Yunhao Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yunhao Zhang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Shaonan Wang
State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS Beijing China
7 shared publications - Chengqing Zong
Institute of Automation, Chinese Academy of Sciences
6 shared publications Chong Li
State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS Beijing China
4 shared publicationsXinyi Dong
State Key Laboratory of Cognitive Neuroscience and Learning Beijing Normal University
3 shared publications- Jiajun Zhang
School of Artificial Intelligence University of Chinese Academy of Sciences
2 shared publications - Jingyuan Sun
KU Leuven KU Leuven National University of Singapore Chinese Academy of Science Chinese Academy of Science KU Leuven
2 shared publications
Latest Publications
- Open Access
Component-Level Lesioning of Language Models Reveals Clinically Aligned Aphasia Phenotypes
Large language models (LLMs) increasingly exhibit human-like linguistic behaviors and internal representations that they could serve as computational simulators of language cognition. We ask whether LLMs can be systematically manipulated to reproduce language-production impairments characteristic of aphasia following focal brain lesions. Such models could provide scalable proxies for testing rehabilitation hypotheses, and offer a controlled framework for probing the functional organization of language. We introduce a clinically grounded, component-level framework that simulates aphasia by selectively perturbing functional components in LLMs, and apply it to both modular Mixture-of-Experts models and dense Transformers using a unified intervention interface. Our pipeline (i) identifies subtype-linked components for Broca's and Wernicke's aphasia, (ii) interprets these components with linguistic probing tasks, and (iii) induces graded impairments by progressively perturbing the top-k subtype-linked components, evaluating outcomes with Western Aphasia Battery (WAB) subtests summarized by Aphasia Quotient (AQ). Across architectures and lesioning strategies, subtype-targeted perturbations yield more systematic, aphasia-like regressions than size-matched random perturbations, and MoE modularity supports more localized and interpretable phenotype-to-component mappings. These findings suggest that modular LLMs, combined with clinically informed component perturbations, provide a promising platform for simulating aphasic language production and studying how distinct language functions degrade under targeted disruptions.
Open AccessComponent-Level Lesioning of Language Models Reveals Clinically Aligned Aphasia Phenotypes
Large language models (LLMs) increasingly exhibit human-like linguistic behaviors and internal representations that they could serve as computational simulators of language cognition. We ask whether LLMs can be systematically manipulated to reproduce language-production impairments characteristic of aphasia following focal brain lesions. Such models could provide scalable proxies for testing rehabilitation hypotheses, and offer a controlled framework for probing the functional organization of language. We introduce a clinically grounded, component-level framework that simulates aphasia by selectively perturbing functional components in LLMs, and apply it to both modular Mixture-of-Experts models and dense Transformers using a unified intervention interface. Our pipeline (i) identifies subtype-linked components for Broca's and Wernicke's aphasia, (ii) interprets these components with linguistic probing tasks, and (iii) induces graded impairments by progressively perturbing the top-k subtype-linked components, evaluating outcomes with Western Aphasia Battery (WAB) subtests summarized by Aphasia Quotient (AQ). Across architectures and lesioning strategies, subtype-targeted perturbations yield more systematic, aphasia-like regressions than size-matched random perturbations, and MoE modularity supports more localized and interpretable phenotype-to-component mappings. These findings suggest that modular LLMs, combined with clinically informed component perturbations, provide a promising platform for simulating aphasic language production and studying how distinct language functions degrade under targeted disruptions.
- 30 May 2025
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (3) , 3005-3028
MulCogBench: a multi-modal cognitive benchmark dataset for evaluating Chinese and English computational language models
- 30 May 2025
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (3) , 3005-3028
MulCogBench: a multi-modal cognitive benchmark dataset for evaluating Chinese and English computational language models
- Open Access
How Syntax Specialization Emerges in Language Models
Large language models (LLMs) have been found to develop surprising internal specializations: Individual neurons, attention heads, and circuits become selectively sensitive to syntactic structure, reflecting patterns observed in the human brain. While this specialization is well-documented, how it emerges during training and what influences its development remains largely unknown. In this work, we tap into the black box of specialization by tracking its formation over time. By quantifying internal syntactic consistency across minimal pairs from various syntactic phenomena, we identify a clear developmental trajectory: Syntactic sensitivity emerges gradually, concentrates in specific layers, and exhibits a 'critical period' of rapid internal specialization. This process is consistent across architectures and initialization parameters (e.g., random seeds), and is influenced by model scale and training data. We therefore reveal not only where syntax arises in LLMs but also how some models internalize it during training. To support future research, we will release the code, models, and training checkpoints upon acceptance.
Open AccessHow Syntax Specialization Emerges in Language Models
Large language models (LLMs) have been found to develop surprising internal specializations: Individual neurons, attention heads, and circuits become selectively sensitive to syntactic structure, reflecting patterns observed in the human brain. While this specialization is well-documented, how it emerges during training and what influences its development remains largely unknown. In this work, we tap into the black box of specialization by tracking its formation over time. By quantifying internal syntactic consistency across minimal pairs from various syntactic phenomena, we identify a clear developmental trajectory: Syntactic sensitivity emerges gradually, concentrates in specific layers, and exhibits a 'critical period' of rapid internal specialization. This process is consistent across architectures and initialization parameters (e.g., random seeds), and is influenced by model scale and training data. We therefore reveal not only where syntax arises in LLMs but also how some models internalize it during training. To support future research, we will release the code, models, and training checkpoints upon acceptance.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 6127-6144
Discovering Semantic Subdimensions through Disentangled Conceptual Representations
Yunhao Zhang, Shaonan Wang, Nan Lin, Xinyi Dong, Chong Li, Chengqing Zong. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 6127-6144
Open AccessDiscovering Semantic Subdimensions through Disentangled Conceptual Representations
Yunhao Zhang, Shaonan Wang, Nan Lin, Xinyi Dong, Chong Li, Chengqing Zong. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
Navigating Brain Language Representations: A Comparative Analysis of Neural Language Models and Psychologically Plausible Models
Neural language models, particularly large-scale ones, have been consistently proven to be most effective in predicting brain neural activity across a range of studies. However, previous research overlooked the comparison of these models with psychologically plausible ones. Moreover, evaluations were reliant on limited, single-modality, and English cognitive datasets. To address these questions, we conducted an analysis comparing encoding performance of various neural language models and psychologically plausible models. Our study utilized extensive multi-modal cognitive datasets, examining bilingual word and discourse levels. Surprisingly, our findings revealed that psychologically plausible models outperformed neural language models across diverse contexts, encompassing different modalities such as fMRI and eye-tracking, and spanning languages from English to Chinese. Among psychologically plausible models, the one incorporating embodied information emerged as particularly exceptional. This model demonstrated superior performance at both word and discourse levels, exhibiting robust prediction of brain activation across numerous regions in both English and Chinese.
Open AccessNavigating Brain Language Representations: A Comparative Analysis of Neural Language Models and Psychologically Plausible Models
Neural language models, particularly large-scale ones, have been consistently proven to be most effective in predicting brain neural activity across a range of studies. However, previous research overlooked the comparison of these models with psychologically plausible ones. Moreover, evaluations were reliant on limited, single-modality, and English cognitive datasets. To address these questions, we conducted an analysis comparing encoding performance of various neural language models and psychologically plausible models. Our study utilized extensive multi-modal cognitive datasets, examining bilingual word and discourse levels. Surprisingly, our findings revealed that psychologically plausible models outperformed neural language models across diverse contexts, encompassing different modalities such as fMRI and eye-tracking, and spanning languages from English to Chinese. Among psychologically plausible models, the one incorporating embodied information emerged as particularly exceptional. This model demonstrated superior performance at both word and discourse levels, exhibiting robust prediction of brain activation across numerous regions in both English and Chinese.
- Open Access
Computational Models to Study Language Processing in the Human Brain: A Survey
Despite differing from the human language processing mechanism in implementation and algorithms, current language models demonstrate remarkable human-like or surpassing language capabilities. Should computational language models be employed in studying the brain, and if so, when and how? To delve into this topic, this paper reviews efforts in using computational models for brain research, highlighting emerging trends. To ensure a fair comparison, the paper evaluates various computational models using consistent metrics on the same dataset. Our analysis reveals that no single model outperforms others on all datasets, underscoring the need for rich testing datasets and rigid experimental control to draw robust conclusions in studies involving computational models.
Open AccessComputational Models to Study Language Processing in the Human Brain: A Survey
Despite differing from the human language processing mechanism in implementation and algorithms, current language models demonstrate remarkable human-like or surpassing language capabilities. Should computational language models be employed in studying the brain, and if so, when and how? To delve into this topic, this paper reviews efforts in using computational models for brain research, highlighting emerging trends. To ensure a fair comparison, the paper evaluates various computational models using consistent metrics on the same dataset. Our analysis reveals that no single model outperforms others on all datasets, underscoring the need for rich testing datasets and rigid experimental control to draw robust conclusions in studies involving computational models.
- Open Access
Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities
Decoding visual stimuli from neural responses recorded by functional Magnetic Resonance Imaging (fMRI) presents an intriguing intersection between cognitive neuroscience and machine learning, promising advancements in understanding human visual perception and building non-invasive brain-machine interfaces. However, the task is challenging due to the noisy nature of fMRI signals and the intricate pattern of brain visual representations. To mitigate these challenges, we introduce a two-phase fMRI representation learning framework. The first phase pre-trains an fMRI feature learner with a proposed Double-contrastive Mask Auto-encoder to learn denoised representations. The second phase tunes the feature learner to attend to neural activation patterns most informative for visual reconstruction with guidance from an image auto-encoder. The optimized fMRI feature learner then conditions a latent diffusion model to reconstruct image stimuli from brain activities. Experimental results demonstrate our model's superiority in generating high-resolution and semantically accurate images, substantially exceeding previous state-of-the-art methods by 39.34% in the 50-way-top-1 semantic classification accuracy. Our research invites further exploration of the decoding task's potential and contributes to the development of non-invasive brain-machine interfaces.
Open AccessContrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities
Decoding visual stimuli from neural responses recorded by functional Magnetic Resonance Imaging (fMRI) presents an intriguing intersection between cognitive neuroscience and machine learning, promising advancements in understanding human visual perception and building non-invasive brain-machine interfaces. However, the task is challenging due to the noisy nature of fMRI signals and the intricate pattern of brain visual representations. To mitigate these challenges, we introduce a two-phase fMRI representation learning framework. The first phase pre-trains an fMRI feature learner with a proposed Double-contrastive Mask Auto-encoder to learn denoised representations. The second phase tunes the feature learner to attend to neural activation patterns most informative for visual reconstruction with guidance from an image auto-encoder. The optimized fMRI feature learner then conditions a latent diffusion model to reconstruct image stimuli from brain activities. Experimental results demonstrate our model's superiority in generating high-resolution and semantically accurate images, substantially exceeding previous state-of-the-art methods by 39.34% in the 50-way-top-1 semantic classification accuracy. Our research invites further exploration of the decoding task's potential and contributes to the development of non-invasive brain-machine interfaces.
- Open Access
Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning
Transformer-based models, even though achieving super-human performance on several downstream tasks, are often regarded as a black box and used as a whole. It is still unclear what mechanisms they have learned, especially their core module: multi-head attention. Inspired by functional specialization in the human brain, which helps to efficiently handle multiple tasks, this work attempts to figure out whether the multi-head attention module will evolve similar function separation under multi-tasking training. If it is, can this mechanism further improve the model performance? To investigate these questions, we introduce an interpreting method to quantify the degree of functional specialization in multi-head attention. We further propose a simple multi-task training method to increase functional specialization and mitigate negative information transfer in multi-task learning. Experimental results on seven pre-trained transformer models have demonstrated that multi-head attention does evolve functional specialization phenomenon after multi-task training which is affected by the similarity of tasks. Moreover, the multi-task training strategy based on functional specialization boosts performance in both multi-task learning and transfer learning without adding any parameters.
Open AccessInterpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning
Transformer-based models, even though achieving super-human performance on several downstream tasks, are often regarded as a black box and used as a whole. It is still unclear what mechanisms they have learned, especially their core module: multi-head attention. Inspired by functional specialization in the human brain, which helps to efficiently handle multiple tasks, this work attempts to figure out whether the multi-head attention module will evolve similar function separation under multi-tasking training. If it is, can this mechanism further improve the model performance? To investigate these questions, we introduce an interpreting method to quantify the degree of functional specialization in multi-head attention. We further propose a simple multi-task training method to increase functional specialization and mitigate negative information transfer in multi-task learning. Experimental results on seven pre-trained transformer models have demonstrated that multi-head attention does evolve functional specialization phenomenon after multi-task training which is affected by the similarity of tasks. Moreover, the multi-task training strategy based on functional specialization boosts performance in both multi-task learning and transfer learning without adding any parameters.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 233-241
A Comprehensive Neural and Behavioral Task Taxonomy Method for Transfer Learning in NLP
Yunhao Zhang, Chong Li, Xiaohan Zhang, Xinyi Dong, Shaonan Wang. Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 233-241
Open AccessA Comprehensive Neural and Behavioral Task Taxonomy Method for Transfer Learning in NLP
Yunhao Zhang, Chong Li, Xiaohan Zhang, Xinyi Dong, Shaonan Wang. Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings). 2023.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 16460-16476
Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning
Chong Li, Shaonan Wang, Yunhao Zhang, Jiajun Zhang, Chengqing Zong. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 16460-16476
Open AccessInterpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning
Chong Li, Shaonan Wang, Yunhao Zhang, Jiajun Zhang, Chengqing Zong. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.