Mitigating Semantic Drift: Evaluating LLMs' Efficacy in Psychotherapy through MI Dialogue Summarization

• URL: http://arxiv.org/abs/2511.22818v1
• Date: Fri, 28 Nov 2025 00:37:58 GMT
• Title: Mitigating Semantic Drift: Evaluating LLMs' Efficacy in Psychotherapy through MI Dialogue Summarization
• Authors: Vivek Kumar, Pushpraj Singh Rajawat, Eirini Ntoutsi,
• Abstract summary: This study employs a mixed-methods approach to evaluate the efficacy of large language models (LLMs) in psychotherapy.<n>We use LLMs to generate precise summaries of motivational interviewing (MI) dialogues and design a two-stage annotation scheme.<n>Using expert-annotated MI dialogues as ground truth, we formulate multi-class classification tasks to assess model performance under progressive prompting techniques.
• Score: 1.877929053436765
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in large language models (LLMs) have shown their potential across both general and domain-specific tasks. However, there is a growing concern regarding their lack of sensitivity, factual incorrectness in responses, inconsistent expressions of empathy, bias, hallucinations, and overall inability to capture the depth and complexity of human understanding, especially in low-resource and sensitive domains such as psychology. To address these challenges, our study employs a mixed-methods approach to evaluate the efficacy of LLMs in psychotherapy. We use LLMs to generate precise summaries of motivational interviewing (MI) dialogues and design a two-stage annotation scheme based on key components of the Motivational Interviewing Treatment Integrity (MITI) framework, namely evocation, collaboration, autonomy, direction, empathy, and a non-judgmental attitude. Using expert-annotated MI dialogues as ground truth, we formulate multi-class classification tasks to assess model performance under progressive prompting techniques, incorporating one-shot and few-shot prompting. Our results offer insights into LLMs' capacity for understanding complex psychological constructs and highlight best practices to mitigate ``semantic drift" in therapeutic settings. Our work contributes not only to the MI community by providing a high-quality annotated dataset to address data scarcity in low-resource domains but also critical insights for using LLMs for precise contextual interpretation in complex behavioral therapy.

Related papers

• Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models [72.36715571932696]
  Narrative therapy helps individuals transform problematic life stories into empowering alternatives.<n>Current approaches lack realism in specialized psychotherapy and fail to capture therapeutic progression over time.<n>Int (Interactive Narrative Therapist) simulates expert narrative therapists by planning therapeutic stages, guiding reflection levels, and generating contextually appropriate expert-like responses.
  arXiv  Detail & Related papers  (2025-07-27T11:52:09Z)
• LlaMADRS: Prompting Large Language Models for Interview-Based Depression Assessment [75.44934940580112]
  This study introduces LlaMADRS, a novel framework leveraging open-source Large Language Models (LLMs) to automate depression severity assessment.<n>We employ a zero-shot prompting strategy with carefully designed cues to guide the model in interpreting and scoring transcribed clinical interviews.<n>Our approach, tested on 236 real-world interviews, demonstrates strong correlations with clinician assessments.
  arXiv  Detail & Related papers  (2025-01-07T08:49:04Z)
• Unlocking LLMs: Addressing Scarce Data and Bias Challenges in Mental Health [8.703482957316107]
  Large language models (LLMs) have shown promising capabilities in healthcare analysis but face several challenges like hallucinations, parroting, and bias manifestation.<n>In this work we introduce IC-AnnoMI, an expert-annotated motivational interviewing (MI) dataset built upon AnnoMI.<n> IC-AnnoMI employs targeted prompts accurately engineered through cues and tailored information, taking into account therapy style (empathy, reflection), contextual relevance, and false semantic change.
  arXiv  Detail & Related papers  (2024-12-17T15:01:07Z)
• PALLM: Evaluating and Enhancing PALLiative Care Conversations with Large Language Models [10.258261180305439]
  Large language models (LLMs) offer a new approach to assessing complex communication metrics. LLMs offer the potential to advance the field through integration into passive sensing and just-in-time intervention systems. This study explores LLMs as evaluators of palliative care communication quality, leveraging their linguistic, in-context learning, and reasoning capabilities.
  arXiv  Detail & Related papers  (2024-09-23T16:39:12Z)
• Rethinking the Alignment of Psychotherapy Dialogue Generation with Motivational Interviewing Strategies [30.237161801912453]
  Large language models (LLMs) have shown promise in generating psychotherapeutic dialogues, particularly in the context of motivational interviewing (MI)<n>Applying MI strategies, a set of MI skills, to generate more controllable therapeutic-adherent conversations with explainability provides a possible solution.
  arXiv  Detail & Related papers  (2024-08-12T23:19:02Z)
• Evaluating Large Language Models with Psychometrics [59.821829073478376]
  This paper offers a comprehensive benchmark for quantifying psychological constructs of Large Language Models (LLMs)<n>Our work identifies five key psychological constructs -- personality, values, emotional intelligence, theory of mind, and self-efficacy -- assessed through a suite of 13 datasets.<n>We uncover significant discrepancies between LLMs' self-reported traits and their response patterns in real-world scenarios, revealing complexities in their behaviors.
  arXiv  Detail & Related papers  (2024-06-25T16:09:08Z)
• Meta Reasoning for Large Language Models [58.87183757029041]
  We introduce Meta-Reasoning Prompting (MRP), a novel and efficient system prompting method for large language models (LLMs) MRP guides LLMs to dynamically select and apply different reasoning methods based on the specific requirements of each task. We evaluate the effectiveness of MRP through comprehensive benchmarks.
  arXiv  Detail & Related papers  (2024-06-17T16:14:11Z)
• GPT as Psychologist? Preliminary Evaluations for GPT-4V on Visual Affective Computing [74.68232970965595]
  Multimodal large language models (MLLMs) are designed to process and integrate information from multiple sources, such as text, speech, images, and videos. This paper assesses the application of MLLMs with 5 crucial abilities for affective computing, spanning from visual affective tasks and reasoning tasks.
  arXiv  Detail & Related papers  (2024-03-09T13:56:25Z)
• Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models [56.93074140619464]
  We propose RiC (Reasoning in Conversation), a method that focuses on solving subjective tasks through dialogue simulation. The motivation of RiC is to mine useful contextual information by simulating dialogues instead of supplying chain-of-thought style rationales. We evaluate both API-based and open-source LLMs including GPT-4, ChatGPT, and OpenChat across twelve tasks.
  arXiv  Detail & Related papers  (2024-02-27T05:37:10Z)
• A Computational Framework for Behavioral Assessment of LLM Therapists [7.665475687919995]
  Large language models (LLMs) like ChatGPT have increased interest in their use as therapists to address mental health challenges.<n>We propose BOLT, a proof-of-concept computational framework to systematically assess the conversational behavior of LLM therapists.
  arXiv  Detail & Related papers  (2024-01-01T17:32:28Z)
• Evaluating the Efficacy of Interactive Language Therapy Based on LLM for High-Functioning Autistic Adolescent Psychological Counseling [1.1780706927049207]
  This study investigates the efficacy of Large Language Models (LLMs) in interactive language therapy for high-functioning autistic adolescents. LLMs present a novel opportunity to augment traditional psychological counseling methods.
  arXiv  Detail & Related papers  (2023-11-12T07:55:39Z)
• Re-Reading Improves Reasoning in Large Language Models [87.46256176508376]
  We introduce a simple, yet general and effective prompting method, Re2, to enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs) Unlike most thought-eliciting prompting methods, such as Chain-of-Thought (CoT), Re2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. We evaluate Re2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality.
  arXiv  Detail & Related papers  (2023-09-12T14:36:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.