Publications

Hang Chen, Jiaying Zhu, Xinyu Yang, Wenya Wang (2026). CLUE: Conflict-guided Localization for LLM Unlearning Framework. ICLR.

Hang Chen, Xinyu Yang, Jiaying Zhu, Wenya Wang (2026). Skill Path: Unveiling Language Skills from Circuit Graphs. AAAI (Oral).

Hang Chen, Jiaying Zhu, Xinyu Yang, Wenya Wang (2025). Rethinking Circuit Completeness in Language Models: AND, OR, and ADDER Gates. Neurips.

Hang Chen, Xinyu Yang, Keqing Du (2025). Towards Causal Relationship in indefinite data: New Datasets and Baseline Model. DMLR.

Keqing Du, Xinyu Yang, Hang Chen (2025). CASR: Refining Action Segmentation via marginalizing frame-level causal relationships. TMM.

Hang Chen, Xinyu Yang, Jiaying Zhu, Wenya Wang (2025). Quantifying Semantic Emergence in Language Models. ACL 2025 (main).

Daiying Zhao, Xinyu Yang, Hang Chen (2025). Debiasing the Fine-Grained Classification Task in LLMs with Bias-Aware PEFT. ACL 2025 (main).

Hang Chen , Bingyu Liao , Jing Luo , Wenjing Zhu , and Xinyu Yang (2024). Learning a Structural Causal Model for Intuition Reasoning in Conversation. TKDE.

Hang Chen, Xinyu Yang, Jing Luo, Wenjing Zhu (2023). How to enhance causal discrimination of utterances: A case on affective reasoning. EMNLP 2023 (main).

Hang Chen, Xinyu Yang, Keqing Du, Wenya Wang (2019). Ssl framework for causal inconsistency between structures and representations.