Search Results for author:
Found 5 papers, 2 papers with code
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation
Compositional generalization, representing the model's ability to generate text with new attribute combinations obtained by recombining single attributes from the training data, is a crucial property for multi-aspect controllable text generation (MCTG) methods.
Understanding and Patching Compositional Reasoning in LLMs
LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
Invariant Representation via Decoupling Style and Spurious Features from Images
This paper considers the out-of-distribution (OOD) generalization problem under the setting that both style distribution shift and spurious features exist and domain labels are missing.
Evolutionary Curriculum Training for DRL-Based Navigation Systems
Additionally, an evolutionary training environment generates all the curriculum to improve the DRL model's inadequate skills tested in the previous evaluation.
Learning to Substitute Spans towards Improving Compositional Generalization
Despite the rising prevalence of neural sequence models, recent empirical evidences suggest their deficiency in compositional generalization.
