Publication

I publish under "Xinliang Frederick Zhang".
* indicates equal contribution.
^ indicates my mentees.
The provision of supplementary materials (e.g., slides, poster) will discontinue since 2027.

2026

  1. arXiv
    TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
    Xinliang Frederick Zhang, and Lu Wang
    Paper
  2. ACL
    Do LLMs Really Need 10+ Thoughts for “find the time 1000 days after today?” Towards Structural Understanding of LLM Overthinking
    Xinliang Frederick Zhang, Anhad Mohananey*, Alexandra Chronopoulou*, Pinelopi Papalampidi, Somit Gupta, Tsendsuren Munkhdalai, Lu Wang, and Shyam Upadhyay
    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics, ACL 2026. (acceptance rate: 19%)
    Paper
  3. ACL-Findings
    Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
    Yunxiang Zhang, Muhammad Khalifa, Lechen Zhang, Xin Liu, Ayoung Lee, Xinliang Frederick Zhang, Farima Fatahi Bayat, and Lu Wang
    In Findings of the Association for Computational Linguistics: ACL 2026. (main conference acceptance rate: 19%, findings acceptance rate: 18%)
    Paper

2025

  1. arXiv
    LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
    Kaijian Zou, Aaron Xiong, Yunxiang Zhang, Xinliang Frederick Zhang, Yueqi Ren, Jirong Yang, Ayoung Lee, Shitanshu Bhushan, and Lu Wang
    Paper Code&Data
  2. IJCNLP-AACL
    FINDR: A Fast Influential Data Selector for NL2Code Pretraining
    Xinliang Frederick Zhang, and Lu Wang
    In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, IJCNLP-AACL 2025. (acceptance rate: 19%)
    Paper Slides Poster Video
  3. EMNLP
    PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process
    Xinliang Frederick Zhang, Nicholas Beauchamp, and Lu Wang
    In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, EMNLP 2025. (acceptance rate: 22.2%)
    Paper Code&Data Slides Poster Video

2024

  1. EMNLP-Findings
    Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted Narratives
    Xinliang Frederick Zhang, Nicholas Beauchamp, and Lu Wang
    In Findings of the Association for Computational Linguistics: EMNLP 2024. (main conference acceptance rate: 20.8%, findings acceptance rate: 16.4%)
    Paper Code&Data Slides Poster Video
  2. ACL-Findings
    ULTRA: Unleashing LLM’s Potential for Event Argument Extraction through Hierarchical Modeling and Pairwise Self-Refinement
    Xinliang Frederick Zhang, Carter Blum, Temma Choji, Shalin Shah, and Alakananda Vempala
    In Findings of the Association for Computational Linguistics: ACL 2024. (main conference acceptance rate: 21.3%, findings acceptance rate: 22.1%)
    Paper Slides Poster Video
  3. NAACL
    MOKA: Moral Knowledge Augmentation for Moral Event Extraction
    Xinliang Frederick Zhang, Winston Wu, Nicholas Beauchamp, and Lu Wang
    In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2024. (acceptance rate: 23.2%)
    Paper Code&Data Slides Poster Video

2023

  1. EMNLP
    All Things Considered: Detecting Partisan Events from News Media with Cross-Article Comparison
    Yujian Liu, Xinliang Frederick Zhang, Kaijian Zou, Ruihong Huang, Nicholas Beauchamp, and Lu Wang
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023. (acceptance rate: 23.3%)
    Paper Slides Poster
  2. EMNLP-Findings
    Crossing the Aisle: Unveiling Partisan and Counter-Partisan Events in News Reporting
    Kaijian Zou, Xinliang Frederick Zhang, Winston Wu, Nicholas Beauchamp, and Lu Wang
    In Findings of the Association for Computational Linguistics: EMNLP 2023. (main conference acceptance rate: 14.0%, findings acceptance rate: 19.5%)
    Paper Data Slides
  3. EMNLP-Findings
    You Are What You Annotate: Towards Better Models through Annotator Representations
    Naihao Deng, Xinliang Frederick Zhang, Siyang Liu, Winston Wu, Lu Wang, and Rada Mihalcea
    In Findings of the Association for Computational Linguistics: EMNLP 2023. (main conference acceptance rate: 23.3%, findings acceptance rate: 22.9%)
    Paper Code&Data Slides Poster

2022

  1. EMNLP
    Generative Entity-to-Entity Stance Detection with Knowledge Graph Augmentation
    Xinliang Frederick Zhang, Nick Beauchamp, and Lu Wang
    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022. (acceptance rate: 20.9%)
    Paper Code&Data Slides Poster Video
  2. EMNLP
    Late Fusion with Triplet Margin Objective for Multimodal Ideology Prediction and Analysis
    Changyuan Qiu*^, Winston Wu*, Xinliang Frederick Zhang, and Lu Wang
    In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022. (acceptance rate: 20.9%)
    Paper Code&Data Slides Poster Video
  3. NAACL-Findings
    POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection
    Xinliang Frederick Zhang*, Yujian Liu*, David Wegsman, Nicholas Beauchamp, and Lu Wang
    In Findings of the Association for Computational Linguistics: NAACL 2022. (main conference acceptance rate: 21.0%, findings acceptance rate: 9.9%)
    Paper Code&Data Demo Slides Poster Video

2021

  1. Thesis
    Towards More Robust Natural Language Understanding
    Xinliang Frederick Zhang
    Committee: Dr. Huan Sun (Chair), Dr. Marie-Catherine de Marneffe
    Undergraduate Research Thesis, The Ohio State University
    Paper
  2. BIBM
    CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering
    Xinliang Frederick Zhang*, Xiang Yue*, Ziyu Yao, Simon M. Lin, and Huan Sun
    In 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), IEEE BIBM 2021. (acceptance rate: 19.6%)
    Best Paper Award
    Paper Code Data Slides Video
  3. EMNLP
    COUGH: A Challenge Dataset and Models for COVID-19 FAQ Retrieval
    Xinliang Frederick Zhang, Heming Sun, Xiang Yue, Simon M. Lin, and Huan Sun
    In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021. (acceptance rate: 17.9%)
    Paper Data Slides Poster Video
  4. NAACL
    Identifying inherent disagreement in natural language inference
    Xinliang Frederick Zhang, and Marie-Catherine de Marneffe
    In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021. (acceptance rate: 22.6%)
    Paper Code&Data Slides Poster Video