Current LLMs lack the consistent and reliable socio-communicative skills needed for safe and effective use as healthcare advisors, and showed strength in non-hostility, mixed results in sensitivity and non-intrusiveness and performed poorly in structuring.
Abstract
Background. Effective clinical practice relies heavily on the socio-communicative skills of medical professionals. Large language models (LLMs) have been proposed for tasks such as triaging patients, report drafting or translating medical jargon to support informed decision-making. These applications require both factual and social competence. This study evaluates dialogues between LLMs and participants to assess the current state of socio-communicative competencies displayed in LLM-generated texts. Methods. We extracted a subset of extended dialogues from the HELP-Med dataset, comprising 1800 conversation transcripts of interactions between human participants seeking medical information and three different LLMs, GPT 4o, Llama 3 and Command R+. Two experts coded the transcripts for demonstrations of socio-communicative behaviours (non-hostility, sensitivity, structuring, non-intrusiveness) using the IC-MD instrument, originally designed to evaluate interactional competencies in medical student admissions. Results. The LLMs in our study showed strength in non-hostility, mixed results in sensitivity and non-intrusiveness and performed poorly in structuring. Conclusion. Current LLMs lack the consistent and reliable socio-communicative skills needed for safe and effective use as healthcare advisors. While existing frameworks for assessing interactional competencies may support the development of more socially responsive LLMs, they will require adaptation to account for the differences in desirable behaviour between humans and LLMs.
Overall, LLMs have the potential to complement peer responses in OHCs, but require greater emotional depth, reasoning transparency, and alignment with community norms.
M. Hussein, R. Doshi, L. He et al.· medRxiv· 0 citations
Despite recent advances in large language models (LLMs), their ability to generate empathetic mental health counseling responses in low-resource languages remains largely unexplored. To address this gap, we curate 625 authentic mental health cases from three complementary sources: (1) publicly available Facebook posts discussing mental health concerns, (2) transcripts from the Bangladeshi television program"Ami Akhon Ki Korbo", and (3) anonymized student questionnaire responses covering diverse emotional and psychological challenges. Based on these cases, we build an evaluation corpus comprising advice written by licensed clinical psychologists and responses generated by three modern proprietary LLMs: GPT-4o Mini, Claude 4.5 Haiku, and Gemini 2.5 Pro. We further propose the Role-Playing Reflective Chain-of-Thought Advisory Framework (RP-RCAF), a task-specific prompting strategy that combines expert-authored few-shot examples with structured self-reflection to produce supportive, culturally aware, and ethically aligned counseling through a compassionate advisor persona. We also introduce the Grok 4-Based Response Evaluation and Scoring Framework (G-REFS), which integrates automated assessment with expert psychologist validation across emotional sensitivity, cultural appropriateness, linguistic clarity, and ethical soundness. Experimental results show that RP-RCAF consistently outperforms conventional prompting across all evaluated models and produces responses that more closely align with professional psychological counseling.
Fatema Tuj Johora Faria, Mukaffi Bin Moin, Md. Mahfuzur Rahman et al.· arXiv.org· 0 citations
LLMs hold substantial potential to enhance healthcare teamwork by supporting clinical decisions, streamlining administrative workflows, and improving patient communication, however, ethical, legal, and accountability concerns remain.
Ilse Super, Olya Rezaeian, Onur Asan· International Journal of Med...· 0 citations
Speech-language pathology has traditionally been informed by sender-receiver models of communication and medicalised frameworks that prioritise impairment, diagnosis, and measurable outcomes. While these approaches have contributed substantially to clinical assessment and intervention, they can underrepresent relational, social, and embodied dimensions of communication that shape participation in everyday life.
PURPOSE
We argue that expanding the theoretical foundations of speech-language pathology through engagement with dialogic, sociological, and philosophical perspectives can enrich contemporary practice. Drawing on the work of sociological philosophers we explore communication as a dynamic, co-constructed, and polyphonic process in which meaning emerges through interaction, embodiment, and encounter.
METHOD
We reflect on three qualitative research projects involving people with communication disabilities. Across these examples, dialogic concepts illuminate aspects of practice that are often difficult to capture through conventional frameworks, including relational attunement, embodied knowledge, ethical responsiveness, and co-construction of meaning.
RESULT
Dialogic conceptualisations of communication offer speech-language pathologists a broader professional vision that extends beyond impairment-focused models towards more collaborative, person-centred, and contextually situated practice.
CONCLUSION
Dialogism offers concepts that can advance assessment, intervention, professional education, and research; greater engagement with theory can support more ethical, creative, and inclusive approaches to communication support.
Katherine Broomfield, Laura Hrastelj, Deborah James· International Journal of Spe...· 0 citations
Large language model (LLM)-enhanced chatbots are increasingly proposed as scalable tools for mental health support. However, their successful integration into healthcare depends not only on technical performance, but also on clinicians' acceptance of these technologies and their perceptions of the value these tools can bring to clinical practice. This study examined how psychotherapists and general practitioners (GPs) perceived the potential of the implementation of an LLM-enhanced psychoeducational chatbot in routine mental healthcare.
We conducted a qualitative, practice-informed study using four profession-specific focus groups with 48 clinicians in Italy, including 40 psychotherapists and 8 GPs. Participants directly interacted with a digital prototype based on the World Health Organization's Self-Help Plus (SH+) intervention, in which structured psychoeducational content was combined with constrained LLM-based conversational support. Data included participants' written reflections, structured group outputs, and researchers' field notes. Materials were analyzed using inductive thematic analysis.
Across both professional groups, participants evaluated the chatbot primarily in relation to its place within care pathways, its appropriateness for different users, the level of professional oversight required, and the risks associated with its use. Two distinct professional logics emerged. Psychotherapists framed the chatbot as a clinician-guided adjunct to psychotherapy, valuing it for therapeutic continuity while emphasizing the need for contextualization and supervision. GPs framed it as a low-threshold preventive and signposting resource, valuing accessibility and feasibility within primary care while emphasizing clear eligibility criteria and referral pathways. Although both groups identified similar safety concerns, they proposed different mitigation strategies, leading to distinct implementation models.
The findings suggest that the implementation of LLM-enhanced mental health chatbots is shaped by profession-specific logics rather than by a single, uniform model of adoption. Successful integration therefore requires context-sensitive governance and implementation strategies tailored to different care settings, professional responsibilities, and risk management assumptions.
Silvia Rizzi, S. Fait, M. Franzin et al.· Frontiers in Digital Health· 0 citations
Healthcare spaces are “contact zones,” where care may be practised using a lingua franca, or in various configurations of language codes. This paper examines two foundational constructs, communicative competence and health literacy, that are implicated in the contact zones of health care. I propose a heuristic framework of
spheres of activity
for locating, articulating, and understanding the facets and workings of measured constructs as a basis for a multiperspectival, interdisciplinary research agenda. The framework is applied to a health literacy test to explore the multilayered texture of construct activity. Moving to the applicable world of the hospital ward, I consider what “health literacy” may look like in authentic doctor–patient interaction. Finally, I discuss the relationship between the different activities: what is operationalized in tests, what is wished for in policy, and what is evident in practice. Even though the capacity to communicate is considered a key ingredient in mobilizing health literacy for shared decision-making, communication is barely represented in operationalized constructs. An orientation to the interactional repertoires of health care and the dynamic nature of knowledge co-construction in health decision-making could generate useful development in theory, measurement, and practice.
Susy Macqueen· Annual Review of Applied Lin...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
