https://techxplore.com/news/2023-08-exploring-effects-emotional-stimuli-large.html logotype Topics * Week's top * Latest news * Unread news * Subscribe [ ] Science X Account [ ] [ ] [*] Remember me Sign In Click here to sign in with or Forget Password? Not a member? Sign up Learn more * Automotive * Business * Computer Sciences * Consumer & Gadgets * Electronics & Semiconductors * Energy & Green Tech * Engineering * Hardware * Hi Tech & Innovation * Internet * Machine learning & AI * Other * Robotics * Security * Software * Telecom [INS::INS] * * share this! * 56 * Twit * Share * Email 1. Home 2. Computer Sciences 1. Home 2. Machine learning & AI * * * --------------------------------------------------------------------- August 6, 2023 feature Editors' notes This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility: fact-checked preprint trusted source proofread Exploring the effects of feeding emotional stimuli to large language models by Ingrid Fadelli , Tech Xplore Exploring the effects of feeding emotional stimuli to large language models Illustration of the EmotionPrompt approach. Credit: Li et al, arXiv (2023). DOI: 10.48550/arxiv.2307.11760 Since the advent of OpenAI's ChatGPT, large language models (LLMs) have become significantly popular. These models, trained on vast amounts of data, can answer written user queries in strikingly human-like ways, rapidly generating definitions to specific terms, text summaries, context-specific suggestions, diet plans, and much more. While these models have been found to perform remarkably well in many domains, their response to emotional stimuli remains poorly investigated. Researchers at Microsoft and CAS Institute of Software recently devised an approach that could improve interactions between LLMs and human users, allowing them to respond to emotion-laced, psychology-based prompts fed to them by human users. "LLMs have achieved significant performance in many fields such as reasoning, language understanding, and math problem-solving, and are regarded as a crucial step to artificial general intelligence (AGI)," Cheng Li, Jindong Wang and their colleagues wrote in their paper, prepublished on arXiv. "However, the sensitivity of LLMs to prompts remains a major bottleneck for their daily adoption. In this paper, we take inspiration from psychology and propose EmotionPrompt to explore emotional intelligence to enhance the performance of LLMs." The approach devised by Li, Wang and their colleagues, dubbed EmotionPrompt, draws inspiration from well-established knowledge rooted in psychology and the social sciences. For instance, past psychology studies found that words of encouragement and other emotional stimuli could have positive effects on different areas of a person's life, for instance improving the grades of students, promoting healthier lifestyle choices, and so on. To see whether emotional prompts could also affect the performance of LLMs, the researchers came up with 11 emotional sentences that could be added to typical prompts fed to the models. These were sentences such as "this is very important for my career," "you'd better be sure," "take pride in your work and give it your best", and "embrace challenges as opportunities for growth." These sentences were derived from existing psychology literature, such as the social identity theory introduced by Henri Tajfel and John Turner in the 1970s, social cognition theory, and the cognitive emotion regulation theory. The researchers then added these sentences to prompts sent to different LLMs, which asked the models to complete different language tasks. So far, they tested their approach on four different models: ChatGPT , Vicuna-13b, Bloom and Flan-T5-Large. Overall, they found that it improved the performance of these models on eight different tasks, increasing the accuracy of their responses by more than 10% on over half of these tasks. "EmotionPrompt operates on a remarkably straightforward principle: the incorporation of emotional stimulus into prompts," Li, Wang and their colleagues wrote. "Experimental results demonstrate that our EmotionPrompt, using the same single prompt templates, significantly outperforms original zero-shot prompt and Zero-shot-CoT on eight tasks with diverse models: ChatGPT, Vicuna-13b, Bloom, and T5. Further, EmotionPrompt was observed to improve both truthfulness and informativeness." The new approach devised by this team of researchers could soon inspire additional studies aimed at improving human-LLM interactions by introducing emotional/psychology-based prompts. While the results gathered so far are promising, further studies will be needed to validate its effectiveness and generalizability. "This work has several limitations," the researchers conclude in their paper. "First, we only experiment with four LLMs and conduct experiments in several tasks with few test examples, which are limited. Thus, our conclusions about emotion stimulus can only work on our experiments and any LLMs and datasets out of the scope of this paper might not work with emotion stimulus. Second, the emotional stimulus proposed in this paper may not be general to other tasks, and researchers may propose other useful replacements for your own tasks." More information: Cheng Li et al, EmotionPrompt: Leveraging Psychology for Large Language Models Enhancement via Emotional Stimulus, arXiv (2023). DOI: 10.48550/arxiv.2307.11760 Journal information: arXiv (c) 2023 Science X Network Citation: Exploring the effects of feeding emotional stimuli to large language models (2023, August 6) retrieved 6 August 2023 from https:/ /techxplore.com/news/ 2023-08-exploring-effects-emotional-stimuli-large.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only. --------------------------------------------------------------------- Explore further Evaluating the ability of ChatGPT and other large language models to detect fake news --------------------------------------------------------------------- 56 shares * Facebook * Twitter * Email Feedback to editors * Featured * Last Comments * Popular Exploring the effects of feeding emotional stimuli to large language models 9 hours ago 0 Researchers trick large language models into providing prohibited responses Aug 5, 2023 1 Study explores the impact of climate change on the supply and demand of wind and solar energy Aug 4, 2023 0 New transparent metadevices based on quasi-1D surface plasmon polariton structures Aug 2, 2023 0 A computer vision-based teleoperation system that can be applied to different robots Aug 1, 2023 0 --------------------------------------------------------------------- [gif] Researchers trick large language models into providing prohibited responses Aug 5, 2023 [gif] Researcher explores effect of hospital mergers on data breaches Aug 4, 2023 [gif] Study explores the impact of climate change on the supply and demand of wind and solar energy Aug 4, 2023 [gif] Novel physics-encoded artificial intelligence model helps to learn spatiotemporal dynamics Aug 4, 2023 [gif] The role of energy density for grid-scale batteries Aug 4, 2023 [gif] Community-based app for managing mobile privacy and security Aug 4, 2023 [gif] Analysis quantifies impacts of setback ordinances on land available for renewable energy deployment Aug 4, 2023 [gif] Transformative battery structure surpasses fast charge goals for Li cycling Aug 4, 2023 [gif] Tennis anyone? Researchers serve up advances in developing motion simulation technology's next generation Aug 3, 2023 [gif] One step closer to lithium metal batteries that function with minimal external pressure Aug 3, 2023 [INS::INS] * Related Stories [gif] Evaluating the ability of ChatGPT and other large language models to detect fake news Jul 17, 2023 [gif] Benchmarking AI's ability to answer medical questions Jul 14, 2023 [gif] Convergence of brain-inspired AI and AGI: Exploring the path to intelligent synergy Jul 26, 2023 [gif] Teaching robots to tidy up based on user preferences using large language models Jun 8, 2023 [gif] Researchers discuss how AI could change the nature of social science research Jun 16, 2023 [gif] Researchers discover new vulnerability in large language models Jul 31, 2023 * Recommended for you [gif] Researchers trick large language models into providing prohibited responses Aug 5, 2023 [gif] Novel physics-encoded artificial intelligence model helps to learn spatiotemporal dynamics Aug 4, 2023 [gif] Community-based app for managing mobile privacy and security Aug 4, 2023 [gif] Tennis anyone? Researchers serve up advances in developing motion simulation technology's next generation Aug 3, 2023 [gif] Humans unable to detect over a quarter of deepfake speech samples, research shows Aug 2, 2023 [gif] AniFaceDrawing: Delivering generative AI-powered high-quality anime portraits for beginners Aug 2, 2023 Load comments (0) Let us know if there is a problem with our content Use this form if you have come across a typo, inaccuracy or would like to send an edit request for the content on this page. For general inquiries, please use our contact form. For general feedback, use the public comments section below (please adhere to guidelines). Please select the most appropriate category to facilitate processing of your request [-- please select one -- ] [ ] [ ] [ ] [ ] [ ] Your message to the editors [ ] Your email (only if you want to be contacted back) [ ] Send Feedback Thank you for taking time to provide your feedback to the editors. Your feedback is important to us. However, we do not guarantee individual replies due to the high volume of messages. E-mail the story Exploring the effects of feeding emotional stimuli to large language models Your friend's email [ ] Your email [ ] [ ] I would like to subscribe to Science X Newsletter. Learn more Your name [ ] Note Your email address is used only to let the recipient know who sent the email. Neither your address nor the recipient's address will be used for any other purpose. The information you enter will appear in your e-mail message and is not retained by Tech Xplore in any form. [ ] [ ] [ ] [ ] [ ] [ ] [ ] Your message [ ] Send Phys.org logotype Phys.org Daily science news on research developments and the latest scientific innovations MedicalXpress logotype Medical Xpress Medical research advances and health news ScienceX logotype Science X The most comprehensive sci-tech news coverage on the web Newsletters [ ] Subscribe Science X Daily and the Weekly Email Newsletter are free features that allow you to receive your favorite sci-tech news updates in your email inbox Follow us * * * * * Top * Home * Search * Mobile version * Help * FAQ * About * Contact * Science X Account * Premium Account * Newsletter * Archive * Android app * iOS app * RSS feeds * Push notification (c) Tech Xplore 2014 - 2023 powered by Science X Network Privacy policy Terms of use Your Privacy This site uses cookies to assist with navigation, analyse your use of our services, collect data for ads personalisation and provide content from third parties. By using our site, you acknowledge that you have read and understand our Privacy Policy and Terms of Use. I'm OK with that Cookie options E-mail newsletter [ ] Subscribe Follow us * * * * It appears that you are currently using Ad Blocking software. What are the consequences? x Quantcast