The field of large language models (LLMs) is rapidly evolving, with significant advancements in their application to social science and healthcare research. Recent studies have demonstrated the potential of LLMs to improve access to justice, enhance mental health discourse, and facilitate more effective communication between humans and AI systems. Notably, LLMs have been shown to be effective in tasks such as multi-document summarization, legal interpretation, and implicature inference. However, challenges persist, including the need for more transparent and reliable models, as well as the importance of carefully designing LLM instructions to avoid paradigmatic bias. Overall, the field is moving towards more nuanced and contextually grounded applications of LLMs, with a focus on leveraging their strengths to drive positive social and healthcare outcomes. Noteworthy papers include: Digital Permission Structures, which explores the impact of celebrity mental health disclosures on Black masculine communities, and Leveraging Hierarchical Organization for Medical Multi-document Summarization, which demonstrates the effectiveness of hierarchical approaches to medical summarization. Additionally, the paper Implicature in Interaction highlights the importance of understanding implicature in human-LLM interaction, and Depth and Autonomy introduces a framework for evaluating LLM applications in social science research.
Advances in Large Language Models for Social Science and Healthcare Applications
Sources
Digital Permission Structures: How Celebrity Disclosure Enables Black Masculine Vulnerability in Online Mental Health Discourse
FicSim: A Dataset for Multi-Faceted Semantic Similarity in Long-Form Fiction
Can ChatGPT be a good follower of academic paradigms? Research quality evaluations in conflicting areas of sociology
Critical Insights into Leading Conversational AI Models
How Can AI Augment Access to Justice? Public Defenders' Perspectives on AI Adoption
Reasoning About Reasoning: Towards Informed and Reflective Use of LLM Reasoning in HCI
Leveraging Hierarchical Organization for Medical Multi-document Summarization
Detecting Religious Language in Climate Discourse
Human- vs. AI-generated tests: dimensionality and information accuracy in latent trait evaluation
Topic-aware Large Language Models for Summarizing the Lived Healthcare Experiences Described in Health Stories
Not ready for the bench: LLM legal interpretation is unstable and out of step with human judgments
Implicature in Interaction: Understanding Implicature Improves Alignment in Human-LLM Interaction
Depth and Autonomy: A Framework for Evaluating LLM Applications in Social Science Research
Through the Judge's Eyes: Inferred Thinking Traces Improve Reliability of LLM Raters
Evaluating the Impact of LLM-Assisted Annotation in a Perspectivized Setting: the Case of FrameNet Annotation
Interaction-Augmented Instruction: Modeling the Synergy of Prompts and Interactions in Human-GenAI Collaboration
Normative Reasoning in Large Language Models: A Comparative Benchmark from Logical and Modal Perspectives