Controllable Citation Sentence Generation with Language Models

TL;DR

This paper introduces a controllable citation sentence generation method using language models, enabling authors to specify citation intent and keywords, thereby improving citation relevance and customization.

Contribution

It proposes a structured template and fine-tuning approach with reinforcement learning to enhance controllability in citation sentence generation.

Findings

Achieves improved control over citation attributes

Integrates citation attribute suggestion with generation

Uses reinforcement learning for optimization

Abstract

Citation generation aims to generate a citation sentence that refers to a chosen paper in the context of a manuscript. However, a rigid citation generation process is at odds with an author's desire to control specific attributes, such as 1) the citation intent, e.g., either introducing background information or comparing results, and 2) keywords that should appear in the citation text. To provide these degrees of controllability during citation generation, we propose to integrate the manuscript context, the context of the referenced paper, and the desired control attributes into a structured template and use it to fine-tune a language model (LM) via next-token prediction. We then utilize Proximal Policy Optimization to directly optimize the LM in favor of a high score of our proposed controllability metric. The proposed workflow harmoniously combines citation attribute suggestion and conditional citation generation into one LM, allowing for better user control.