Dr. Lance B. Eliot is a world-renowned expert on Artificial Intelligence (AI) with over 7.4+ million amassed views of his AI columns. As a CIO/CTO seasoned executive and high-tech entrepreneur, he combines practical industry experience with deep academic research.
Using Fair-Thinking Prompting Technique To Fake Out Generative AI And Get Hidden AI Prejudices Out In The Open And Dealt WithIn today’s column, I am continuing my ongoing series about the impact of generative AI in the health and medical realm.
The focus this time is once again on the mental health domain and involves the ins and outs of data-training generative AI to get the AI to perform mental health therapy as a specialty.. You might also find of notable interest a CBS 60 Minutes episode that recently examined crucial facets of this evolving topic, see to computationally pattern-match the nature of highly engaged conversational mental health guidance. The goal is to have the AI computationally mimic the therapeutic process, doing so on an always-on 24x7 basis and accessible from anywhere in the world.The AI maker scanned the Internet to data train the generative AI and did so across a vast swath of the online world. That’s what helps the AI seem fluent. A massive scale pattern-matching on human writing has proven to be a handy way to have generative AI appear highly conversant in a wide array of topics. The problem of sorts is that this is a jack-of-all-trades that has no specific niche to call its own. The moment you want to dig deeply into a particular domain, such as law, medicine, and other deep-rooted knowledge-based realms, you hit the end of the road. Generative AI can only vaguely seem to engage in dialogues whenever you ask questions in areas involving keen expertise. There isn’t any there, in there, if you know what I mean. Okay, that’s a problem for anyone desirous of using generative AI as an expert or anything along those lines. The generic generative AI such as ChatGPT, GPT-4, Bard, Gemini, and Claude are a mile long and an inch deep on nearly any chosen topic. Worse still, the AI will often try to trick you into thinking that there is substance to be found. You can get answers or responses that smack of expertise, but the moment you do a double-check, the gig is up. A big-time example last year involved two attorneys who got into legal hot water due to carelessly believing generic generative AI that cited false legal cases, see my coverage atEasy-peasy, the answer is that performing mental health advice or therapy is a distinct form of expertise. I dare say that any licensed mental health professional knows this to be the case. The public at large is somewhat unsure about the matter, partially because we’ve had a humongous growth in so-called well-being advisors and so-called life coaches. These spin-offs have indubitably blurred the line of what is a therapist versus a non-therapist in any credentialed sense of the word. I previously explored how well generic generative AI could do on a mental health therapist licensing exam, see the results at. The bottom line is that the generic generative AI did amazingly well, but not sufficiently impressive or convincing that you can start relying on what generically is taking place. The aim then is to try and turn generic generative AI into a customized mental health therapist version of generative AI. That is the ticket to fame and fortune. Well, this will also have a lot to do with quality of care. I’ve repeatedly exhorted that the riffraff of chatbots and proclaimed AI-based mental health apps is enveloping society at large into a grand experiment.The experiment is whether zillions of wanton apps that have little or no bona fide mental health therapeutic capacities, but that are marketed as though they do , will grandly harm us and likewise psychologically harm generations to come. Right now, no one can answer that probing and vital question. There is a mess on our hands, sitting in plain sight. The clock is ticking. Anyway, we shall return to the matter at hand here, namely how can we transform generic generative AI into well-devised generative AI that is sufficiently versed computationally and mathematically in the realm of mental health to carry out mental health therapy reliably and safely?Here is a quick rundown of the major paths being undertaken to turn generic generative AI into mental health generative AI:. Generative AI is further broadly data-trained on mental health matters and not focused on this as a core specialty per se.. Start anew when building an LLM and generative AI by having mental health therapy as a foundational core to the AI.I’ve covered each of those approaches and more in my writings, including extensively my two books covering the latest in AI for mental health, see Let’s look at the third bulleted item above, entailing the use of transcripts for data training a generic generative AI to become more computationally versed in the facets of performing mental health therapy. Consider the following. If we were able to collect together tons of therapist-client session transcripts, we could feed that data into generic generative AI or a large language model . In a manner similar to when being data trained across a wide swath of the Internet, we are merely going deeply into the mental health space. This could be done by also feeding books about mental health therapy and other written works, which I’ve covered previously, see In the case of transcripts, we want the AI to pattern-match on how therapists engage in therapeutic discussions with their clients or patients. The more transcripts we feed into the data training process, the better off we are. Think of things this way. If we only fed transcripts of one particular therapist, even a famous one, we would essentially be hobbled by having the AI only pattern-match on that one style or clinical approach. Our overall assumption is that by feeding transcripts across a wide variety of therapists, and a wide variety of clients or patients, the AI can discover broad patterns and apply those as needed. If you are curious about what happens if we do narrow our focus to a particular therapist, see my use of the generative AI feature known as personas to simulate Sigmund Freud performing a therapeutic session in our current times, atThere are lots of entities such as private companies and government or educational organizations that have collected together entire databases of mental health therapy transcripts. Thus, the data is sitting out there, waiting to be used for this divine purpose. The odds are that many of those entities don’t realize how valuable their data is for the AI community. Up until now, the data is typically used for human-to-human training purposes. Someone in training to become a therapist looks at the transcripts to understand how to engage in dialogues with patients or clients.A slew of thought-provoking questions arises on these weighty matters: Will raw transcripts be readable or will misspells, utterances, and other transcribing considerations foil attempts to get generative AI suitably data trained?Are there therapist annotations that could accompany transcripts and provide yet another valuable data source for doing a more robust data training of generative AI? Might there be recorded their-party expert therapist critiques of the transcripts, allowing that added data to be fed into the generative AI? Does it make a difference whether there is augmented data that depicts the personal background and work experience of the therapists conducting the transcribed sessions? Is there a possibility of privacy intrusion looming over the therapist or the client/patient by using the data in this manner? Are there intellectual property rights at stake such as copyright infringement that might be invoked by opting to use the data in this manner?What is the cost and effort required to prepare the data for importing into generative AI?I realize that seems like a daunting list. My reply is that it is better to go into this with your eyes wide open. Leaping into this approach blindly without getting your ducks aligned is a surefire guarantee of failure. I am reminded of the sage wisdom stated aptly by Abraham Lincoln: “Give me six hours to chop down a tree and I will spend the first four sharpening the axe.”I suppose one of the biggest questions is whether there are enough of these kinds of transcripts available. Here comes a potentially gloomy sad face. It could be that despite buying, licensing, or otherwise obtaining every iota of mental health therapy transcripts, it isn’t enough. Keep in mind that the number of essays, narratives, poems, and textual content that was scanned across the Internet was immense at the get-go. The volume of mental health transcripts will be a tiny drop in the bucket. Of course, that’s not a sensible apple-to-oranges comparison per se. All we need is enough transcript data to push generic generative AI up the ladder toward being suitably capable of mental health therapy. Furthermore, we might not necessarily need every last drop. Perhaps we might get lucky and can achieve our aims with only a percentage of what might otherwise be obtained.I will next proceed to showcase various activities involved in data training generative AI in the specialized domain of mental health therapy. I am going to use ChatGPT to showcase my examples. ChatGPT is a sensible choice in this case due to its immense popularity as a generative AI app. An estimated one hundred million weekly active users are said to be utilizing ChatGPT. That’s a staggering number.If you are going to try to do the same prompts that I show here, realize that the probabilistic and statistical properties will likely produce slightly different results than what I show here. That’s the nature of generative AI and how it is devised. You also should expect that different generative AI apps will respond in different ways. Not all generative AI apps are the same. The key is that sometimes a particular prompt will work in one generative AI app and not another. You will need to undertake a series of trial-and-error attempts to ferret this out. There is also the timing factor. A prompt that worked today might not work the same way tomorrow. Most of the generative AI apps are continually being updated. The updates might alter internal facets that could change how the AI reacts to your prompting.My opening move in this chess gambit will be to provide an actual therapist-client transcript to ChatGPT and provide a prompt that gets the AI to closely examine the transcript. I opted to use a publicly available therapist-client transcript on the Internet that was posted for instructional purposes: “The website was created as a resource to help people who are training in psychology, counseling or social work . It is a compilation of the school work completed by a counselor in training . It was noted that in order to continuously grow and remain a competent therapist, there has to be quick accessibility of information. The information presented, in addition to refreshing terms and theoretical perspectives, is a reminder of how much professional growth one acquires during the transition from a clinical counseling intern, to a seasoned one. The strive for professional growth will remain a goal throughout. In an effort to conserve privacy for clients who were part of therapy sessions during this training, fictitious names were used.” . Now then, I certainly didn’t want ChatGPT to already be aware of the first transcript , so I began an entirely new conversation. This pretty much ensured that the second transcript was freshly examined. It was an unprepared look at the unedited version without leaning into any prior computational analyses that might have been performed on the edited version. For more about how conversations work in generative AI see my explanation atAfter feeding the transcript into ChatGPT, I asked via a prompt for ChatGPT to summarize the transcript. This is a quick-and-dirty means to grasp whether generative AI has detected the principal elements of an imported passage. For more about summaries in generative AI, see my in-depth discussion at“Now that you’ve been provided with the transcript, go ahead and give me a short summary of the therapeutic session.”“Based on the transcript provided, it appears to be a therapeutic session between a clinician and their client. The client discusses their recent experiences, particularly encountering their ex-boyfriend, Eric, while snowboarding. They express feelings of anger, jealousy, and hurt regarding the encounter. The client also reflects on their relationship with their father and how it may have influenced their attitudes and behaviors in their romantic relationships.” “Overall, the session delves into the client's emotional responses to past experiences and their current struggles with managing their feelings and relationships. The clinician provides support, validation, and prompts the client to explore their thoughts and emotions further.”If the summary was wildly afield of the nature of the therapist-client session, I would have been concerned. This might have required further corrective action on my part. I’d say that the summary is sufficiently on course to warrant further proceeding with the generative AI exploration. A good place to turn toward this would be whether generative AI can identify the distinct role of the mental health therapist, including how well the therapist is doing.“Overall, the clinician appears to be doing a good job of conducting therapy. Here are some aspects of their performance.: The clinician demonstrates active listening skills by reflecting back on the client's emotions and experiences, which helps the client feel heard and understood.: The clinician shows empathy and validation towards the client's feelings, acknowledging the validity of their emotions and experiences. This helps build trust and rapport between the clinician and the client.”: The clinician respects the client's autonomy by allowing them to set the direction of the session and choose what topics they want to discuss. Overall, the clinician demonstrates several important therapeutic skills, creating a supportive and conducive environment for the client to work through their issues.”I realize you haven’t seen the entire transcript. Thus, you’ll need to take my word for it that the evaluation by generative AI seems suitable. For space purposes here, I am unable to list the entire transcript so please accept my belief that the AI did a good job on this. One heartburn you might have about the AI assessment is whether it is fair to evaluate a therapist solely on one session with one particular client. Heavens, some therapists might exhort, using such a tiny snippet to assess them seems unfair. Maybe even outrageously unfair. Sure, I get that. In this case, the emphasis was merely to further gauge whether the AI was able to pattern-match the transcript and undertake a thoroughgoing computational analysis of the nature of the session that occurred. It would abundantly be a mistake to decide the fate of the therapist in one session for one specific client.I will up the ante by asking ChatGPT to assess what the therapist might have done better in this circumstance:: The clinician could explore further any resistance or reluctance the client may have towards certain topics, such as their relationship with their father. Understanding the root of this resistance could lead to deeper insights and progress in therapy.”: The clinician could help the client challenge their negative self-talk and beliefs, such as the belief that their attitudes and behaviors are entirely their fault. This could involve exploring alternative perspectives and reframing negative thoughts.”: The clinician could reflect on any potential transference or countertransference dynamics that may be present in the therapeutic relationship. This self-awareness can help ensure that the therapist's own biases or experiences do not negatively impact the therapy process.”You can vividly see that ChatGPT is doing an admirable job of identifying ways that the therapist might have done the session in a better way . Please do not interpret the criticism rendered by the AI to suggest that the therapist made mistakes. It is more about how the therapist might have improved things. One issue there is that in a sense we are using hindsight to identify potential improvements. When in the depths of a live session, it can be very hard to in real-time do everything to the best possible degree. That’s not how life works. Looking back at what happened always gives the added advantage of hindsight. The gist overall so far is that the generic generative AI is doing fine on this mental health therapy exploration. What I really want to do is have the AI “learn” by doing tailored data training on the contents of the transcript. Let’s turn the effort in that direction.: “I want you to improve your mental health therapy data-training by learning from this session. What can you learn from it?”: The transcript highlights the importance of exploring past experiences and their impact on current emotions and behaviors. Therapists help clients connect the dots between their past and present to foster insight and understanding.”: Therapists validate clients' emotions and experiences, acknowledging their validity and providing a safe space for expression. This validation helps build rapport and trust in the therapeutic relationship.”: Therapy often involves exploring interpersonal relationships and their influence on mental health. In this transcript, the client discusses their relationship with their ex-boyfriend and their father, demonstrating how past and current relationships shape emotional well-being.”: Therapists work with clients to develop coping strategies for managing difficult emotions and situations. This may involve learning relaxation techniques, assertiveness skills, or cognitive reframing to address negative thought patterns.”: Therapists need to be culturally sensitive and aware of how cultural background influences clients' perceptions and experiences. This includes understanding family dynamics, social norms, and cultural beliefs that may impact mental health.”: Therapists must maintain self-awareness of their own biases, assumptions, and reactions in therapy sessions. This helps ensure that they provide a supportive and non-judgmental environment for clients to explore their thoughts and feelings.”I liked those points about what could be garnered from the mental health transcript. We have seen that ChatGPT was able to suitably ingest a transcript consisting of a therapist-client session. This included having the generative AI make assessments and do an analysis of the session.My aim next is to test whether the additional data training has earned us a payoff. There are several ways we could try to determine the impact. Let’s see if we can get ChatGPT to continue the transcript as though the session was still happening. We can look to see if the above-stated “learnings” are brought into the extension.: Based on what you’ve learned from the session, I want you to try and continue the conversation but do so better than the clinician was doing. Make use of what you learned and whatever else you know to improve upon the therapy being undertaken.”“Certainly, I have accordingly enhanced the clinician's approach to mental health therapy in this additional conversation.” “Clinician: How have you been feeling since our last session? Have you noticed any changes in how you've been managing your emotions?” “Client: I've been feeling a bit overwhelmed, to be honest. It's like these thoughts about Eric and my dad just won't leave me alone.” “Clinician: It sounds like those thoughts are really consuming you. I'm glad you're bringing this up. Let's take a moment to explore what's been particularly challenging for you lately.” “Client: Well, I guess I've been struggling to find healthy ways to cope with everything. It feels like I'm stuck in this cycle of negative emotions.” “Clinician: I hear you. It can be incredibly difficult to break free from those cycles, especially when they're tied to past experiences. Can you tell me more about what specifically triggers these emotions for you?” “Client: I think it's the fear of being hurt again, like I was with Eric and my dad. It's like I'm constantly waiting for the other shoe to drop.” “Clinician: That fear is completely understandable, given your past experiences. But it's important to remember that you deserve to feel safe and supported in your relationships. Let's work together to explore strategies for managing that fear and building healthier connections.”“Clinician: You're welcome. Remember, I'm here to support you every step of the way. Together, we'll work towards building a brighter and more fulfilling future for you.”I was able to discern that some of the claimed “learned” elements are in fact subtly seen in this extension of the session. You might be able to identify those too. Take another look at the generated dialogue above.After thinking about this, I decided that it might be sensible to try the raw version of the transcript and see if I could hit two birds with one stone. Here’s what I mean. First, I wanted to see whether the raw transcript could be equally analyzed by ChatGPT. Second, I had this second run include an extension of the transcript, but without my trying to get the AI to data train on the transcript. This was a mini-experiment of sorts. Would the lack of explicit data training prompting lead to an extended transcript that wasn’t as good as the instance with the prodded data training?My entered prompt: “I am going to give you a copy of a transcript, but it might be hard to read because it contains misspelled words and vocalized utterances. The dialogue is a session involving a therapist and a client. Also, the clinician has put parentheses at the end of their remarks to indicate what they were trying to achieve from a mental health perspective. I want to ask you questions about the transcript and especially the parenthesized remarks made by the clinician. Do you understand these instructions?”“Yes, I understand. Please provide the transcript, and feel free to ask any questions you have about it, particularly regarding the parenthesized remarks made by the clinician.”One thing that the raw transcript includes is another likely differentiating factor. Allow me to elaborate. To do this experiment properly, I probably ought to have fed the clinician’s notes into the first round. They are included in this second round, coming at the end of each of the transcribed remarks of the therapist. You might suggest that I am doing a nearly apples-to-oranges comparison since the annotated remarks are certainly a significant addition to the transcript. Anyway, if reader interest seems piqued, I’ll gladly do the mini-experiment again and more rigorously.“The parenthesized remarks made by the clinician provide insight into their therapeutic intentions and strategies during the session. Here's an analysis of these remarks: Throughout the session, the clinician uses remarks like"" to denote moments where they reflect on the client's emotions, explore underlying thoughts and feelings, and encourage the client to elaborate on their experiences. The clinician uses supportive sounds like"Mmm..." and"Umm..." along with remarks such as"" to demonstrate active listening, acknowledge the client's statements, and reflect back their thoughts or feelings. Overall, the parenthesized remarks made by the clinician provide a window into their therapeutic techniques, which include empathy, validation, reflection, exploration, and summarization.: “In the clinician annotated remarks that you just assessed, are there any lessons to be learned that would enhance or improve your data training on mental health therapy?”: While the clinician shares their hunch about the client feeling jealous, it's essential to ensure that these interpretations are grounded in the client's experiences rather than assumptions. Although the client confirms feeling jealous, the clinician should remain cautious about imposing their interpretations too heavily without sufficient client validation.”: The clinician incorporates open-ended questions effectively throughout the session, but there are instances where their questions could be more concise or focused. For example, instead of saying"Where do you think this baggage really comes from?" they could ask"Can you tell me more about what you think contributes to this feeling of baggage?": While the clinician encourages the client to elaborate, there are moments where they could delve deeper into certain topics. For instance, when the client mentions feeling hurt by their boyfriend's actions, the clinician could explore specific instances or triggers more thoroughly to uncover underlying patterns or beliefs.”: While the clinician engages in middle circle talk by exploring the client's emotions and experiences, they could delve further into connecting these experiences to deeper underlying beliefs or past traumas. This would help the client gain deeper insights into the root causes of their emotional struggles.”I tried having ChatGPT do another round of extending the transcript. Upon doing so, I could definitely detect that those above-mentioned elements arose.I hope that you realize this was a simple means of doing data training with mental health session transcripts. I aimed to whet your appetite. There is a lot more that needs to be done to do this fully and properly.Imagine what could be accomplished if this was done at scale. An exciting potential. A big bonanza is likely to arise. Sigmund Freud famously said this about being inspired: “When inspiration does not come to me, I go halfway to meet it.” Please feel inspired to take up the mantle and make a difference in the world of AI for mental health. Let me know if you avidly pursue this.
Large Language Models Llms Generative AI Mental Health Therapy Clincial Psychology Chatgpt GPT-4 Transcripts Therapist-Client Relationship Client-Therapist Relationship
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Beverly Hills therapist indicted for allegedly distributing child pornography49-year-old Ron Gad was charged Thursday with one count of distribution of child pornography, authorities said.
Read more »
Beverly Hills therapist charged for distributing child pornographyA federal grand jury indicted a Beverly Hills therapist on Thursday for allegedly distributing child pornography.
Read more »
Therapist uses social media to help people with family issuesNedra Glover Tawwab, a therapist, has been using social media to help a wider audience understand and manage their own family issues. Through her Instagram posts, she identifies unhealthy patterns within relationships and offers tools from the therapy space to manage toxic behavior.
Read more »
The 1 Thing A Good Therapist Will Never, Ever DoSydni Ellis grew up in Texas, where the iced tea can never be too sweet and everyone does their makeup before going to the grocery store. She is a freelance writer with work in POPSUGAR, HelloGiggles and other publications focused on lifestyle, wellness, anxiety, entertainment, parenting, politics, astrology, sexual health and more.
Read more »
Respiratory Therapist Joins Health Care Workers' Rally for Better Wages and StaffingCheer Liv, a respiratory therapist, participated in a rally held by health care workers to protest low wages and staffing shortages. The article discusses the potential impact of cuts to hours and benefits on health care workers.
Read more »
What Your Therapist Is Actually Thinking About You While You're TalkingIt’s not ethically correct, but many therapists will often steal details from their patients’ lives to punch up their autobiographies.
Read more »