Research

• Shape Guides Visual Pretense
  PsyArXiv (2024)
  Peng Qian, Tomer Ullman
  [pdf] [osf]
  
  
• On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe
  ArXiv (2024)
  Ningyu Xu, Qi Zhang, Menghan Zhang, Peng Qian*, Xuanjing Huang*
  [pdf] [code]
  
  
• Comprehenders’ Error Correction Mechanisms are Finely Calibrated to Language Production Statistics
  PsyArXiv (2023)
  Peng Qian, Roger Levy
  [pdf]
  
  
• Ambivalence by Design: A Computational Account of Loopholes
  PsyArXiv (2023)
  Peng Qian, Sophie Bridgers, Maya Taliaferro, Kiera Parece, Tomer Ullman
  [pdf]
  
  
• Skirting the Sacred: Moral Contexts Increase the Cost of Intentional Misunderstandings
  PsyArXiv (2023)
  Kiera Parece, Sophie Bridgers, Peng Qian, Laura Schulz, Tomer Ullman
  [pdf]
  
  
• Comparing the Evaluation and Production of Loophole Behavior in Humans and Large Language Model
  Findings of the Association for Computational Linguistics: EMNLP (2023)
  Sonia Murthy, Kiera Parece, Sophie Bridgers, Peng Qian, Tomer Ullman
  [pdf]
  
  
• Learning Syntactic Structures from String Input
  In Algebraic Structures in Natural Language, CRC Press (2022)
  Ethan Wilcox, Jon Gauthier, Jennifer Hu, Peng Qian, Roger Levy
  
  
• Flexible Generation from Fragmentary Linguistic Input
  In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL 2022)
  Peng Qian, Roger Levy
  [pdf] [code]
  
  
• When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes
  In Proceedings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2022)
  Mycal Tucker, Tiwalayo Eisape, Peng Qian, Roger Levy, Julie Shah
  [pdf] [code]
  
  
• Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language Models
  In Proceedings of 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)
  Yiwen Wang, Jennifer Hu, Roger Levy, Peng Qian
  [pdf] [code]
  
  
• Structural Guidance for Transformer Language Models
  In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL 2021)
  Peng Qian, Tahira Naseem, Roger Levy, Ramón Fernandez Astudillo
  [pdf] [code]
  
  
• What if This Modified That? Syntactic Intervention via Counterfactual Embeddings
  In Findings of ACL (2021)
  Mycal Tucker, Peng Qian, Roger Levy
  [pdf] [code]
  
  
• Structural Supervision Improves Few-shot Learning and Syntactic Generalization in Neural Language Models
  In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
  Ethan Wilcox, Peng Qian, Richard Futrell, Ryosuke Kohita, Roger Levy, Miguel Ballesteros
  [pdf] [code]
  
  
• On the Predictive Power of Neural Language Models for Human Real-time Comprehension Behavior
  In Proceedings of the 42nd Annual Meeting of the Cognitive Science Society (CogSci 2020)
  Ethan Wilcox, Jon Gauthier, Jennifer Hu, Peng Qian, Roger Levy
  [pdf] [code]
  
  
• SyntaxGym: An Online Platform for Targeted Evaluation of Language Models
  In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL 2020)
  Jon Gauthier, Jennifer Hu, Ethan Wilcox, Peng Qian, Roger Levy
  [pdf] [code]
  
  
• A Systematic Assessment of Syntactic Generalization in Neural Language Models
  In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL 2020)
  Jennifer Hu, Jon Gauthier, Peng Qian, Ethan Wilcox, Roger Levy
  [pdf] [code]
  
  
• Composition is the Core Driver of the Language-selective Network
  In Neurobiology of Language (2020)
  Francis Mollica, Matthew Siegelman, Evgeniia Diachek, Steven T. Piantadosi, Zachary Mineroff, Richard Futrell, Hope Kean, Peng Qian, Evelina Fedorenko
  [pdf] [code]
  
  
• Representation of Constituents in Neural Language Models: Coordination Phrase as a Case Study
  In Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019)
  Aixiu An, Peng Qian, Ethan Wilcox, Roger Levy
  [pdf] [code]
  
  
• Inferring Structured Visual Concepts from Minimal Data
  In Proceedings of the 41st Annual Meeting of the Cognitive Science Society (CogSci 2019)
  Peng Qian, Luke Hewitt, Joshua B. Tenenbaum, Roger Levy
  [pdf]
  
  
• Syntactic Dependencies Correspond to Word Pairs with High Mutual Information
  In Proceedings of the Fifth International Conference on Dependency Linguistics (DepLing 2019)
  Richard Futrell, Peng Qian, Edward Gibson, Evelina Fedorenko, Idan Blank
  [pdf] [code]
  
  
• Structural Supervision Improves Learning of Non-local Grammatical Dependencies
  In Proceedings of the 18th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2019)
  Ethan Wilcox, Peng Qian, Richard Futrell, Miguel Ballesteros, Roger Levy
  [pdf]
  
  
• Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
  In Proceedings of the 18th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2019)
  Richard Futrell, Ethan Wilcox, Takashi Morita, Peng Qian, Miguel Ballesteros, Roger Levy
  [pdf] [code]
  
  
• Analyzing Linguistic Knowledge in Sequential Model of Sentence
  In Proceedings of 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP 2016)
  Peng Qian, Xipeng Qiu, Xuanjing Huang
  [pdf]
  
  
• Investigating Language Universal and Specific Properties in Word Embeddings
  In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL 2016)
  Peng Qian, Xipeng Qiu, Xuanjing Huang
  [pdf]
  
  
• A New Psychometric-inspired Evaluation Metric for Chinese Word Segmentation
  In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL 2016)
  Peng Qian, Xipeng Qiu, Xuanjing Huang
  [pdf]
  
  
• Bridging LSTM Architecture and the Neural Dynamics during Reading
  In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI 2016)
  Peng Qian, Xipeng Qiu, Xuanjing Huang
  [pdf]