arXiv:2406.11338
Fine-grained Controllable Text Generation through In-context Learning with Feedback
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Mitigating Object Hallucinations via Sentence-Level Early Intervention
Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques
The Reader is the Metric: How Textual Features and Reader Profiles Explain Conflicting Evaluations of AI Creative Writing
Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport
Factors affecting the in-context learning abilities of LLMs for dialogue state tracking
EEG2TEXT-CN: An Exploratory Study of Open-Vocabulary Chinese Text-EEG Alignment via Large Language Model and Contrastive Learning on ChineseEEG
토론
이 논문과 연결된 포럼 글이 아직 없습니다.