Publications

Full list on Google Scholar. Bold marks me; entries are sorted by year, most recent first.

2026
  1. Detecting Contextual Hallucinations in Large Language Models with Frequency-Aware Attention
    S Qi, Y Chen, R Zhao, Q Zhu, Z Hu, W Liu, Y He, Z Yuan, L Gui. ICML 2026, 2026. PDF
  2. HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices
    W Liu, S Qi, L Zhang, L Tudor Car, Y He. EMNLP 2026 (System Demonstrations), 2026. PDF Code
  3. Position: Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain
    W Liu, S Qi, Y Du, Y He. ICML 2026 (Position Paper Track), 2026. PDF
2025
  1. NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
    W Liu, S Qi, X Wang, C Qian, Y Du, Y He. EMNLP 2025, 2025. PDF
  2. EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States
    H Xu, S Qi, J Li, Y Zhou, J Du, C Catmur, Y He. Findings of ACL 2025, 2025. PDF
  3. Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases
    R Gao, X Wu, T Kuribayashi, M Ye, S Qi, C Roever, Y Liu, Z Yuan, JH Lau. ACL 2025, 2025. PDF
2024
2022
  1. SAPGraph: Structure-aware extractive summarization for scientific papers with heterogeneous graph
    S Qi, L Li, Y Li, J Jiang, D Hu, Y Li, Y Zhu, Y Zhou, M Litvak, N Vanetik. AACL-IJCNLP 2022, 2022. PDF
2021
  1. Subjective bias in abstractive summarization
    L Li, W Liu, M Litvak, N Vanetik, J Pei, Y Liu, S Qi. arXiv preprint, 2021. PDF
2020
  1. CIST@CL-SciSumm 2020, LongSumm 2020: Automatic scientific document summarization
    L Li, Y Xie, W Liu, Y Liu, Y Jiang, S Qi, X Li. SDP Workshop @ EMNLP 2020, 2020. PDF

Preprints are listed with their arXiv identifiers; peer-reviewed venues are shown in their published form.