DLCLJul 20, 2024

Improving Citation Text Generation: Overcoming Limitations in Length Control

arXiv:2407.14997v1h-index: 9
Originality Synthesis-oriented
AI Analysis

This addresses a specific issue in citation text generation for researchers, but appears incremental as it builds on prior length control methods.

The paper tackled the problem of generating citation text with mismatched lengths by studying limitations in length prediction and exploring heuristic length estimates, but did not report concrete numerical results.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes