Comparable Demonstrations Are Important In In-Context Learning: A Novel Perspective On Demonstration Selection.

Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis.

Improving the out-of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enough.

Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding.

MTR: A Dataset Fusing Inductive, Deductive, and Defeasible Reasoning.

Latent Constraints on Unsupervised Text-Graph Alignment with Information Asymmetry.

Preference-Controlled Multi-Objective Reinforcement Learning for Conditional Text Generation.

To What Extent Do Natural Language Understanding Datasets Correlate to Logical Reasoning? A Method for Diagnosing Logical Reasoning.

MaxGNR: A Dynamic Weight Strategy via Maximizing Gradient-to-Noise Ratio for Multi-task Learning.

Dependent Multi-Task Learning with Causal Intervention for Image Captioning.