The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Emotional intelligence of Large Language Models
Open accessAbstract
Large Language Models (LLMs) have demonstrated remarkable abilities across numerous disciplines, primarily assessed through tasks in language generation, knowledge utilization, and complex reasoning. However, their alignment with human emotions and values, which is critical for real-world applications, has not been systematically evaluated. Here, we assessed LLMs' Emotional Intelligence (EI), encompassing emotion recognition, interpretation, and understanding, which is necessary for effective communication and social interactions. Specifically, we first developed a novel psychometric assessment focusing on Emotion Understanding (EU), a core component of EI. This test is an objective, performance-driven, and text-based evaluation, which requires evaluating complex emotions in realistic scenarios, providing a consistent assessment for both human and LLM capabilities. With a reference frame constructed from over 500 adults, we tested a variety of mainstream LLMs. Most achieved above-average Emotional Quotient (EQ) scores, with GPT-4 exceeding 89% of human participants with an EQ of 117. Interestingly, a multivariate pattern analysis revealed that some LLMs apparently did not rely on the human-like mechanism to achieve human-level performance, as their representational patterns were qualitatively distinct from humans. In addition, we discussed the impact of factors such as model size, training method, and architecture on LLMs' EQ. In summary, our study presents one of the first psychometric evaluations of the human-like characteristics of LLMs, which may shed light on the future development of LLMs aiming for both high intellectual and emotional intelligence. Project website: https://emotional-intelligence.github.io/
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The results showed that most LLMs achieve above-average scores in emotional quotient (EQ), with GPT-4 scoring 117, surpassing 89% of human participants.”
From A Survey on Evaluation of Large Language Models (2024) · cites this paper as [212]
In the citing paper
“This is evident from the distinct differences in the quality of their representational patterns, as compared to humans.”
From A Survey on Evaluation of Large Language Models (2024) · cites this paper as [212]
In the citing paper
“However, a multivariate pattern analysis indicated that certain LLMs achieve human-level performance without relying on mechanisms resembling those found in humans.”
From A Survey on Evaluation of Large Language Models (2024) · cites this paper as [212]
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Salovey, P., & Mayer, J. D. (1990) · Imagination, Cognition and Personality · doi:10.2190/dugg-p24e-52wk-6cdg · Cited by 10,484
Does the autistic child have a “theory of mind” ?
Baron-Cohen, S., Leslie, A. M., & Frith, U. (1985) · Cognition · doi:10.1016/0010-0277(85)90022-8 · Cited by 8,599 · cited 2×
“…is a heterogeneous concept, spanning from false belief, the understanding that others can hold beliefs about the world that diverge from reality (Baron-Cohen et al., 1985), to pragmatic reasoning, the ability to incorporate contextual information and practical considerations when solving…”
BackgroundLLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Proceedings of the 13th International Conference on Neural Information Processing Systems
Leen, T. K., Dietterich, T. G., & Tresp, V. (2000) · Cited by 2,190
Measuring emotional intelligence with the MSCEIT V2.0.
Mayer, J. D., Salovey, P., Caruso, D. R., & Sitarenios, G. (2003) · Emotion · doi:10.1037/1528-3542.3.1.97 · Cited by 1,879
The Ability Model of Emotional Intelligence: Principles and Updates
Mayer, J. D., Caruso, D. R., & Salovey, P. (2016) · Emotion Review · doi:10.1177/1754073916639667 · Cited by 1,651
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y. T., Li, Y., Lundberg, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.12712 · Cited by 1,526
Reflexion: Language Agents with Verbal Reinforcement Learning
Shinn, N., Cassano, F., Berman, E., Gopinath, A., Narasimhan, K., & Yao, S. (2023) · arXiv · doi:10.48550/arxiv.2303.11366 · Cited by 1,087 · cited 1×
“Prompt engineering — the meticulous development and choice of prompts — plays a pivotal role in the ef fi cacy of LLMs (Hebenstreit et al., 2023; Hendrycks et al., 2021; Nair et al., 2023; OpenAI, 2023; Shinn et al., 2023).”
BackgroundEmotional intelligence as a standard intelligence.
Mayer, J. D., Salovey, P., Caruso, D. R., & Sitarenios, G. (2001) · Emotion · doi:10.1037/1528-3542.1.3.232 · Cited by 1,036
Research works printed but not linked: 13
- Bai Y., Kadavath S., Kundu S., Askell A., Kernion J., Jones A., Chen A., Goldie A., Mirhoseini A., McKinnon C., Chen C., Olsson C., Olah C., Hernandez D., Drain D., Ganguli D., Li D., Tran-Johnson E., Perez E. … Kaplan J. (2022). Constitutional AI: Harmlessness from AI feedback (arXiv:2212.08073). arXiv. http://arxiv.org/abs/2212.08073 · arXiv
- Baron-Cohen S., 2020, The pattern seekers: How autism drives human invention
- Hanafi Z., 2016, International Journal of Academic Research in Business and Social Sciences, 6, 268
- Hebenstreit K., Praas R., Kiesewetter L. P., Samwald M. (2023). An automatically discovered chain-of-thought prompt generalizes to novel models and datasets (arXiv:2305.02897). arXiv. http://arxiv.org/abs/2305.02897 · arXiv
- Hendrycks D., Burns C., Basart S., Zou A., Mazeika M., Song D., Steinhardt J. (2021). Measuring massive multitask language understanding (arXiv:2009.03300). arXiv. http://arxiv.org/abs/2009.03300 · arXiv
- Izard V., 2009, Human Evolution, 23, 213
- Kosinski M. (2023). Theory of mind may have spontaneously emerged in large language models (arXiv:2302.02083). arXiv. http://arxiv.org/abs/2302.02083 · arXiv
- OpenAI. (2023). GPT-4 technical report (arXiv:2303.08774). arXiv. http://arxiv.org/abs/2303.08774 · arXiv
- Taori R., Stanford Center for Research on Foundation Models, 3, 7
- Vaswani A., 2017, 31st Conference on Neural Information Processing Systems
- Zeng A., Liu X., Du Z., Wang Z., Lai H., Ding M., Yang Z., Xu Y., Zheng W., Xia X., Tam W. L., Ma Z., Xue Y., Zhai J., Chen W., Zhang P., Dong Y., Tang J. (2022). GLM-130B: An open bilingual pre-trained model (arXiv:2210.02414). arXiv. http://arxiv.org/abs/2210.02414 · arXiv
- Zhao W. X., Zhou K., Li J., Tang T., Wang X., Hou Y., Min Y., Zhang B., Zhang J., Dong Z., Du Y., Yang C., Chen Y., Chen Z., Jiang J., Ren R., Li Y., Tang X., Liu Z. … J.R. Wen (2023). A survey of large language models (arXiv:2303.18223). arXiv. http://arxiv.org/abs/2303.18223 · arXiv
- Zheng L., Chiang W.L., Sheng Y., Zhuang S., Wu Z., Zhuang Y., Lin Z., Li Z., Li D., Xing E. P., Zhang H., Gonzalez J. E., Stoica I. (2023). Judging LLM-as-a-judge with MT-Bench and Chatbot Arena . http://arxiv.org/abs/2306.05685 · arXiv
Cited by
Sorted by citations
A Survey on Evaluation of Large Language Models
Chang, Y., Wang, X., Wang, J., Wu, Y., Yang, L., Zhu, K., Chen, H., Yi, X., Wang, C., Wang, Y., et al. (2024) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3641289 · Cited by 4,254
“[200] developed a new psychometric assessment method.”
Self-citationHuman-AI agency in the age of generative AI
Krakowski, S. M. (2025) · Information and Organization · doi:10.1016/j.infoandorg.2025.100560 · Cited by 223
Hadi, M. U., Al-Tashi, Q., Qureshi, R., Shah, A., Muneer, A., Irfan, M., Zafar, A., Shaikh, M. B., Akhtar, N., Hassan, S. Z., et al. (2023) · doi:10.36227/techrxiv.23589741.v4 · Cited by 193
Yuan, A., Colato, E. G., Pescosolido, B. A., Song, H., & Samtani, S. (2024) · ACM Transactions on Management Information Systems · doi:10.1145/3701041 · Cited by 84
Zhang, Y., Wang, M., Wu, Y., Tiwari, P., Li, Q., Wang, B., & Qin, J. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107901 · Cited by 120
Self-citation
Metadata
- Authors
- Wang, X., Li, X., Yin, Z., Wu, Y., & Liu, J.
- Affiliations
- Tsinghua University (CN)
- Renmin University of China (CN)
- Department of Psychology & Tsinghua Laboratory of Brain and Intelligence, Tsinghua University, Beijing, China
- Venue
- Journal of Pacific Rim Psychology
- Publisher
- SAGE Publications
- Published
- 2023-01
- Volume
- 17
- ISSN
- 1834-4909 (ISSN-L)
- OpenAlex
- W4388708748
- Cited by
- 128
- References
- 31
- Citations by year
- 2026: 41 · 2025: 59 · 2024: 27 · 2023: 1
- FWCI
- 33.02
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Journal of Pacific Rim Psychology (publishedVersion, cc-by-nc)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Tsinghua University Guoqiang Institute (2020GQG1016)
- Shuimu Tsinghua Scholar Program
- Beijing Municipal Science & Technology Commission, Administrative Commission of Zhongguancun Science Park (Z221100002722012)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Social Sciences › Psychology › Social Psychology › Emotional Intelligence and Performance
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Keywords
- large language models, emotional intelligence, emotional understanding, emotional quotient, psychometric assessment, emotion recognition, GPT-4, model size, training methods, neural architecture, multivariate pattern analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
