Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth

Riku Arakawa, Hiromu Yakura·May 24, 2024

Summary

This paper investigates the integration of Large Language Model (LLM)-powered chatbots in executive coaching, emphasizing their potential to enhance self-reflection and complement human coaching. Through workshops with coaches and a user study involving coach-client pairs, the research highlights the benefits of chatbots' 24/7 availability, reasoning capabilities, and support for self-guidance between sessions. However, it also identifies limitations, such as the need for human interaction for context understanding and empathy, and the importance of blending AI with human coaches for effective collaboration. Studies show that chatbots can foster self-disclosure, support goal-setting, and reduce human coach workload, but struggle with deep reflection and challenging questions. The research contributes guidelines for designing blended coaching systems, acknowledging the potential for expansion in accessibility while addressing ethical considerations. Future directions include larger-scale studies and the exploration of technology in other personal growth and well-being domains.

Paper digest

What problem does the paper attempt to solve? Is this a new problem?

The paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" aims to explore the potential of integrating chatbots powered by Large Language Models (LLMs) in collaboration with professional coaches to foster deep introspective reflection and behavior change, particularly in the field of executive coaching . This paper addresses the challenge of utilizing chatbots in coaching contexts that require profound introspection and strategic decision-making, such as leadership development, which is a relatively less explored area in prior research . The research focuses on augmenting self-reflective processes with conversational agents through a human-in-the-loop approach, emphasizing the benefits of chatbots' ubiquity and reasoning capabilities while identifying their limitations and design requirements for effective collaboration with human coaches . The paper's exploration of blending human and chatbot coaches in the context of executive coaching is a novel approach that aims to diversify the ways of leveraging chatbots in coaching practices .


What scientific hypothesis does this paper seek to validate?

This paper aims to validate the hypothesis that blending an LLM-powered chatbot with a human coach effectively supports self-reflection for leadership growth . The study explores the enduring value of human coaches and the benefits of a blended approach, emphasizing the importance of collaboration between human and artificial intelligence in chatbot-based reflection support . The research provides empirical evidence on the performance boundaries of LLM-powered chatbots in fostering deep self-reflection and suggests future directions for human-centered natural language processing and conversation analysis research .


What new ideas, methods, or models does the paper propose? What are the characteristics and advantages compared to previous methods?

The paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" proposes several innovative ideas, methods, and models in the field of coaching and reflective conversational agents . Here are some key points from the paper:

  1. Blended Approach: The paper introduces a blended approach that combines the strengths of human coaches and chatbot coaches to enhance the reflection experience for individuals seeking leadership growth. This approach emphasizes the enduring value of human coaches while leveraging the benefits of chatbot technology .

  2. LLM-Powered Chatbot: The paper explores the potential of an LLM-powered chatbot to facilitate deep reflection for leadership development within the context of executive coaching. This innovative chatbot aims to support self-reflection and growth through a combination of human and AI coaching .

  3. Qualitative Data Analysis: The study conducted in the paper involves qualitative data analysis to understand the effectiveness and value of the blended coaching approach. The findings highlight the importance of combining human and chatbot coaches to achieve optimal reflection outcomes .

  4. Future Research Directions: The paper suggests future research directions, including the need for larger participant pools from diverse coaching organizations to validate the findings further. It also emphasizes the importance of conducting long-term studies to mitigate novelty effects and enhance the understanding of the blended coaching approach .

  5. Ethical Considerations: The paper discusses ethical considerations related to introducing chatbots in coaching settings, such as data privacy, psychological safety, and the risk of bias or discrimination. It emphasizes the importance of clarifying the role of chatbots and ensuring confidentiality, aligning with established standards in executive coaching .

  6. Socio-Technical Tool Development: The paper proposes extending the blended coaching approach to develop a socio-technical tool that can be applied across different domains. This tool aims to leverage the blended coaching model in various contexts beyond leadership growth, offering practitioners a versatile approach to coaching .

Overall, the paper presents a comprehensive framework for integrating human and chatbot coaches to support self-reflection and leadership development, highlighting the potential of blended coaching approaches in the era of advanced AI technologies . The paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" introduces a novel approach that combines the strengths of human coaches and chatbot coaches to enhance self-reflection for leadership development . Here are the characteristics and advantages of this blended approach compared to previous methods:

  1. Blended Approach: The paper emphasizes the enduring value of human coaches while leveraging the benefits of chatbot technology to support self-reflection and leadership growth . This blended approach aims to provide a comprehensive coaching experience by combining the strengths of both human and AI coaches.

  2. Empirical Evidence: The study conducted in the paper involves empirical findings that highlight the benefits of the blended coaching approach, especially in the context of executive coaching . The results confirm the advantages of conversational agents in complementing existing coaching practices for leadership growth.

  3. Client Engagement: The blended initiative of human and chatbot coaches promotes client engagement and self-disclosure . Clients favored the overall experience of text coaching due to the designed approach of blending human and chatbot coaches, maintaining engagement throughout the trial.

  4. Optimal Reflection Experience: The paper synthesizes a way to combine human and chatbot coaches to realize an optimal reflection experience for individuals seeking leadership growth . This approach offers a set of key factors guided by empirical evidence from actual executive coaching sessions.

  5. Future Research Directions: The paper suggests the need for larger participant pools from diverse coaching organizations to further validate the findings and enhance understanding of the blended coaching approach . Conducting long-term studies is also recommended to mitigate novelty effects and provide deeper insights into the effectiveness of the approach.

  6. Ethical Considerations: The paper discusses ethical considerations related to introducing chatbots in coaching settings, emphasizing the importance of data privacy, psychological safety, and avoiding bias or discrimination . It highlights the necessity of clarifying the role of chatbots and ensuring confidentiality in line with established standards in executive coaching.

Overall, the blended approach proposed in the paper offers a unique combination of human expertise and AI technology to support deep self-reflection and leadership development, providing a promising framework for enhancing coaching practices in the context of executive coaching .


Do any related researches exist? Who are the noteworthy researchers on this topic in this field?What is the key to the solution mentioned in the paper?

In the field of chatbot-based coaching and self-reflection for leadership growth, several noteworthy researchers have contributed to related research:

  • Mara Castro Correia, Nuno Rebelo dos Santos, and Jonathan Passmore have provided insights into the Coach-Coachee-Client relationship .
  • Fred D. Davis explored the relationship between perceived usefulness, perceived ease of use, and user acceptance of information technology .
  • Harry Barton Essel, Dimitrios Vlachopoulos, and others studied the impact of a virtual teaching assistant (chatbot) on students' learning in Ghanaian higher education .
  • Liang, Hai Trung Le, and others delved into design opportunities for reflective conversational agents to reduce compulsive smartphone use .

The key to the solution mentioned in the paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" lies in leveraging chatbots to facilitate deep introspective reflection, especially in the context of Large Language Models (LLMs) . This approach aims to augment the potential of conversational agents to support individuals in achieving professional goals, such as leadership growth, by fostering introspective analysis and strategic decision-making .


How were the experiments in the paper designed?

The experiments in the paper were designed as follows:

  • The experimenter explained the use of the chatbot coach to the human coach, who then conducted a session with the client to set goals and plan how to use the chatbot coach .
  • The client filled out questionnaires regarding their behavioral intention and authenticity scale .
  • The human coach conducted a session with the client to reflect on the two weeks of text coaching .
  • Semi-structured interviews were conducted with both the coach and the client individually by the experimenter .
  • The client then conducted text coaching sessions at their own pace with the chatbot coach, and the human coach received a summary of the text coaching and any questions from the client .
  • The study involved metrics to assess the impact on the client, including questionnaire-based measurements filled out by the clients every time they used the prototype to evaluate the outcome of reflection and attitude toward using the system .

What is the dataset used for quantitative evaluation? Is the code open source?

The dataset used for quantitative evaluation in the study is based on questionnaire-based measurements filled out by clients every time they used the prototype . The code used in the study is not explicitly mentioned to be open source in the provided context.


Do the experiments and results in the paper provide good support for the scientific hypotheses that need to be verified? Please analyze.

The experiments and results presented in the paper provide strong support for the scientific hypotheses that needed verification. The study conducted on the blended approach of using an LLM-powered chatbot coach and a human coach for self-reflection in leadership growth revealed valuable insights. The qualitative data from the study highlighted the enduring value of human coaches and the benefits of the blended approach, emphasizing the importance of securing commitment with human coaches . The study also demonstrated that clients' behavioral intention was sustained, and their authenticity scale was affected positively throughout the trial, confirming the benefits of conversational agents in complementing existing coaching practices for leadership development .

Moreover, the study's implications summarized a guideline to support the achievement of professional goals by blending an LLM-powered chatbot coach and a human coach, emphasizing the necessity of collaboration between human and artificial intelligence in chatbot-based reflection support . The findings provided empirical evidence guided by coaches and their clients in actual executive coaching sessions, outlining key factors for effective self-reflection and hinting at future directions for human-centered natural language processing and conversation analysis research .

Overall, the experiments and results in the paper offer a comprehensive analysis of the effectiveness of integrating chatbot coaches with human coaches for self-reflection in leadership growth. The study's outcomes provide valuable insights into the benefits of conversational agents in coaching practices and emphasize the significance of a blended approach for fostering deep self-reflection effectively .


What are the contributions of this paper?

The paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" makes several significant contributions:

  • It explores the design opportunities for reflective conversational agents to reduce compulsive smartphone use .
  • The paper incorporates a reflective thinking promoting mechanism into AI-supported English writing environments .
  • It examines the effects of coachee readiness and core self-evaluations on leadership coaching outcomes through a controlled trial .
  • The study accompanies reflection processes by an AI-based StudiCoachBot, focusing on rapport building in human-machine coaching using self-disclosure .
  • It examines AI methods for micro-coaching dialogs, providing insights into the use of AI in coaching interactions .
  • The research offers a guideline to support the achievement of professional goals by blending an LLM-powered chatbot coach and a human coach, emphasizing the collaboration between human and artificial intelligence in chatbot-based reflection support .
  • It provides empirical evidence guided by coaches and their clients in actual executive coaching sessions, outlining key factors for the successful integration of LLM-powered chatbots in fostering deep self-reflection .
  • The findings of the paper delineate the current performance boundaries of LLM-powered chatbots in fostering self-reflection and suggest future directions for human-centered natural language processing and conversation analysis research .

What work can be continued in depth?

Further work in this area can focus on conducting a larger user study involving more participants, especially coaches, from different organizations to validate the findings . Additionally, a comparison study with a baseline condition could be beneficial to provide additional evidence on the effectiveness of the blended approach . Long-term studies could also be conducted to reduce the possibility of novelty effects and assess sustained impact . Ethical considerations, such as data privacy, psychological safety, and monitoring for bias or discrimination in chatbots, should be further discussed to advance the deployment of chatbots in coaching .


Introduction
Background
Emergence of LLMs in coaching industry
Current limitations of traditional coaching methods
Objective
To evaluate the impact of chatbots on executive coaching
To explore their potential for self-reflection and support
To address ethical implications and design guidelines
Method
Data Collection
Workshops with Coaches
Design and implementation of LLM chatbot workshops
Feedback and insights from coaching professionals
User Study
Selection of coach-client pairs
Randomized controlled trial with LLM chatbot intervention
Pre- and post-study assessments
Data Preprocessing
Analysis of workshop data
Quantitative and qualitative analysis of user study results
Benefits and Limitations
Advantages
24/7 Availability - Continuous support for self-guidance
Reasoning Capabilities - Facilitating goal-setting and self-disclosure
Support for Self-Reflection - Between-session assistance
Limitations
Contextual Understanding - Human interaction for complex situations
Empathy - Importance of emotional intelligence in coaching
Blended Approach - Combining AI with human coaches for effective collaboration
Ethical Considerations and Guidelines
Design principles for blended coaching systems
Ensuring privacy and data security
Addressing potential biases in AI
Findings and Implications
Reduced coach workload
Fostering self-guidance and growth
Challenges in deep reflection and complex questions
Future Research Directions
Large-scale studies for broader adoption
Expanding to personal growth and well-being domains
Technological advancements in coaching practices
Conclusion
Summary of key insights and implications for the coaching industry
Recommendations for integrating LLM chatbots responsibly
Basic info
papers
human-computer interaction
artificial intelligence
Advanced features
Insights
What limitations are mentioned in the study regarding the use of chatbots in coaching?
What are the key contributions and future directions suggested in the paper?
What is the primary focus of the paper regarding LLM-powered chatbots in executive coaching?
How do chatbots enhance self-reflection and coaching according to the research?

Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth

Riku Arakawa, Hiromu Yakura·May 24, 2024

Summary

This paper investigates the integration of Large Language Model (LLM)-powered chatbots in executive coaching, emphasizing their potential to enhance self-reflection and complement human coaching. Through workshops with coaches and a user study involving coach-client pairs, the research highlights the benefits of chatbots' 24/7 availability, reasoning capabilities, and support for self-guidance between sessions. However, it also identifies limitations, such as the need for human interaction for context understanding and empathy, and the importance of blending AI with human coaches for effective collaboration. Studies show that chatbots can foster self-disclosure, support goal-setting, and reduce human coach workload, but struggle with deep reflection and challenging questions. The research contributes guidelines for designing blended coaching systems, acknowledging the potential for expansion in accessibility while addressing ethical considerations. Future directions include larger-scale studies and the exploration of technology in other personal growth and well-being domains.
Mind map
Pre- and post-study assessments
Randomized controlled trial with LLM chatbot intervention
Selection of coach-client pairs
Feedback and insights from coaching professionals
Design and implementation of LLM chatbot workshops
Blended Approach - Combining AI with human coaches for effective collaboration
Empathy - Importance of emotional intelligence in coaching
Contextual Understanding - Human interaction for complex situations
Support for Self-Reflection - Between-session assistance
Reasoning Capabilities - Facilitating goal-setting and self-disclosure
24/7 Availability - Continuous support for self-guidance
Quantitative and qualitative analysis of user study results
Analysis of workshop data
User Study
Workshops with Coaches
To address ethical implications and design guidelines
To explore their potential for self-reflection and support
To evaluate the impact of chatbots on executive coaching
Current limitations of traditional coaching methods
Emergence of LLMs in coaching industry
Recommendations for integrating LLM chatbots responsibly
Summary of key insights and implications for the coaching industry
Technological advancements in coaching practices
Expanding to personal growth and well-being domains
Large-scale studies for broader adoption
Challenges in deep reflection and complex questions
Fostering self-guidance and growth
Reduced coach workload
Addressing potential biases in AI
Ensuring privacy and data security
Design principles for blended coaching systems
Limitations
Advantages
Data Preprocessing
Data Collection
Objective
Background
Conclusion
Future Research Directions
Findings and Implications
Ethical Considerations and Guidelines
Benefits and Limitations
Method
Introduction
Outline
Introduction
Background
Emergence of LLMs in coaching industry
Current limitations of traditional coaching methods
Objective
To evaluate the impact of chatbots on executive coaching
To explore their potential for self-reflection and support
To address ethical implications and design guidelines
Method
Data Collection
Workshops with Coaches
Design and implementation of LLM chatbot workshops
Feedback and insights from coaching professionals
User Study
Selection of coach-client pairs
Randomized controlled trial with LLM chatbot intervention
Pre- and post-study assessments
Data Preprocessing
Analysis of workshop data
Quantitative and qualitative analysis of user study results
Benefits and Limitations
Advantages
24/7 Availability - Continuous support for self-guidance
Reasoning Capabilities - Facilitating goal-setting and self-disclosure
Support for Self-Reflection - Between-session assistance
Limitations
Contextual Understanding - Human interaction for complex situations
Empathy - Importance of emotional intelligence in coaching
Blended Approach - Combining AI with human coaches for effective collaboration
Ethical Considerations and Guidelines
Design principles for blended coaching systems
Ensuring privacy and data security
Addressing potential biases in AI
Findings and Implications
Reduced coach workload
Fostering self-guidance and growth
Challenges in deep reflection and complex questions
Future Research Directions
Large-scale studies for broader adoption
Expanding to personal growth and well-being domains
Technological advancements in coaching practices
Conclusion
Summary of key insights and implications for the coaching industry
Recommendations for integrating LLM chatbots responsibly

Paper digest

What problem does the paper attempt to solve? Is this a new problem?

The paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" aims to explore the potential of integrating chatbots powered by Large Language Models (LLMs) in collaboration with professional coaches to foster deep introspective reflection and behavior change, particularly in the field of executive coaching . This paper addresses the challenge of utilizing chatbots in coaching contexts that require profound introspection and strategic decision-making, such as leadership development, which is a relatively less explored area in prior research . The research focuses on augmenting self-reflective processes with conversational agents through a human-in-the-loop approach, emphasizing the benefits of chatbots' ubiquity and reasoning capabilities while identifying their limitations and design requirements for effective collaboration with human coaches . The paper's exploration of blending human and chatbot coaches in the context of executive coaching is a novel approach that aims to diversify the ways of leveraging chatbots in coaching practices .


What scientific hypothesis does this paper seek to validate?

This paper aims to validate the hypothesis that blending an LLM-powered chatbot with a human coach effectively supports self-reflection for leadership growth . The study explores the enduring value of human coaches and the benefits of a blended approach, emphasizing the importance of collaboration between human and artificial intelligence in chatbot-based reflection support . The research provides empirical evidence on the performance boundaries of LLM-powered chatbots in fostering deep self-reflection and suggests future directions for human-centered natural language processing and conversation analysis research .


What new ideas, methods, or models does the paper propose? What are the characteristics and advantages compared to previous methods?

The paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" proposes several innovative ideas, methods, and models in the field of coaching and reflective conversational agents . Here are some key points from the paper:

  1. Blended Approach: The paper introduces a blended approach that combines the strengths of human coaches and chatbot coaches to enhance the reflection experience for individuals seeking leadership growth. This approach emphasizes the enduring value of human coaches while leveraging the benefits of chatbot technology .

  2. LLM-Powered Chatbot: The paper explores the potential of an LLM-powered chatbot to facilitate deep reflection for leadership development within the context of executive coaching. This innovative chatbot aims to support self-reflection and growth through a combination of human and AI coaching .

  3. Qualitative Data Analysis: The study conducted in the paper involves qualitative data analysis to understand the effectiveness and value of the blended coaching approach. The findings highlight the importance of combining human and chatbot coaches to achieve optimal reflection outcomes .

  4. Future Research Directions: The paper suggests future research directions, including the need for larger participant pools from diverse coaching organizations to validate the findings further. It also emphasizes the importance of conducting long-term studies to mitigate novelty effects and enhance the understanding of the blended coaching approach .

  5. Ethical Considerations: The paper discusses ethical considerations related to introducing chatbots in coaching settings, such as data privacy, psychological safety, and the risk of bias or discrimination. It emphasizes the importance of clarifying the role of chatbots and ensuring confidentiality, aligning with established standards in executive coaching .

  6. Socio-Technical Tool Development: The paper proposes extending the blended coaching approach to develop a socio-technical tool that can be applied across different domains. This tool aims to leverage the blended coaching model in various contexts beyond leadership growth, offering practitioners a versatile approach to coaching .

Overall, the paper presents a comprehensive framework for integrating human and chatbot coaches to support self-reflection and leadership development, highlighting the potential of blended coaching approaches in the era of advanced AI technologies . The paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" introduces a novel approach that combines the strengths of human coaches and chatbot coaches to enhance self-reflection for leadership development . Here are the characteristics and advantages of this blended approach compared to previous methods:

  1. Blended Approach: The paper emphasizes the enduring value of human coaches while leveraging the benefits of chatbot technology to support self-reflection and leadership growth . This blended approach aims to provide a comprehensive coaching experience by combining the strengths of both human and AI coaches.

  2. Empirical Evidence: The study conducted in the paper involves empirical findings that highlight the benefits of the blended coaching approach, especially in the context of executive coaching . The results confirm the advantages of conversational agents in complementing existing coaching practices for leadership growth.

  3. Client Engagement: The blended initiative of human and chatbot coaches promotes client engagement and self-disclosure . Clients favored the overall experience of text coaching due to the designed approach of blending human and chatbot coaches, maintaining engagement throughout the trial.

  4. Optimal Reflection Experience: The paper synthesizes a way to combine human and chatbot coaches to realize an optimal reflection experience for individuals seeking leadership growth . This approach offers a set of key factors guided by empirical evidence from actual executive coaching sessions.

  5. Future Research Directions: The paper suggests the need for larger participant pools from diverse coaching organizations to further validate the findings and enhance understanding of the blended coaching approach . Conducting long-term studies is also recommended to mitigate novelty effects and provide deeper insights into the effectiveness of the approach.

  6. Ethical Considerations: The paper discusses ethical considerations related to introducing chatbots in coaching settings, emphasizing the importance of data privacy, psychological safety, and avoiding bias or discrimination . It highlights the necessity of clarifying the role of chatbots and ensuring confidentiality in line with established standards in executive coaching.

Overall, the blended approach proposed in the paper offers a unique combination of human expertise and AI technology to support deep self-reflection and leadership development, providing a promising framework for enhancing coaching practices in the context of executive coaching .


Do any related researches exist? Who are the noteworthy researchers on this topic in this field?What is the key to the solution mentioned in the paper?

In the field of chatbot-based coaching and self-reflection for leadership growth, several noteworthy researchers have contributed to related research:

  • Mara Castro Correia, Nuno Rebelo dos Santos, and Jonathan Passmore have provided insights into the Coach-Coachee-Client relationship .
  • Fred D. Davis explored the relationship between perceived usefulness, perceived ease of use, and user acceptance of information technology .
  • Harry Barton Essel, Dimitrios Vlachopoulos, and others studied the impact of a virtual teaching assistant (chatbot) on students' learning in Ghanaian higher education .
  • Liang, Hai Trung Le, and others delved into design opportunities for reflective conversational agents to reduce compulsive smartphone use .

The key to the solution mentioned in the paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" lies in leveraging chatbots to facilitate deep introspective reflection, especially in the context of Large Language Models (LLMs) . This approach aims to augment the potential of conversational agents to support individuals in achieving professional goals, such as leadership growth, by fostering introspective analysis and strategic decision-making .


How were the experiments in the paper designed?

The experiments in the paper were designed as follows:

  • The experimenter explained the use of the chatbot coach to the human coach, who then conducted a session with the client to set goals and plan how to use the chatbot coach .
  • The client filled out questionnaires regarding their behavioral intention and authenticity scale .
  • The human coach conducted a session with the client to reflect on the two weeks of text coaching .
  • Semi-structured interviews were conducted with both the coach and the client individually by the experimenter .
  • The client then conducted text coaching sessions at their own pace with the chatbot coach, and the human coach received a summary of the text coaching and any questions from the client .
  • The study involved metrics to assess the impact on the client, including questionnaire-based measurements filled out by the clients every time they used the prototype to evaluate the outcome of reflection and attitude toward using the system .

What is the dataset used for quantitative evaluation? Is the code open source?

The dataset used for quantitative evaluation in the study is based on questionnaire-based measurements filled out by clients every time they used the prototype . The code used in the study is not explicitly mentioned to be open source in the provided context.


Do the experiments and results in the paper provide good support for the scientific hypotheses that need to be verified? Please analyze.

The experiments and results presented in the paper provide strong support for the scientific hypotheses that needed verification. The study conducted on the blended approach of using an LLM-powered chatbot coach and a human coach for self-reflection in leadership growth revealed valuable insights. The qualitative data from the study highlighted the enduring value of human coaches and the benefits of the blended approach, emphasizing the importance of securing commitment with human coaches . The study also demonstrated that clients' behavioral intention was sustained, and their authenticity scale was affected positively throughout the trial, confirming the benefits of conversational agents in complementing existing coaching practices for leadership development .

Moreover, the study's implications summarized a guideline to support the achievement of professional goals by blending an LLM-powered chatbot coach and a human coach, emphasizing the necessity of collaboration between human and artificial intelligence in chatbot-based reflection support . The findings provided empirical evidence guided by coaches and their clients in actual executive coaching sessions, outlining key factors for effective self-reflection and hinting at future directions for human-centered natural language processing and conversation analysis research .

Overall, the experiments and results in the paper offer a comprehensive analysis of the effectiveness of integrating chatbot coaches with human coaches for self-reflection in leadership growth. The study's outcomes provide valuable insights into the benefits of conversational agents in coaching practices and emphasize the significance of a blended approach for fostering deep self-reflection effectively .


What are the contributions of this paper?

The paper "Coaching Copilot: Blended Form of an LLM-Powered Chatbot and a Human Coach to Effectively Support Self-Reflection for Leadership Growth" makes several significant contributions:

  • It explores the design opportunities for reflective conversational agents to reduce compulsive smartphone use .
  • The paper incorporates a reflective thinking promoting mechanism into AI-supported English writing environments .
  • It examines the effects of coachee readiness and core self-evaluations on leadership coaching outcomes through a controlled trial .
  • The study accompanies reflection processes by an AI-based StudiCoachBot, focusing on rapport building in human-machine coaching using self-disclosure .
  • It examines AI methods for micro-coaching dialogs, providing insights into the use of AI in coaching interactions .
  • The research offers a guideline to support the achievement of professional goals by blending an LLM-powered chatbot coach and a human coach, emphasizing the collaboration between human and artificial intelligence in chatbot-based reflection support .
  • It provides empirical evidence guided by coaches and their clients in actual executive coaching sessions, outlining key factors for the successful integration of LLM-powered chatbots in fostering deep self-reflection .
  • The findings of the paper delineate the current performance boundaries of LLM-powered chatbots in fostering self-reflection and suggest future directions for human-centered natural language processing and conversation analysis research .

What work can be continued in depth?

Further work in this area can focus on conducting a larger user study involving more participants, especially coaches, from different organizations to validate the findings . Additionally, a comparison study with a baseline condition could be beneficial to provide additional evidence on the effectiveness of the blended approach . Long-term studies could also be conducted to reduce the possibility of novelty effects and assess sustained impact . Ethical considerations, such as data privacy, psychological safety, and monitoring for bias or discrimination in chatbots, should be further discussed to advance the deployment of chatbots in coaching .

Scan the QR code to ask more questions about the paper
© 2025 Powerdrill. All rights reserved.