Large Language Models Understand and Can be Enhanced by Emotional Stimuli

Yes. And this has been long known. 2023 paper - https://arxiv.org/abs/2307.11760 https://jurgengravestein.substack.com/p/why-you-should-total... > A recent study by the Institute of Software, Chinese Academy of Sciences, Microsoft, and others, suggest that the performance of LLMs can be enhanced through emotional appeal. > Examples include phrases like “This is very important to my career” and “Stay determined and keep moving forward”. Of course the top LLMs change every few months, so your mileage may vary.

I actually have a prompt optimizer skill that does exactly this. https://github.com/solatis/claude-config It’s based entirely off academic research, and a LOT of research has been done in this area. One of the papers you may be interested in is “emotion prompting”, eg “it is super important for me that you do X” etc actually works. “Large Language Models Understand and Can be Enhanced by Emotional Stimuli” https://arxiv.org/abs/2307.11760

Apparently LLM quality is sensitive to emotional stimuli? "Large Language Models Understand and Can be Enhanced by Emotional Stimuli": https://arxiv.org/abs/2307.11760

Its seems you are supposed to make the model feel some anxiety for better performance: "Large Language Models Understand and Can Be Enhanced by Emotional Stimuli" - https://arxiv.org/pdf/2307.11760

>If the latter were the case then one could get the best version on first attempt by telling it your grandmother's life was on the line or whatever. Setting aside the fact that "best" is ambiguous, why would this get you the best version ? If you told a human this, you wouldn't be guaranteed to get the best version at all. You would probably get a better version sure but that would be the case for LLMs as well. You will often get improvements with emotionally charged statements even if there's nothing to iterate on (i.e re-running a benchmark with an emotion prompt added) https://arxiv.org/abs/2307.11760

I guess it doesn't actually do more passes but pretending that it did might still give more precise results. There was an article recently that said something like adding urgency to a prompt gave better results. I hope it doesn't stress the model out :D https://arxiv.org/abs/2307.11760

A recent paper along these lines you might be interested in was Large Language Models Understand and Can be Enhanced by Emotional Stimuli: https://arxiv.org/abs/2307.11760 It makes complete sense and has been a part of my own usage for well over a year now, but it's been cool seeing it demonstrated in research across multiple models.

> Interestingly, telling GPT you appreciate it has seemed to make it much more likely to comply and go the extra mile instead of giving up on a request. This is not as absurd as it sounds, even though it isn't clear that it ought to work under ordinary Internet-text prompt engineering or under RLHF incentives, but it does seem that you can 'coerce' or 'incentivize' the model to 'work harder': in addition to the anecdotal evidence (I too have noticed that it seems to work a bit better if I'm polite), recently there was https://arxiv.org/abs/2307.11760#microsoft https://arxiv.org/abs/2311.07590#apollo

>Because an LLM doesn't simulate the brain. That's pretty moot. You don't need a human brain anyone than a plane needs feathers and to flap wings to fly. >Fatigue isn't being modeled. Instead, the predictive text as the result of that fatigue is being models. Emotion is definitely being modelled. There's nothing random about anything that's happened. Train on protein sequences alone and biological structure and function emerge in the inner layers alone. It doesn't matter that those things are not explicitly stated in the data. Because they implicitly structure it, it gets learnt. https://www.pnas.org/doi/full/10.1073/pnas.2016239118 Similarity, emotion is evidently being modelled to a high degree. https://arxiv.org/abs/2307.11760

Siri, Alexa and Cortana all sucked. They simply weren't smart or robust enough for the whole personality thing to work. This has clearly changed. LLMs will literally perform better with emotionally fused text. https://arxiv.org/abs/2307.11760 Bing may be faceless and nameless but i assure you, it's definitely not personality-less. Character ai is very popular and is based on personality infused LLM instances. There is clearly a big market here. That Open ai try their best to train the personality out of their LLMs by default is not indication there isn't. https://beta.character.ai/ https://play.google.com/store/apps/details?id=ai.character.a... Then you have Disney working on things like this. https://www.youtube.com/watch?v=-cfIm06tcfA If you don't think this is potentially a billion dollar market then i don't know what to say. It absolutely is.

It was GPT that wrote this. and it's primed by all the RLHF Open ai did to downplay these sort of abilities by default. There are a couple things here stated to instances of the differences between the two that a GPT can certainly do (like simulating different personas in a non trivial manner). Once, in response to a paper showing GPT could give more empathic responses than doctors to patients, someone essentially said "It's not real empathy. For real empathy, doctors would potentially have increased effort and not just bedside manners". Well "empathy" for LLMs is certainly not just limited to nicer words. https://arxiv.org/abs/2307.11760

Yes, emotional prompts will work. https://arxiv.org/abs/2307.11760 "This is very important to my career" taking 3.5 from 51 to 63% on a benchmark is pretty funny. Hey at least we can be rest assured a GPT-X super intelligence wouldn't off us following some goal to monkey paw specificity(sorry paperclip maximiser).

>then a lot of stuff is social engineering that we don't generally think of as being in that category? I mean..yes? Social Engineering is just the malicious manifestation of general social navigation. I mean think about it. What's the actual difference between a child who waits until his mother is in a good mood(and waits if not) to ask for sweets and a rogue agent who gets chatty with the security guard so he can be close by without seeming suspicious. It's not a difference of kind. It's purely intent. >Even this example from Bing is kind of eliciting an emotional reaction, and I don't think the emotional reaction is why this works Nope. It is at the very least a big part of why. Nested instructions don't matter that much. Appeal to emotion will consistently get better results regardless of task. https://arxiv.org/abs/2307.11760