• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

使用基于隐喻和讽刺情景的精神科筛查工具评估大语言模型的能力

Evaluating Large Language Models' Ability Using a Psychiatric Screening Tool Based on Metaphor and Sarcasm Scenarios.

作者信息

Yakura Hiromu

机构信息

Max-Planck Institute for Human Development, 14195 Berlin, Germany.

出版信息

J Intell. 2024 Jul 21;12(7):70. doi: 10.3390/jintelligence12070070.

DOI:10.3390/jintelligence12070070
PMID:39057190
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11278383/
Abstract

Metaphors and sarcasm are precious fruits of our highly evolved social communication skills. However, children with the condition then known as Asperger syndrome are known to have difficulties in comprehending sarcasm, even if they possess adequate verbal IQs for understanding metaphors. Accordingly, researchers had employed a screening test that assesses metaphor and sarcasm comprehension to distinguish Asperger syndrome from other conditions with similar external behaviors (e.g., attention-deficit/hyperactivity disorder). This study employs a standardized test to evaluate recent large language models' (LLMs) understanding of nuanced human communication. The results indicate improved metaphor comprehension with increased model parameters; however, no similar improvement was observed for sarcasm comprehension. Considering that a human's ability to grasp sarcasm has been associated with the amygdala, a pivotal cerebral region for emotional learning, a distinctive strategy for training LLMs would be imperative to imbue them with the ability in a cognitively grounded manner.

摘要

隐喻和讽刺是我们高度进化的社交沟通技巧的宝贵成果。然而,患有当时被称为阿斯伯格综合征的儿童已知在理解讽刺方面存在困难,即使他们具备足够的语言智商来理解隐喻。因此,研究人员采用了一种评估隐喻和讽刺理解能力的筛查测试,以将阿斯伯格综合征与其他具有相似外在行为的病症(如注意力缺陷多动障碍)区分开来。本研究采用标准化测试来评估近期大语言模型(LLMs)对细微人类沟通的理解。结果表明,随着模型参数的增加,隐喻理解能力有所提高;然而,讽刺理解能力并未观察到类似的改善。鉴于人类理解讽刺的能力与杏仁核(情绪学习的关键脑区)有关,一种独特的训练大语言模型的策略将势在必行,以便以基于认知的方式赋予它们这种能力。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8425/11278383/b193c76ff363/jintelligence-12-00070-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8425/11278383/48617a118ce6/jintelligence-12-00070-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8425/11278383/b1d718933de8/jintelligence-12-00070-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8425/11278383/b193c76ff363/jintelligence-12-00070-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8425/11278383/48617a118ce6/jintelligence-12-00070-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8425/11278383/b1d718933de8/jintelligence-12-00070-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/8425/11278383/b193c76ff363/jintelligence-12-00070-g003.jpg

相似文献

1
Evaluating Large Language Models' Ability Using a Psychiatric Screening Tool Based on Metaphor and Sarcasm Scenarios.使用基于隐喻和讽刺情景的精神科筛查工具评估大语言模型的能力
J Intell. 2024 Jul 21;12(7):70. doi: 10.3390/jintelligence12070070.
2
An exploration of sarcasm detection in children with Attention Deficit Hyperactivity Disorder.对注意力缺陷多动障碍儿童讽刺识别能力的探究。
J Commun Disord. 2017 Nov;70:25-34. doi: 10.1016/j.jcomdis.2017.10.003. Epub 2017 Oct 31.
3
Comprehension of sarcasm, metaphor and simile in Williams syndrome.威廉斯综合征患者对反讽、隐喻和明喻的理解。
Int J Lang Commun Disord. 2013 Nov-Dec;48(6):651-65. doi: 10.1111/1460-6984.12037.
4
Communicative competence in Alzheimer's disease: metaphor and sarcasm comprehension.阿尔茨海默病患者的交际能力:隐喻和讽刺理解。
Am J Alzheimers Dis Other Demen. 2013 Feb;28(1):69-74. doi: 10.1177/1533317512467677. Epub 2012 Dec 7.
5
Distinction between the literal and intended meanings of sentences: a functional magnetic resonance imaging study of metaphor and sarcasm.句子的字面意义和意图意义的区别:隐喻和讽刺的功能磁共振成像研究。
Cortex. 2012 May;48(5):563-83. doi: 10.1016/j.cortex.2011.01.004. Epub 2011 Jan 26.
6
Looking at the brains behind figurative language--a quantitative meta-analysis of neuroimaging studies on metaphor, idiom, and irony processing.探讨隐喻、习语和反讽加工背后的大脑机制——一项关于神经影像学研究的定量元分析。
Neuropsychologia. 2012 Sep;50(11):2669-83. doi: 10.1016/j.neuropsychologia.2012.07.021. Epub 2012 Jul 21.
7
On the specificity of figurative language comprehension impairment in schizophrenia and its relation to cognitive skills but not psychopathological symptoms - Study on metaphor, humor and irony.精神分裂症中比喻性语言理解障碍的特异性及其与认知技能而非精神病理症状的关系——关于隐喻、幽默和反讽的研究
Schizophr Res Cogn. 2023 Oct 25;35:100294. doi: 10.1016/j.scog.2023.100294. eCollection 2024 Mar.
8
Inferences and metaphoric comprehension in unilaterally implanted children with adequate formal oral language performance.单侧植入且具有足够正式口语能力的儿童的推理与隐喻理解
Int J Pediatr Otorhinolaryngol. 2014 May;78(5):821-7. doi: 10.1016/j.ijporl.2014.02.022. Epub 2014 Feb 26.
9
Comprehension of figurative language in Taiwanese children with autism: The role of theory of mind and receptive vocabulary.台湾自闭症儿童对比喻性语言的理解:心理理论和接受性词汇的作用。
Clin Linguist Phon. 2015;29(8-10):764-75. doi: 10.3109/02699206.2015.1027833.
10
Impaired Interpretation of Others' Behavior is Associated with Difficulties in Recognizing Pragmatic Language in Patients with Schizophrenia.精神分裂症患者对他人行为的理解受损与语用语言识别困难有关。
J Psycholinguist Res. 2017 Oct;46(5):1309-1318. doi: 10.1007/s10936-017-9497-8.

引用本文的文献

1
Turing Jest: Distributional Semantics and One-Line Jokes.图灵笑话:分布语义学与单行笑话
Cogn Sci. 2025 May;49(5):e70066. doi: 10.1111/cogs.70066.

本文引用的文献

1
Applicability of Online Chat-Based Artificial Intelligence Models to Colorectal Cancer Screening.基于在线聊天的人工智能模型在结直肠癌筛查中的适用性。
Dig Dis Sci. 2024 Mar;69(3):791-797. doi: 10.1007/s10620-024-08274-3. Epub 2024 Jan 24.
2
Reliability of ChatGPT for performing triage task in the emergency department using the Korean Triage and Acuity Scale.使用韩国预检和 acuity 量表时 ChatGPT 在急诊科执行分诊任务的可靠性。
Digit Health. 2024 Jan 17;10:20552076241227132. doi: 10.1177/20552076241227132. eCollection 2024 Jan-Dec.
3
Humor in autism spectrum disorders: A systematic review.
自闭症谱系障碍中的幽默:系统综述。
Encephale. 2024 Apr;50(2):200-210. doi: 10.1016/j.encep.2023.10.002. Epub 2024 Jan 4.
4
Do Large Language Models Know What Humans Know?大语言模型了解人类的知识吗?
Cogn Sci. 2023 Jul;47(7):e13309. doi: 10.1111/cogs.13309.
5
Developing ChatGPT's Theory of Mind.开发ChatGPT的心理理论。
Front Robot AI. 2023 May 30;10:1189525. doi: 10.3389/frobt.2023.1189525. eCollection 2023.
6
An Experimental Study on Sarcasm Comprehension in School Children: The Possible Role of Contextual, Linguistics and Meta-Representative Factors.学龄儿童讽刺理解的实验研究:情境、语言和元表征因素的可能作用
Brain Sci. 2023 May 26;13(6):863. doi: 10.3390/brainsci13060863.
7
Evidence of a predictive coding hierarchy in the human brain listening to speech.人类大脑在听语音时存在预测编码层级的证据。
Nat Hum Behav. 2023 Mar;7(3):430-441. doi: 10.1038/s41562-022-01516-2. Epub 2023 Mar 2.
8
Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models.ChatGPT在美国医师执照考试中的表现:使用大语言模型进行人工智能辅助医学教育的潜力。
PLOS Digit Health. 2023 Feb 9;2(2):e0000198. doi: 10.1371/journal.pdig.0000198. eCollection 2023 Feb.
9
A revisit of the amygdala theory of autism: Twenty years after.自闭症的杏仁核理论再探:二十年后。
Neuropsychologia. 2023 May 3;183:108519. doi: 10.1016/j.neuropsychologia.2023.108519. Epub 2023 Feb 17.
10
Gaze and Motor Traces of Language Processing: Evidence from Autism Spectrum Disorders in Comparison to Typical Controls.语言处理的凝视和运动轨迹:自闭症谱系障碍与典型对照组的比较证据。
Cogn Neuropsychol. 2019 Oct-Dec;36(7-8):383-409. doi: 10.1080/02643294.2019.1652155. Epub 2019 Aug 21.