematic approach to AI safety and ethics while emphasizing the need for continuous adversarial testing in safety-critical AI deployments. We also argue that while certain clearly defined safety measures and guardrails can and must be implemented in LLMs, ensuring robust and comprehensive safety across all use cases and domains remains extremely challenging given the current technical maturity of general-purpose LLMs.

Benjamin Iyoya Irving, Annika Marie Schoene

The stock market provides a rich well of information that can be split across modalities, making it an ideal candidate for multimodal evaluation. Multimodal data plays an increasingly important role in the development of machine learning and has shown to positively impact performance. But information can do more than exist across modes -- it can exist across time. How should we attend to temporal data that consists of multiple information types? This work introduces (i) the MEANT model, a Multimodal Encoder for Antecedent information and (ii) a new dataset called TempStock, which consists of price, Tweets, and graphical data with over a million Tweets from all of the companies in the S&P 500 Index. We find that MEANT improves performance on existing baselines by over 15%, and that the textual information affects performance far more than the visual information on our time-dependent task from our ablation study.