scholar.google.com › citations
Oct 18, 2024 · We propose a lightweight MCTG pipeline based on data augmentation. We analyze bias and correlations in traditional datasets, and address these concerns.
Oct 18, 2024 · We propose a lightweight MCTG pipeline based on data augmentation. We analyze bias and correlations in traditional datasets, and address these concerns with ...
Oct 23, 2024 · Large language models (LLMs) show remarkable abilities with instruction tuning. However, they fail to achieve ideal tasks when lacking ...
Aug 26, 2024 · This paper aims to provide valuable insights and guidance for researchers and developers working in the field of Controllable Text Generation.
[PDF] Multi-Aspect Controllable Text Generation with Disentangled ...
www.semanticscholar.org › paper
A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models. Chenyang ZhangJiayi Lin +4 authors. Junli Wang. Computer Science. 2024.
A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models · no code implementations • 18 Oct 2024 • Chenyang Zhang, Jiayi Lin ...
Dec 6, 2023 · Multi-aspect controllable text generation aims to generate fluent sentences that possess mul- tiple desired attributes simultaneously.
Missing: Solution | Show results with:Solution
A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models ... Augmented datasets are feasible for instruction tuning. Paper
Nov 21, 2024 · The key methods are discussed, including model retraining, fine-tuning, reinforcement learning, prompt engineering, latent space manipulation, ...
May 26, 2024 · This paper introduces a new framework called Dynamic Attribute Graphs-based controlled text generation (DATG) for producing text with ...