Towards a Client-Centered Assessment of LLM Therapists by Client Simulation

• URL: http://arxiv.org/abs/2406.12266v2
• Date: Thu, 20 Jun 2024 22:06:47 GMT
• Title: Towards a Client-Centered Assessment of LLM Therapists by Client Simulation
• Authors: Jiashuo Wang, Yang Xiao, Yanran Li, Changhe Song, Chunpu Xu, Chenhao Tan, Wenjie Li,
• Abstract summary: This work focuses on a client-centered assessment of LLM therapists with the involvement of simulated clients. Ethically, asking humans to frequently mimic clients and exposing them to potentially harmful LLM outputs can be risky and unsafe. We propose ClientCAST, a client-centered approach to assessing LLM therapists by client simulation.
• Score: 35.715821701042266
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although there is a growing belief that LLMs can be used as therapists, exploring LLMs' capabilities and inefficacy, particularly from the client's perspective, is limited. This work focuses on a client-centered assessment of LLM therapists with the involvement of simulated clients, a standard approach in clinical medical education. However, there are two challenges when applying the approach to assess LLM therapists at scale. Ethically, asking humans to frequently mimic clients and exposing them to potentially harmful LLM outputs can be risky and unsafe. Technically, it can be difficult to consistently compare the performances of different LLM therapists interacting with the same client. To this end, we adopt LLMs to simulate clients and propose ClientCAST, a client-centered approach to assessing LLM therapists by client simulation. Specifically, the simulated client is utilized to interact with LLM therapists and complete questionnaires related to the interaction. Based on the questionnaire results, we assess LLM therapists from three client-centered aspects: session outcome, therapeutic alliance, and self-reported feelings. We conduct experiments to examine the reliability of ClientCAST and use it to evaluate LLMs therapists implemented by Claude-3, GPT-3.5, LLaMA3-70B, and Mixtral 8*7B. Codes are released at https://github.com/wangjs9/ClientCAST.

Related papers

• Aligning LLMs with Individual Preferences via Interaction [51.72200436159636]
  We train large language models (LLMs) that can ''interact to align'' We develop a multi-turn preference dataset containing 3K+ multi-turn conversations in tree structures. For evaluation, we establish the ALOE benchmark, consisting of 100 carefully selected examples and well-designed metrics to measure the customized alignment performance during conversations.
  arXiv  Detail & Related papers  (2024-10-04T17:48:29Z)
• 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)
• Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions [12.455050661682051]
  We propose a framework that employs two large language models (LLMs) via role-playing for simulating counselor-client interactions. Our framework involves two LLMs, one acting as a client equipped with a specific and real-life user profile and the other playing the role of an experienced counselor.
  arXiv  Detail & Related papers  (2024-08-28T13:29:59Z)
• An Active Inference Strategy for Prompting Reliable Responses from Large Language Models in Medical Practice [0.0]
  Large Language Models (LLMs) are non-deterministic, may provide incorrect or harmful responses, and cannot be regulated to assure quality control. Our proposed framework refines LLM responses by restricting their primary knowledge base to domain-specific datasets containing validated medical information. We conducted a validation study where expert cognitive behaviour therapy for insomnia therapists evaluated responses from the LLM in a blind format.
  arXiv  Detail & Related papers  (2024-07-23T05:00:18Z)
• CIBench: Evaluating Your LLMs with a Code Interpreter Plugin [68.95137938214862]
  We propose an interactive evaluation framework, named CIBench, to comprehensively assess LLMs' ability to utilize code interpreters for data science tasks. The evaluation dataset is constructed using an LLM-human cooperative approach and simulates an authentic workflow by leveraging consecutive and interactive IPython sessions. We conduct extensive experiments to analyze the ability of 24 LLMs on CIBench and provide valuable insights for future LLMs in code interpreter utilization.
  arXiv  Detail & Related papers  (2024-07-15T07:43:55Z)
• Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models [66.24055500785657]
  Traditional turn-based chat systems prevent users from verbally interacting with system while it is generating responses. To overcome these limitations, we adapt existing LLMs to listen users while generating output and provide users with instant feedback. We build a dataset consisting of alternating time slices of queries and responses as well as covering typical feedback types in instantaneous interactions.
  arXiv  Detail & Related papers  (2024-06-22T03:20:10Z)
• Can LLM be a Personalized Judge? [24.858529542496367]
  We investigate the reliability of LLM-as-a-Personalized-Judge, asking LLMs to judge user preferences based on personas. Our findings suggest that directly applying LLM-as-a-Personalized-Judge is less reliable than previously assumed. We introduce verbal uncertainty estimation into the LLM-as-a-Personalized-Judge pipeline, allowing the model to express low confidence on uncertain judgments.
  arXiv  Detail & Related papers  (2024-06-17T15:41:30Z)
• Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions [77.66677127535222]
  Auto-Arena is an innovative framework that automates the entire evaluation process using LLM-powered agents. In our experiments, Auto-Arena shows a 92.14% correlation with human preferences, surpassing all previous expert-annotated benchmarks.
  arXiv  Detail & Related papers  (2024-05-30T17:19:19Z)
• A Computational Framework for Behavioral Assessment of LLM Therapists [8.373981505033864]
  ChatGPT and other large language models (LLMs) have greatly increased interest in utilizing LLMs as therapists. We propose BOLT, a novel computational framework to study the conversational behavior of LLMs when employed as therapists. We compare the behavior of LLM therapists against that of high- and low-quality human therapy, and study how their behavior can be modulated to better reflect behaviors observed in high-quality therapy.
  arXiv  Detail & Related papers  (2024-01-01T17:32:28Z)
• Can ChatGPT Assess Human Personalities? A General Evaluation Framework [70.90142717649785]
  Large Language Models (LLMs) have produced impressive results in various areas, but their potential human-like psychology is still largely unexplored. This paper presents a generic evaluation framework for LLMs to assess human personalities based on Myers Briggs Type Indicator (MBTI) tests.
  arXiv  Detail & Related papers  (2023-03-01T06:16:14Z)

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.