Year: 2024
Type: preprint
Abstract: A key challenge in citation text generation is that the length of generated text often differs from the length of the target, lowering the quality of the generation. While prior works have investigated length-controlled generation, their effectiveness depends on knowing the appropriate generation length. In this work, we present an in-depth study of the limitations of predicting scientific citation text length and explore the use of heuristic estimates of desired length.
Source: arXiv (Cornell University)
Authors: Mandal, Biswadip, Li, Xiangci, Ouyang, Jessica
Institution: The University of Texas at Dallas
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4402856950