Improving Citation Text Generation: Overcoming Limitations in Length Control

TL;DR

This paper investigates the challenges of controlling the length of generated citation texts, highlighting limitations in length prediction and proposing heuristic estimates to improve generation quality.

Contribution

It provides an in-depth analysis of length prediction issues in citation text generation and explores heuristic methods to better control output length.

Findings

Length prediction is a key challenge in citation generation.

Heuristic estimates can improve length control.

Limitations in current methods affect generation quality.

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.