Acta Psychologica Sinica ›› 2026, Vol. 58 ›› Issue (2): 308-322.doi: 10.3724/SP.J.1041.2026.0308
• Reports of Empirical Studies • Previous Articles Next Articles
Published:2026-02-25
Online:2025-12-03
Contact:
WU Shiyu
E-mail:shiyuw@sjtu.edu.cn
WU Shiyu, WANG Yiyun. (2026). “Zero-Shot Language Learning”: Can Large Language Models “Acquire” Contextual Emotion Like Humans?. Acta Psychologica Sinica, 58(2), 308-322.
Add to citation manager EndNote|Ris|BibTeX
URL: https://journal.psych.ac.cn/acps/EN/10.3724/SP.J.1041.2026.0308
| Model | Architecture & Parameters | Open-source | Context window | Multimodal reasoning |
|---|---|---|---|---|
| Ernie Bot 3.5 (Yiyan) | Transformer/not disclosed | Closed-source | 8K | Text-image-video generation; moderate reasoning; optimized for Chinese |
| ChatGPT-4 (OpenAI) | Transformer/>1.75T parameters | Closed-source | 8K | Strong text-image reasoning; high logical and mathematical capability |
| Gemini 1.5 Pro (Google DeepMind) | Transformer + MoE / not disclosed | Closed-source | 2M | Exceptional visual understanding; advanced reasoning and retrieval |
| LLaMA 3.1-8B (Meta) | Transformer/~8B parameters | Open-source | 128K | Text-only; lacks multimodality; solid baseline reasoning for smaller tasks |
Table 1 Overview of the four large language models
| Model | Architecture & Parameters | Open-source | Context window | Multimodal reasoning |
|---|---|---|---|---|
| Ernie Bot 3.5 (Yiyan) | Transformer/not disclosed | Closed-source | 8K | Text-image-video generation; moderate reasoning; optimized for Chinese |
| ChatGPT-4 (OpenAI) | Transformer/>1.75T parameters | Closed-source | 8K | Strong text-image reasoning; high logical and mathematical capability |
| Gemini 1.5 Pro (Google DeepMind) | Transformer + MoE / not disclosed | Closed-source | 2M | Exceptional visual understanding; advanced reasoning and retrieval |
| LLaMA 3.1-8B (Meta) | Transformer/~8B parameters | Open-source | 128K | Text-only; lacks multimodality; solid baseline reasoning for smaller tasks |
| [1] | Ahmed S. (2004). The cultural politics of emotion. New York: Rouledge. |
| [2] | Ahmed S. (2010). The promise of happiness. London: Duke University Press. |
| [3] |
Andrews B., Vigliocco G., & Vinson D. P. (2009). Integrating experiential and distributional data to learn semantic representations. Psychological Review, 116(3), 463-498.
doi: 10.1037/a0016261 pmid: 19618982 |
| [4] |
Baayen R. H., Davidson D. J., & Bates D. M. (2008). Mixed-effects modeling with crossed random effects for subjects and items. Journal of Memory and Language, 59(4), 390-412.
doi: 10.1016/j.jml.2007.12.005 URL |
| [5] | Balass M. (2011). Learning words in context: An ERP investigation of word experience effects on familiarity and meaning acquisition (Unpublished doctorial dissertation). University of Pittsburgh. |
| [6] | Barrett L. F. (2017). The theory of constructed emotion: An active inference account of interoception and categorization. Social Cognitive and Affective Neuroscience, 12(11),1833. |
| [7] |
Barsalou L. W. (2008). Grounded cognition. Annual Review of Psychology, 59(1), 617-645.
doi: 10.1146/psych.2008.59.issue-1 URL |
| [8] | Binz M., & Schulz E. (2023). Turning large language models into cognitive models. Computer Science. Advance online publication. https://doi.org/10.48550/arXiv.2306.03917 |
| [9] | Bisk Y., Holtzman A., Thomason J., Andreas J., Bengio Y., Chai J.,... Turian J. (2020). Experience grounds language. Computer Science. Advance online publication. https://doi.org/10.48550/arXiv. 2004.10151 |
| [10] |
Blythe H. I., Liang F., Zang C., Wang J., Yan G., Bai X., & Liversedge S. P. (2012). Inserting spaces into Chinese text helps readers to learn new words: An eye movement study. Journal of Memory and Language, 67(2), 241-254.
doi: 10.1016/j.jml.2012.05.004 URL |
| [11] |
Bolger D. J., Balass M., Landen E., & Perfetti C. A. (2008). Context variation and definitions in learning the meanings of words: An instance-based learning approach. Discourse Processes, 45(2), 122-159.
doi: 10.1080/01638530701792826 URL |
| [12] | Brown T. B., Mann B., Ryder N., Subbiah M., Kaplan J., Dhariwal P., … Amodei D. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877-1901. |
| [13] |
Caliskan A., Bryson J. J., & Narayanan A. (2017). Semantics derived automatically from language corpora contain human-like biases. Science, 356(6334), 183-186.
doi: 10.1126/science.aal4230 pmid: 28408601 |
| [14] |
Chomsky N. (1957). Fundamentals of language. International Journal of American Linguistics, 23(3), 234-242.
doi: 10.1086/464414 URL |
| [15] | Christensen R. H. B. (2023). ordinal: Regression models for ordinal data. R package version 2023.12-4.1. https://CRAN.R-project.org/package=ordinal |
| [16] | Clark E., Celikyilmaz A., & Smith N. A. (2019, July). Sentence mover’s similarity: Automatic evaluation for multi-sentence texts. Paper presented at the meeting of the Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy. |
| [17] | Damasio A. R. (1994). Descartes’ error: Emotion, reason and the human brain. New York: Grosset/Putnam. |
| [18] |
Driver M. (2022). Emotion-laden texts and words: The influence of emotion on vocabulary learning for heritage and foreign language learners. Studies in Second Language Acquisition, 44(4), 1071-1094.
doi: 10.1017/S0272263121000851 URL |
| [19] | Ellis N. C., & Wulff S. (2015). Usage-based approaches to SLA. In B. VanPatten, & J. Williams (Eds.), Second language acquisition research series: Theories in second language acquisition (pp. 75-94). Routledge. |
| [20] | Eysenck M. W., & Brysbaert M. (2018). Fundamentals of cognition (3rd ed.). Routledge. |
| [21] |
Godfroid A., Ahn J., Choi I., Ballard L., Cui Y., Johnston S.,... Yoon H. -J. (2018). Incidental vocabulary learning in a natural reading context: An eye-tracking study. Bilingualism: Language and Cognition, 21(3), 563-584.
doi: 10.1017/S1366728917000219 URL |
| [22] | Hagendorff T., Dasgupta I., Binz M., Chan S. C. Y., Lampinen A., Wang J. X.,... Schulz E. (2023). Machine psychology. Computer Science. Advance online publication. https://doi.org/10.48550/arXiv. 2303.13988 |
| [23] |
Hasson U., Ghazanfar A.A., Galantucci B., Garrod S., & Keysers C. (2012). Brain-to-brain coupling: A mechanism for creating and sharing a social world. Trends in cognitive sciences, 16(2), 114-121.
doi: 10.1016/j.tics.2011.12.007 pmid: 22221820 |
| [24] | Hatfield E., Cacioppo J. T., & Rapson R. L. (1993). Emotional Contagion (1st ed.). New York: Cambridge University Press. |
| [25] |
Ho M. H., Kemp B. T., Eisenbarth H., & Rijnders R. J. P. (2023). Designing a neuroclinical assessment of empathy deficits in psychopathy based on the Zipper Model of Empathy. Neuroscience and Biobehavioral Reviews, 151, 105244.
doi: 10.1016/j.neubiorev.2023.105244 URL |
| [26] |
Horst J. S., Parsons K. L., & Bryan N. M. (2011). Get the story straight: Contextual repetition promotes word learning from storybooks. Frontiers in Psychology, 2, 17.
doi: 10.3389/fpsyg.2011.00017 pmid: 21713179 |
| [27] | Hulstijn J. H. (2001). Intentional and incidental second-language vocabulary learning:A reappraisal of elaboration, rehearsal and automaticity. In P. Robinson (Ed.), Cognition and second language instruction (pp. 258-286). Cambridge University Press. |
| [28] | Johns B. T., & Jones M. N. (2008). Predicting lexical decision and naming times from a semantic space model. Proceedings of the 30th Annual Cognitive Science Society, 30(30), 279-284. |
| [29] | Jones M. N., Dye M., & Johns B. T. (2017). Context as an organizing principle of the lexicon. In B. H. Ross (Ed.), Psychology of learning and motivation (Vol. 67, pp. 239-283). United States: Elsevier Science & Technology. |
| [30] |
Joseph H., & Nation K. (2018). Examining incidental word learning during reading in children: The role of context. Journal of Experimental Child Psychology, 166, 190-211.
doi: S0022-0965(16)30239-9 pmid: 28942127 |
| [31] |
Keuleers E., & Brysbaert M. (2010). Wuggy: A multilingual pseudoword generator. Behavior Research Methods, 42(3), 627-633.
doi: 10.3758/BRM.42.3.627 pmid: 20805584 |
| [32] |
Lana N., & Kuperman V. (2024). Learning concrete and abstract novel words in emotional contexts: Evidence from incidental vocabulary learning. Language Learning and Development, 20(2), 158-173.
doi: 10.1080/15475441.2023.2246438 URL |
| [33] |
Landauer T. K., & Dumais S. T. (1997). A solution to Plato’s problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge. Psychological Review, 104(2), 211-240.
doi: 10.1037/0033-295X.104.2.211 URL |
| [34] |
Laufer B., & Aviad-Levitzky T. (2017). What type of vocabulary knowledge predicts reading comprehension: Word meaning recall or word meaning recognition? The Modern Language Journal, 101(4), 729-741.
doi: 10.1111/modl.v101.4 URL |
| [35] |
Lauro J., Schwartz A. I., & Francis W. S. (2020). Bilingual novel word learning in sentence contexts: Effects of semantic and language variation. Journal of Memory and Language, 113, 104123.
doi: 10.1016/j.jml.2020.104123 URL |
| [36] | Li Z. (2024). Semantic prosody acquisition and its influence on the learning of L2 novel word forms and meanings [Unpublished doctorial dissertation]. Shanghai Jiao Tong University. |
| [37] | Louw B. (1993). Irony in the text or insincerity in the writer? The diagnostic potential of semantic prosodies. In M. Baker, G. Francis, & E. Tognini-Bonelli (Eds.), Text and technology: In honour of John Sinclair (pp. 157-176). Amsterdam, The Netherlands: John Benjamins. |
| [38] | Ma Z., & Li Z. (2024). Acquiring semantic prosody in L2 novel word learning: The effect of context variability and gender. Modern Foreign Languages, 47(6), 790-801. |
| [39] |
MacIntyre P. D., & Vincze L. (2017). Positive and negative emotions underlie motivation for L2 learning. Studies in Second Language Learning and Teaching, 7(1), 61-88.
doi: 10.14746/ssllt.2017.7.1.4 URL |
| [40] |
Miller G. A. (1956). The magical number seven, plus or minus two: Some limits on our capacity for processing information. Psychological Review, 63(2), 81-97.
doi: 10.1037/h0043158 URL |
| [41] | Nevisi R. B., Hosseinpur R. M., & Darvish F. Z. (2018). The impact of L1/L2-based explicit output task instruction on Iranian EFL learners’ semantic prosody learning. Journal of Language Horizons, 2(2), 51-74. |
| [42] |
Pessoa L. (2008). On the relationship between emotion and cognition. Nature Reviews Neuroscience, 9(2), 148-158.
doi: 10.1038/nrn2317 pmid: 18209732 |
| [43] | Radford A., Wu J., Child R., Luan D., Amodei D., & Sutskever I. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9. |
| [44] | Schmidt R. W. (1990). The role of consciousness in second language learning. Applied Linguistics, 11(2), 129. |
| [45] | Sinclair J. M. (1987). Looking up. London: Collins. |
| [46] |
Snefjella B., Lana N., & Kuperman V. (2020). How emotion is learned: Semantic learning of novel words in emotional contexts. Journal of Memory and Language, 115, 104171.
doi: 10.1016/j.jml.2020.104171 URL |
| [47] |
Stewart J., Gyllstad H., Nicklin C., & McLean S. (2024). Establishing meaning recall and meaning recognition vocabulary knowledge as distinct psychometric constructs in relation to reading proficiency. Language Testing, 41(1), 89-108.
doi: 10.1177/02655322231162853 URL |
| [48] |
Tamir M., Schwartz S. H., Cieciuch J., Riediger M., Torres C., Scollon C.,... Vishkin A. (2016). Desired emotions across cultures: A value-based account. Journal of personality and social psychology, 111(1), 67-82.
doi: 10.1037/pspp0000072 pmid: 26524003 |
| [49] | Tomasello M. (2005). Constructing a language: A usage-based theory of language acquisition (1st ed.). Cambridge: Harvard University Press. |
| [50] |
Tulving E., & Thomson D. M. (1973). Encoding specificity and retrieval processes in episodic memory. Psychological Review, 80(5), 352-373.
doi: 10.1037/h0020071 URL |
| [51] | Wang W., Zheng V. W., Yu H., & Miao C. (2019). A survey of zero-shot learning: Settings, methods, and applications. ACM Transactions on Intelligent Systems and Technology, 10(2), 1-37. |
| [52] | Wetherell M. (2012). Affect and emotion: A new social science understanding (1st ed.). Los Angeles: SAGE. |
| [53] |
Wu S. Y., & Li Z. (2024). How semantic prosody is acquired in novel word learning: Evidence from the “Double-date Tree” effect. Acta Psychologica Sinica, 56(5), 531-543.
doi: 10.3724/SP.J.1041.2024.00531 URL |
| [1] | JIAO Liying, LI Chang-Jin, CHEN Zhen, XU Hengbin, XU Yan. When AI “possesses” personality: Roles of good and evil personalities influence moral judgment in large language models [J]. Acta Psychologica Sinica, 2025, 57(6): 929-946. |
| [2] | GAO Chenghai, DANG Baobao, WANG Bingjie, WU Michael Shengtao. The linguistic strength and weakness of artificial intelligence: A comparison between Large Language Model (s) and real students in the Chinese context [J]. Acta Psychologica Sinica, 2025, 57(6): 947-966. |
| [3] | ZHANG Yanbo, HUANG Feng, MO Liuling, LIU Xiaoqian, ZHU Tingshao. Suicidal ideation data augmentation and recognition technology based on large language models [J]. Acta Psychologica Sinica, 2025, 57(6): 987-1000. |
| [4] | HUANG Feng, DING Huimin, LI Sijia, HAN Nuo, DI Yazheng, LIU Xiaoqian, ZHAO Nan, LI Linyan, ZHU Tingshao. Self-help AI psychological counseling system based on large language models and its effectiveness evaluation [J]. Acta Psychologica Sinica, 2025, 57(11): 2022-2042. |
| Viewed | ||||||
|
Full text |
|
|||||
|
Abstract |
|
|||||
