← Search

Renlong Jie

2 accepted papers

2024

Prompt-Based Length Controlled Generation with Multiple Control Types

ACL 2024findings

Large language models (LLMs) have attracted great attention given their strong performance on a wide range of NLP tasks. In practice, users often expect generated texts to fall within a specific length range, making length controlled generation an important topic, especially for GPT-style models. Ex…

Cited by 7SourcePDFScholar
2024

Unsupervised Extractive Summarization with Learnable Length Control Strategies

AAAI 2024technical

Unsupervised extractive summarization is an important technique in information extraction and retrieval. Compared with supervised method, it does not require high-quality human-labelled summaries for training and thus can be easily applied for documents with different types, domains or languages. Mo…

Cited by 3SourcePDFScholar