Weihua Luo

KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation

2021 · arXiv (Cornell University)

Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. However, existing models cannot perform as well as humans, since sentences they produce are …

Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models

2025 · arXiv (Cornell University)

Multi-aspect controllable text generation aims to control text generation in attributes from multiple aspects, making it a complex but powerful task in natural language processing. Supervised fine-tuning methods are often employed for this task due …