paper-with-me

홈 › Papers

Fine-grained Controllable Text Generation through In-context Learning with Feedback

2024-06-17 · Sarubi Thillainathan, Alexander Koller

We present a method for rewriting an input sentence to match specific values of nontrivial linguistic features, such as dependency depth. In contrast to earlier work, our method uses in-context learning rather than finetuning, making it applicable in use cases where data is sparse. We show that our model performs accurate rewrites and matches the state of the art on rewriting sentences to a specified school grade level.

📄 PDF Abstract BibTeX arXiv:2406.11338

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context LearningSentenceText Generation

Similar Papers 제목 키워드 기반

Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events

2021-01-04 · Le Fang, Tao Zeng, Chaochun Liu, Liefeng Bo 외

Large-scale pretrained language models have shown thrilling generation capabilities, especially when they generate consistent long text in thousands of words with ease. However, users of these models can only control the…

Keyword ExtractionLanguage ModelingLanguage ModellingStory Generation+1

StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer

2021-04-12 · NAACL 2021 4 · Yiwei Lyu, Paul Pu Liang, Hai Pham, Eduard Hovy 외

Text style transfer aims to controllably generate text with targeted stylistic changes while maintaining core meaning from the source sentence constant. Many of the existing style transfer benchmarks primarily focus on i…

BenchmarkingSentenceStyle TransferText Generation+1

ACMo: Attribute Controllable Motion Generation

2025-03-14 · Mingjie Wei, Xuemei Xie, Guangming Shi

Attributes such as style, fine-grained text, and trajectory are specific conditions for describing motion. However, existing methods often lack precise user control over motion attributes and suffer from limited generali…

AttributeMotion Generation

ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models

2024-07-28 · Peiming Li, Ziyi Wang, Mengyuan Liu, Hong Liu 외

Grasp generation aims to create complex hand-object interactions with a specified object. While traditional approaches for hand generation have primarily focused on visibility and diversity under scene constraints, they …

Controllable Grasp GenerationGrasp GenerationObject

Fine-grained Controllable Video Generation via Object Appearance and Context

2023-12-05 · Hsin-Ping Huang, Yu-Chuan Su, Deqing Sun, Lu Jiang 외

Text-to-video generation has shown promising results. However, by taking only natural languages as input, users often face difficulties in providing detailed information to precisely control the model's output. In this w…

Text-to-Video GenerationVideo Generation