"It seems like this past week has been quite challenging for you," a disembodied voice tells me, before proceeding to ask a series of increasingly personal questions. "Have you been feeling down or depressed?" "Can you describe what this feeling has been like for you?" "Does the feeling lift at all when something good happens?" When I respond to each one, my chatbot interviewer thanks me for my honesty and empathises with any issues. By the end of the conversation, I will have also spoken about my sleep patterns, sex drive and appetite for food.

Research links variations in the gene GRIN2A to a higher risk of developing schizophrenia and other forms of mental illness. A team of physicians specializing in genetics and neurology discovered that mental illnesses such as schizophrenia are closely linked to mutations in the GRIN2A gene. The scientists mantain that identifying this genetic risk factor opens up the possibility of designing preventive therapies in the future. The GRIN2A gene regulates communication between neurons by producing the GluN2A protein. When functioning optimally, it promotes the transmission of electrical signals between nerve cells and facilitates essential processes such as learning, memory, language, and brain development.

A timeline of genetic changes in millions of years of human evolution shows that variants linked to higher intelligence appeared most rapidly around 500,000 years ago, and were closely followed by mutations that made us more prone to mental illness. The findings suggest a "trade-off" in brain evolution between intelligence and psychiatric issues, says Ilan Libedinsky at the Center for Neurogenomics and Cognitive Research in Amsterdam, the Netherlands. Why did humans evolve big brains? "Mutations related to psychiatric disorders apparently involve part of the genome that also involves intelligence. So there's an overlap there," says Libedinsky. "[The advances in cognition] may have come at the price of making our brains more vulnerable to mental disorders."

Mindstate Design Labs, backed by Silicon Valley power players, has created what its CEO calls "the least psychedelic psychedelic that's psychoactive." While there's growing evidence that psychedelic drugs can effectively treat severe mental health conditions, especially in cases where traditional treatments have failed, they still come with downsides. Their hallucinogenic effects can be scary and overwhelming, with dosing sessions lasting several hours. Good treatment is heavily reliant on the individual's mindset going into a session and the environment in which they receive it. And though it's rare, psychedelics can sometimes worsen existing mental illness.

It might sound like a scenario from the most far-fetched of science fiction novels. But scientists have revealed the 32 terrifyingly real ways that AI systems could go rogue. Researchers warn that sufficiently advanced AI might start to develop'behavioural abnormalities' which mirror human psychopathologies. From relatively harmless'Existential Anxiety' to the potentially catastrophic 'Übermenschal Ascendancy', any of these machine mental illnesses could lead to AI escaping human control. As AI systems become more complex and gain the ability to reflect on themselves, scientists are concerned that their errors may go far beyond simple computer bugs.

Mental-health stigma remains a pervasive social problem that hampers treatment-seeking and recovery. Existing resources for training neural models to finely classify such stigma are limited, relying primarily on social-media or synthetic data without theoretical underpinnings. To remedy this gap, we present an expert-annotated, theory-informed corpus of human-chatbot interviews, comprising 4,141 snippets from 684 participants with documented socio-cultural backgrounds. Our experiments benchmark state-of-the-art neural models and empirically unpack the challenges of stigma detection. This dataset can facilitate research on computationally detecting, neutralizing, and counteracting mental-health stigma. Our corpus is openly available at https://github.com/HanMeng2004/Mental-Health-Stigma-Interview-Corpus.

Mental-illness stigma is a persistent social problem, hampering both treatment-seeking and recovery. Accordingly, there is a pressing need to understand it more clearly, but analyzing the relevant data is highly labor-intensive. Therefore, we designed a chatbot to engage participants in conversations; coded those conversations qualitatively with AI assistance; and, based on those coding results, built causal knowledge graphs to decode stigma. The results we obtained from 1,002 participants demonstrate that conversation with our chatbot can elicit rich information about people's attitudes toward depression, while our AI-assisted coding was strongly consistent with human-expert coding. Our novel approach combining large language models (LLMs) and causal knowledge graphs uncovered patterns in individual responses and illustrated the interrelationships of psychological constructs in the dataset as a whole. The paper also discusses these findings' implications for HCI researchers in developing digital interventions, decomposing human psychological constructs, and fostering inclusive attitudes.

Mental health disorders pose a growing public health concern in the Arab world, emphasizing the need for accessible diagnostic and intervention tools. Large language models (LLMs) offer a promising approach, but their application in Arabic contexts faces challenges including limited labeled datasets, linguistic complexity, and translation biases. This study comprehensively evaluates 8 LLMs, including general multi-lingual models, as well as bi-lingual ones, on diverse mental health datasets (such as AraDepSu, Dreaddit, MedMCQA), investigating the impact of prompt design, language configuration (native Arabic vs. translated English, and vice versa), and few-shot prompting on diagnostic performance. We find that prompt engineering significantly influences LLM scores mainly due to reduced instruction following, with our structured prompt outperforming a less structured variant on multi-class datasets, with an average difference of 14.5\%. While language influence on performance was modest, model selection proved crucial: Phi-3.5 MoE excelled in balanced accuracy, particularly for binary classification, while Mistral NeMo showed superior performance in mean absolute error for severity prediction tasks. Few-shot prompting consistently improved performance, with particularly substantial gains observed for GPT-4o Mini on multi-class classification, boosting accuracy by an average factor of 1.58. These findings underscore the importance of prompt optimization, multilingual analysis, and few-shot learning for developing culturally sensitive and effective LLM-based mental health tools for Arabic-speaking populations.

The growing prevalence and complexity of mental health disorders present significant challenges for accurate diagnosis and treatment, particularly in understanding the interplay between co-occurring conditions. Mental health disorders, such as depression and Anxiety, often co-occur, yet current datasets derived from social media posts typically focus on single-disorder labels, limiting their utility in comprehensive diagnostic analyses. This paper addresses this critical gap by proposing a novel methodology for cleaning, sampling, labeling, and combining data to create versatile multi-label datasets. Our approach introduces a synthetic labeling technique to transform single-label datasets into multi-label annotations, capturing the complexity of overlapping mental health conditions. To achieve this, two single-label datasets are first merged into a foundational multi-label dataset, enabling realistic analyses of co-occurring diagnoses. We then design and evaluate various prompting strategies for large language models (LLMs), ranging from single-label predictions to unrestricted prompts capable of detecting any present disorders. After rigorously assessing multiple LLMs and prompt configurations, the optimal combinations are identified and applied to label six additional single-disorder datasets from RMHD. The result is SPAADE-DR, a robust, multi-label dataset encompassing diverse mental health conditions. This research demonstrates the transformative potential of LLM-driven synthetic labeling in advancing mental health diagnostics from social media data, paving the way for more nuanced, data-driven insights into mental health care.

As large language models (LLMs) become increasingly integrated into operational workflows (LLM-Ops), there is a pressing need for effective guardrails to ensure safe and aligned interactions, including the ability to detect potentially unsafe or inappropriate content across languages. However, existing safe-for-work classifiers are primarily focused on English text. To address this gap for the Malaysian language, we present a novel safe-for-work text classifier tailored specifically for Malaysian language content. By curating and annotating a first-of-its-kind dataset of Malaysian text spanning multiple content categories, we trained a classification model capable of identifying potentially unsafe material using state-of-the-art natural language processing techniques. This work represents an important step in enabling safer interactions and content filtering to mitigate potential risks and ensure responsible deployment of LLMs.