相关论文: ADAPTS: Agentic Decomposition for Automated Protoc…

Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems. While…

Mental-health dialogue models are increasingly evaluated by AI-based evaluators, yet these evaluators often treat surface empathy, supportiveness, or fluency as evidence of safety. In this paper, we study a hidden failure mode that we call…

Attention-Deficit/Hyperactivity Disorder (ADHD) is a challenging disorder to study due to its complex symptomatology and diverse contributing factors. To explore how we can gain deeper insights on this topic, we performed a network analysis…

Large Language Models (LLMs) suffer from reliability issues on complex tasks, as existing decomposition methods are heuristic and rely on agent or manual decomposition. This work introduces a novel, systematic decomposition framework that…

AI models for medical diagnosis often exhibit uneven performance across patient populations due to heterogeneity in disease prevalence, imaging appearance, and clinical risk profiles. Existing algorithmic fairness approaches typically seek…

Most ATP benchmarks embed the final answer within the formal statement -- a convention we call "Easy Mode" -- a design that simplifies the task relative to what human competitors face and may lead to optimistic estimates of model…

Paraphrases represent a human's intuitive ability to understand expressions presented in various different ways. Current paraphrase evaluations of language models primarily use binary approaches, offering limited interpretability of…

Multi-modal affective computing aims to automatically recognize and interpret human attitudes from diverse data sources such as images and text, thereby enhancing human-computer interaction and emotion understanding. Existing approaches…

This paper introduces a novel paradigm for depression detection and treatment using advanced Large Language Models (LLMs): Generative Pre-trained Transformer 4 (GPT-4), Llama 2 chat, and Gemini. These LLMs are fine-tuned with specialized…

Background: Advancements in large language models (LLMs) have opened new possibilities in psychiatric interviews, an underexplored area where LLMs could be valuable. This study focuses on enhancing psychiatric interviews by analyzing…

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt…

As conversational models become increasingly available to the general public, users are engaging with this technology in social interactions. Such unprecedented interaction experiences may pose considerable social and psychological risks to…

Caregivers of individuals with autism spectrum disorder (ASD) often find the 77-item Autism Treatment Evaluation Checklist (ATEC) burdensome, limiting its use for routine monitoring. This study introduces a generalizable machine learning…

Recent advances in agentic AI have shifted the focus from standalone Large Language Models (LLMs) to integrated systems that combine LLMs with tools, memory, and other agents to perform complex tasks. These multi-agent architectures enable…

Graph neural networks (GNNs) excel on homophilic graphs where connected nodes share labels, but struggle with heterophilic graphs where edges do not imply similarity. Moreover, iterative message passing limits scalability due to…

ADHD is a prevalent disorder among the younger population. Standard evaluation techniques currently use evaluation forms, interviews with the patient, and more. However, its symptoms are similar to those of many other disorders like…

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

AI tools in pathology have improved screening throughput, standardized quantification, and revealed prognostic patterns that inform treatment. However, adoption remains limited because most systems still lack the human-readable reasoning…

Depression remains widely underdiagnosed and undertreated because stigma and subjective symptom ratings hinder reliable screening. To address this challenge, we propose a coarse-to-fine, multi-stage framework that leverages large language…

Automatic Affect Prediction (AAP) uses computational analysis of input data such as text, speech, images, and physiological signals to predict various affective phenomena (e.g., emotions or moods). These models are typically constructed…