Improving Citation Text Generation: Overcoming Limitations in Length Control
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 18 references that are in the map. First posted on arXiv 20 Jul 2024.
Builds on
9 of 18 references.
References · 9
- 2020Longformer: The Long-Document Transformercited by 3,362
- 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
- 2017Controllable Abstractive Summarizationcited by 110
- 2016Controlling Output Length in Neural Encoder-Decoderscited by 75
- 2023Evaluating Large Language Models on Controlled Generation Taskscited by 73
- 2019Positional Encoding to Control Output Sequence Lengthcited by 56
- 2019Controlling the Output Length of Neural Machine Translationcited by 36
- 2020Explaining Relationships Between Scientific Documentscited by 35
- 2022CORWA: A Citation-Oriented Related Work Annotation Datasetcited by 17
Built on by
Not cited yet.