Selected Publications

Computational Pragmatics

• B. Chen, X. Chen, H. Zi, X. Zhang, K. Johnson, G. Liu. Enhancing Moral Diagnosis and Correction in Large Language Models. ArXiv 2026. [PDF]
• G. Liu, X. Chen, B. Chen, H. Zi, X. Zhang, K. Johnson. Pragmatic Inference for Moral Reasoning Acquisition: Generalization via Metapragmatic Links. ArXiv 2025. [PDF]
• G. Liu, Z. Qi, X. Zhang, L. Jiang, K. M. Johnson. Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization. EMNLP 2025. [PDF]

Machine Morality

• G. Liu, Z. Qi, X. Zhang, K. M. Johnson. Discourse Heuristics for Paradoxically Moral Self-Correction. EMNLP 2025. [PDF]
• G. Liu, Z. Qi, X. Zhang, L. Cheng, K. Johnson. Moral Self-Correction is Not An Innate Capability in Language Models. AACL 2025. [PDF]
• G. Liu, H. Mao, B. Cao, X. Zhang, Z. Xue, R. Wang, K. Johnson. On the Convergence of Moral Self-Correction in Large Language Models. AACL 2025. [PDF]
• G. Liu, H. Mao, J. Tang, K. Johnson. Intrinsic Self-Correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis. EMNLP 2024. [PDF]

Statistical Learning Theory

• G. Liu, M. Afshari, X. Zhang, Z. Xue, A. Ghosh, B. Bashyal, R. Wang, et al. Towards Understanding Task-Agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness. ACL 2024. [PDF]
• X. Zhang, A. Ghosh, G. Liu, R. Wang. Improving Generalization of Complex Models under Unbounded Loss using PAC-Bayes Bounds. TMLR 2023. [PDF]
• G. Liu, Z. Xue, X. Zhang, K. Johnson, R. Wang. PAC-tuning: Fine-tuning Pre-trained Language Models with PAC-driven Perturbed Gradient Descent. EMNLP 2023. [PDF]