Research & Publications

Recent Projects

Sentence Boundaries and Language-Model Reasoning

Ongoing

We study how explicit sentence structure shapes reasoning, generation organization, and capability boundaries in language models.

Generated-Text Detection and Quality Evaluation

Ongoing

We use spectral, statistical, and psycholinguistic signals to identify machine-generated text and evaluate generation quality.

Model Memory and Lifelong Learning

Exploring

We study how language models store, forget, and update information, and how old and new knowledge interact in continual settings.

Language, Cognition, and Human Preference

Long-term

We connect computational models, psycholinguistics, and behavioral experiments to compare human and machine language understanding.

Publications

2026

Teaching LLMs to Abstain via Fine-Grained Semantic Confidence Reward

Hao An, Yang Xu

Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026, Main Conference)

Evaluating Memory Capability in Continuous Lifelog Scenario

Jianjie Zheng, Zhichen Liu, Zhanyu Shen, Jingxiang Qu, Guanhua Chen, Yile Wang, Yang Xu, Yang Liu, Sijie Cheng

Findings of the Association for Computational Linguistics: ACL 2026 (accepted; CCF-A)

Eye Movement Features Can Predict Human Preferences on Machine-Generated Texts

Xiaoshan He, Xiaoqun Liu, Haodong He, Yu Wang, Yang Xu

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop) (accepted)

Identifying the Periodicity of Information in Natural Language

Yulin Ou, Yu Wang, Yang Xu, Hendrik Buschmeier

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) (accepted; CCF-A)

Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models

Yu Wang, Leyi Lao, Langchu Huang, Gabriel Skantze, Yang Xu, Hendrik Buschmeier

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) (accepted; oral; CCF-A)

Purging the Gray Zone: Latent-Geometric Denoising for Precise Knowledge Boundary Awareness

Hao An, Yibin Lou, Jiayi Guo, Yang Xu

Findings of the Association for Computational Linguistics: ACL 2026 (accepted; CCF-A)

Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities

Zhichen Liu, Yongyuan Li, Yang Xu

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) (accepted; oral; CCF-A)

WaveDetect: Robust Framework for Machine-Generated Text Detection via Wavelet Transform

Zhichen Liu, Kaitong Qin, Linhan He, Yang Xu

Findings of the Association for Computational Linguistics: ACL 2026 (accepted; CCF-A)

2025

Evaluating Text Generation Quality Using Spectral Distances of Surprisal

Zhichen Liu, Yongyuan Li, Yang Xu, Yu Wang, Yingfang Yuan, Zuhao Yang

Findings of the Association for Computational Linguistics: EMNLP 2025

Reasoning for Translation: Comparative Analysis of Chain-of-Thought and Tree-of-Thought Prompting for LLM Translation

Lam Nguyen, Yang Xu

ACL Student Research Workshop 2025 (Oral)

ReChar: Revitalising Characters with Structure Preserved and User-Specified Aesthetic Enhancements

Zhongyu Yang, Junhao Song, Zhang Luo, Zuhao Yang, Yang Xu, Jingfen Lan, Yonghan Zhang, Wei Pang, Siyang Song, Yingfang Yuan

Proceedings of the SIGGRAPH Asia 2025 Technical Communications

2024

Detecting Subtle Differences between Human and Model Languages Using Spectrum of Relative Likelihood

Yang Xu, Yu Wang, Hao An, Zhichen Liu, Yongyuan Li

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)

How Much Does Nonverbal Communication Conform to Entropy Rate Constancy?: A Case Study on Listener Gaze in Interaction

Yu Wang, Yang Xu, Gabriel Skantze, Hendrik Buschmeier

Findings of the Association for Computational Linguistics: ACL 2024

2023

FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy

Zuhao Yang, Yingfang Yuan, Yang Xu, Shuo Zhan, Huajun Bai, Kefan Chen

Advances in Neural Information Processing Systems 36 (NeurIPS 2023)

Spontaneous gestures encoded by hand positions improve language models: An Information-Theoretic motivated study

Yang Xu, Yang Cheng

Findings of the Association for Computational Linguistics: ACL 2023

2022

Gestures Are Used Rationally: Information Theoretic Evidence from Neural Sequential Models

Yang Xu, Yang Cheng, Riya Bhatia

Proceedings of the 29th International Conference on Computational Linguistics (COLING 2022)

Hierarchical data visualization of experimental erythrocyte aggregation employing cross correlation and optical flow applications

Bruce I. Gaynes, Mark B. Shapiro, Abel Saju Augustine, Yang Xu, ..., Jie Xu

Microvascular Research

2021

Global divergence and local convergence of utterance semantic representations in dialogue

Yang Xu

Proceedings of the Society for Computation in Linguistics (SCiL 2021)

Historical changes in semantic weights of sub-word units

Yang Xu, Zheng-sheng Zhang

Computational Approaches to Semantic Change (Book Chapter)

2020

Which Sentence Embeddings and Which Layers Encode Syntactic Structure?

M. A. Kelly, Yang Xu, Jesús Calvillo, David Reiter

Proceedings of the 42nd Annual Conference of the Cognitive Science Society (CogSci 2020, full paper)

2019

Linguistic alignment is affected more by lexical surprisal rather than social power

Yang Xu, Jeremy Cole, David Reiter

Proceedings of the Society for Computation in Linguistics (SCiL 2019)

Subword Embeddings Reveal Language Change

Yang Xu, Jeremy Cole, David Reiter

Proceedings of the 41st Annual Meeting of the Cognitive Science Society (CogSci 2019, poster presentation)

Treat the Word As a Whole or Look Inside? Subword Embeddings Model Language Change and Typology

Yang Xu, Jiasheng Zhang, David Reiter

Workshop of LChange 2019 (colocated at ACL 2019)

2018

Information density converges in dialogue: Towards an information-theoretic model

Yang Xu, David Reiter

Cognition (journal paper)

Not that much power: Linguistic alignment is influenced more by low-level linguistic features rather than social power

Yang Xu, Jeremy Cole, David Reiter

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018)

2017

Spectral analysis of information density in dialogue predicts collaborative task performance

Yang Xu, David Reiter

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017)

2016

Convergence of syntactic complexity in conversation

Yang Xu, David Reiter

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016, short paper)

Entropy converges between dialogue participants: Explanations from an information-theoretic perspective

Yang Xu, David Reitter

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016)

2015

An evaluation and comparison of linguistic alignment measures

Yang Xu, David Reiter

Proceedings of Proceedings of Cognitive Modeling and Computational Linguistics (CMCL 2015, colocated at NAACL 2015)

Error-correction and aggregation in crowd-sourcing of geopolitical incident information

Alexander G. Ororbia II, Yang Xu, David Reiter

Social Computing, Behavioral Modeling and Prediction (SBP 2015)