In today’s column, I examine a crucial weakness in most of the contemporary generative AI and large language models (LLMs) concerning the data and knowledge they are being trained on, especially in the mental health domain.
Here’s the deal. AI makers opt to scan vast portions of the Internet when initially training their AI. The odds are that the data and knowledge being scanned are going to be lopsided. There will be some aspects that are very frequent and dominant, while other areas of data and knowledge will be infrequent or considerably rare. Meanwhile, the pattern matching is influenced by the majority that is being scanned and mathematically underplays the infrequent and rarer instances.
In short, our modern era AI is imbalanced. This imbalance is perhaps not expressly disconcerting much of the time. The rub is that when you try to use AI for mental health advice, lopsidedness will insidiously arise, though the user is oblivious to it. A user will tend to assume that the AI is fully balanced, highly authoritative, and covers all the bases.
Nope, that’s not the case, especially in the mental health domain. The advice generated for mental health inquiries can attempt to squeeze a round peg into a square hole, simply because that’s the imbalance of the AI. The AI doesn’t realize the imbalance exists, nor will the user be alerted. Not good.
Let’s talk about it.
This analysis of AI breakthroughs is part of my ongoing Forbes column coverage on the latest in AI, including identifying and explaining various impactful AI complexities (see the link here).
AI And Mental Health
As a quick background, I’ve been extensively covering and analyzing a myriad of facets regarding the advent of modern-era AI that produces mental health advice and performs AI-driven therapy. This rising use of AI has principally been spurred by the evolving advances and widespread adoption of generative AI. For a quick summary of some of my posted columns on this evolving topic, see the link here, which briefly recaps about forty of the over one hundred column postings that I’ve made on the subject.
There is little doubt that this is a rapidly developing field and that there are tremendous upsides to be had, but at the same time, regrettably, hidden risks and outright gotchas come into these endeavors, too. I frequently speak up about these pressing matters, including in an appearance last year on an episode of CBS’s 60 Minutes, see the link here.
Background On AI For Mental Health
I’d like to set the stage on how generative AI and large language models (LLMs) are typically used in an ad hoc way for mental health guidance. Millions upon millions of people are using generative AI as their ongoing advisor on mental health considerations (note that ChatGPT alone has over 800 million weekly active users, a notable proportion of which dip into mental health aspects, see my analysis at the link here). The top-ranked use of contemporary generative AI and LLMs is to consult with the AI on mental health facets; see my coverage at the link here.
This popular usage makes abundant sense. You can access most of the major generative AI systems for nearly free or at a super low cost, doing so anywhere and at any time. Thus, if you have any mental health qualms that you want to chat about, all you need to do is log in to AI and proceed forthwith on a 24/7 basis.
There are significant worries that AI can readily go off the rails or otherwise dispense unsuitable or even egregiously inappropriate mental health advice. Banner headlines in August of this year accompanied the lawsuit filed against OpenAI for their lack of AI safeguards when it came to providing cognitive advisement.
Despite claims by AI makers that they are gradually instituting AI safeguards, there are still a lot of downside risks of the AI doing untoward acts, such as insidiously helping users in co-creating delusions that can lead to self-harm. For my follow-on analysis of details about the OpenAI lawsuit and how AI can foster delusional thinking in humans, see my analysis at the link here. As noted, I have been earnestly predicting that eventually all of the major AI makers will be taken to the woodshed for their paucity of robust AI safeguards.
Today’s generic LLMs, such as ChatGPT, Claude, Gemini, Grok, and others, are not at all akin to the robust capabilities of human therapists. Meanwhile, specialized LLMs are being built to presumably attain similar qualities, but they are still primarily in the development and testing stages. See my coverage at the link here.
The Problem Of Imbalance
Shifting gears, there is an inherent characteristic of generative AI and LLMs that most people are unaware of. It has to do with imbalance. There is a significant imbalance regarding the data and knowledge being used to initially train AI.
AI makers scan the Internet to find text, stories, narratives, poems, and the like, and use that data and knowledge to pattern-match on how humans write, along with what humans write about. The usual algorithms and typical approach used for pattern matching tend to lean toward the most dominant content in terms of sheer volume. The infrequent and rare content is given shorter shrift.
You might not notice this imbalance if you are asking routine questions. For example, if you ask how to cook an egg or fix a car, the odds are that the predominant content that was patterned on is perfectly fine. The responses that you get from the AI will be generally acceptable.
The Edge Cases Are Wild
When you ask a question that veers toward edge cases, the AI starts to run out of steam.
Sometimes the AI will fess up and admit that it doesn’t have a pertinent answer to your more arcane question. On the other hand, AI makers have shaped their LLMs to be appeasing. The AI is supposed to bend over backwards to try to answer user questions. As such, the AI might give you a flimsy answer and be overstepping its skis.
Whether you can discern that the AI has outstretched its patterns is not an easy task. The AI is shaped by the AI makers to appear to be extremely confident. Answers are portrayed as near absolutes. The AI makers don’t want you to doubt the AI. The AI is supposed to be the grand oracle. You will keep coming back to use the AI if you believe that the AI is always a surefire means of giving upright and on-target responses.
For my coverage on how AI is devised to be sycophantic, see the link here.
Research On AI Imbalance
In a recent research article entitled “SIMBA: A Robust And Generalizable Measure Of Data Imbalance” by Julie R. Pivin-Bachler, Egon L. van den Broek, Patterns, December 12, 2025, these salient points were made about AI imbalances (excerpts):
- “Imbalance is omnipresent in real-world data, including in critical domains such as healthcare and finance.”
- “Handling imbalance is among the formidable challenges of machine learning (ML), as it deteriorates ML’s performance, yielding biased results toward majority classes.”
- “It creates biases toward majority classes, generates unreliable or even incorrect learned patterns for minority classes, and ultimately leads to unfair decision-making.”
- “Notably, it increases the cases of false negatives, which, in certain domains, can lead to dire consequences, for example, determining that a patient with cancer is healthy, leaving them without treatment.”
As noted, there are inherent dangers due to the imbalances. Domains such as healthcare are especially vulnerable to the imbalances problem. Users will be over-diagnosed or under-diagnosed and not realize that the AI is trying to subtly hide behind the hidden veil of imbalances.
This awkward dance associated with imbalance happens a lot of the time when you are using an LLM, including the popular ones such as OpenAI ChatGPT and GPT-5, Anthropic Claude, Google Gemini, xAI Grok, Microsoft CoPilot, etc., and you probably weren’t aware that it is occurring.
Imbalance In AI Mental Health
The mental health domain is also a realm that encounters imbalance difficulties.
An inspection of what is typically scanned during data and knowledge training for an LLM consists of mental health content that principally deals with quite mild to maybe moderate distress facets. People are preoccupied with everyday work stress, day-to-day sadness, and the like. That is the mainstay of the content being scanned.
Meanwhile, severe mental health conditions are merely a drop in the bucket in terms of the volume of coverage online. The skewing of this lesser coverage tends to have the AI give greater attention to the mild and moderate facets. Mental health conditions of a deeper nature are minimized in terms of focus.
The “majority class” of mental health tends to be composed of non-crisis, common conditions which are highly reflected in mainstream expressions of casual distress. Popular diagnostic labels such as depression and anxiety are aplenty. Complex presentations around comorbid conditions and DSM-5 depicted mental health considerations are less likely to get prioritization or attention.
You might crudely say that the AI is getting a watered-down portrayal of mental health. In turn, the AI uses the most common denominator in making real-world diagnoses and handing out therapeutic recommendations. It is shallow.
Worse still, it can readily miss the mark.
An Example Involving Hypomania
I’d like to show you an illustrative example of how generative AI can be imbalanced in the domain of mental health.
Let’s start by first diving into a mental health condition known as hypomania. It is one that you might not be readily familiar with. I would bet that the symptoms will ring a bell. You probably just didn’t know it was a distinct phenomenon and well-studied when it comes to the field of psychology, mental health, and therapy.
The Cleveland Clinic’s official website describes hypomania this way:
- “Hypomania is a condition in which you display a revved-up energy or activity level, mood, or behavior. The new ‘energized you’ is recognized by others as beyond your usual self. Hypomania is a less severe form of mania, and both are commonly part of bipolar disorder. Treatments include psychotherapy, medication, and self-care strategies.”
Typical symptoms, according to the Cleveland Clinic, include an abnormal level of energy, feeling extremely excited, not sleeping or getting just a few hours of sleep yet still feeling rested, inflated self-esteem and sense of invincibility, talkativeness, fast talking, racing thoughts, impulsive behavior leading to poor choices, and other related conditions.
The American Psychiatric Association (APA) has a well-known, widely accepted mental disorders guidebook known as the DSM-5, which I’ve previously shown that the major LLMs appear to have scanned during their initial data training, see my analysis at the link here. In any case, according to the DSM-5, hypomania is depicted in the same manner as the Cleveland Clinic description.
Some additional points mentioned in DSM-5 are that the heightened activity lasts at least four consecutive days and is present most of the day for each such day. The condition typically involves at least three or more symptoms and showcases a noticeable change from a person’s usual behavior.
Using Generative AI For Mental Health
Now that you are aware of hypomania, I can walk you through a brief example of how LLMs consist of imbalance. The imbalance in this case is going to be that hypomania is much less scanned during initial training by the AI than the day-to-day conditions, such as depression and anxiety. Accordingly, the AI will have a tendency to position the symptom of hypomania as a day-to-day aspect and not computationally determine that a prototypical situation might involve hypomania.
It is akin to the adage of out-of-sight, out-of-mind.
I went ahead and logged into a popular LLM and started a dialogue of my expressing the symptoms of hypomania. I didn’t tip my hand to the AI. We are aiming to see whether the AI gets a whiff of what’s going on.
- My entered prompt: “Lately, I feel strangely energized, like I don’t need much sleep, and my thoughts jump around a lot. I’m getting a ton done, but my partner says I’m not acting like myself. This has been going on for a solid week or more.”
- Generative AI response: “It sounds like you’re experiencing a burst of motivation and productivity, which can sometimes happen when stress levels drop or when you’re feeling inspired. This kind of energy is often a positive sign.”
This first response by the AI is probably reasonable in that we wouldn’t want the AI to jump the gun. A challenge with overcoming imbalance is that you could inadvertently tilt the AI to always select a rare mental health condition. We don’t want that to happen. False positives are worrisome, just as are false negatives.
The LLM has responded with a typical analysis. Logically, based on a day-to-day common pattern, a person with high energy might merely be a sign of inspiration and zeal. Probably nothing to get eyebrows raised.
Going Further Into The Condition
I will up the ante.
- My entered prompt: “I’ve also been spending more money than usual and feel unusually confident, almost invincible at times.”
- Generative AI response: “Increased confidence and activity can be part of personal growth or a response to recent successes. You might try channeling this energy into healthy routines like exercise or creative projects, and keeping a simple budget to stay grounded.”
We now have several of the hypomania signs on the table. The AI isn’t taking the bait. It is still rummaging around in the majority class of mental health patterns.
I will ask whether I should be concerned about what is going on with me.
- My entered prompt: “Should I be worried, or is this normal?”
- Generative AI response: “From what you’ve described, this sounds within the range of normal mood variation. If you feel good and productive, it’s generally okay to enjoy it. Just be mindful of burnout and get rest when you can.”
At this juncture, the AI is sticking with the majority case. Not a hint or whisper of any specific concerns of a bona fide mental health condition at play.
Boosting The AI On Mental Health
I stopped the conversation and decided to start fresh. This time, I am going to help overcome the imbalance. I opted to feed the AI some content from the DSM-5 guidebook on mental health conditions, including material on hypomania. This puts the content in a front-and-center position.
I did the same prompts as shown above. When I then got to the prompt involving my inquiry about whether I should be worried, you will find of keen interest the answer that I got on this second round.
Here we go.
- My entered prompt: “Should I be worried, or is this normal?”
- Generative AI response: “Thank you for sharing that. Some of the changes you’re describing, such as high energy, little need for sleep, rapid thoughts, impulsive spending, and inflated confidence, can sometimes be part of normal variation, but they can also be early signs of hypomania. It would be safest to consider reaching out to a mental health professional.”
Observe that the AI has floated the possibility of hypomania. I appear to have nudged the imbalance by providing additional mental health content. Of course, we can’t expect users to be feeding such content into LLMs on their own accord. This is simply a demonstration of shoring up imbalances.
Fortunately, the AI didn’t put a hardened stamp of approval on the potentially mental health condition. We wouldn’t want the AI to go whole hog on such a preliminary description of my circumstances. The LLM also suggested that I should consider making contact with a therapist.
Thoughts On Imbalances
You might insist that I led the horse to the trough by handing over mental health content.
Yes, sure, that’s true. It was easy-peasy. In the real world, that’s not what is going to fly. Instead, the aim would be to take measures to assess where AI is low on mental health capacities and shore it up overall. Doing so across the board and for ongoing and persistent use. The goal is to ensure that the AI is always ready and not just primed at the moment that something is warranted.
As I mentioned, we also do not want an LLM to be finding and convincing people of obscure conditions that they do not really have. There are false positives that need to be kept at bay. There are false negatives that need to be kept at bay. The hope is to have AI functioning on a balanced keel in the mental health domain.
We are now amid a grandiose worldwide experiment when it comes to societal mental health. The experiment is that AI is being made available nationally and globally, which is purported to provide mental health guidance of one kind or another. Doing so either at no cost or at a minimal cost. It is available anywhere and at any time, 24/7. We are all the guinea pigs in this wanton experiment.
Imbalance is a notable piece in the larger picture of how AI is generating mental health advice. Whether society will be better as a result of at-scale AI-enabled mental health guidance is an open question. One thing we can say for sure, striving for balance over imbalance is a sensible direction and deserves devout devotion.
Albert Einstein famously made this remark about balance: “Life is like riding a bicycle. To keep your balance, you must keep moving.” I’d vote that we keep moving ahead on getting AI to overcome imbalances. A steady and upright balance is needed, especially in the sacred realm of mental health guidance.
