How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study

TL;DR

This paper systematically evaluates how different types of out-of-distribution scenarios affect the performance of language models in computational argumentation, highlighting the varying effectiveness of in-context learning and fine-tuning methods.

Contribution

It provides a comprehensive, fine-grained analysis of OOD challenges in computational argumentation, addressing topic, domain, and language shifts, and compares different LM adaptation techniques.

Findings

ICL performs well for domain shifts

Prompt-based fine-tuning is better for topic shifts

Base-sized LMs show potential in OOD scenarios

Abstract

The advent of pre-trained Language Models (LMs) has markedly advanced natural language processing, but their efficacy in out-of-distribution (OOD) scenarios remains a significant challenge. Computational argumentation (CA), modeling human argumentation processes, is a field notably impacted by these challenges because complex annotation schemes and high annotation costs naturally lead to resources barely covering the multiplicity of available text sources and topics. Due to this data scarcity, generalization to data from uncovered covariant distributions is a common challenge for CA tasks like stance detection or argument classification. This work systematically assesses LMs' capabilities for such OOD scenarios. While previous work targets specific OOD types like topic shifts or OOD uniformly, we address three prevalent OOD scenarios in CA: topic shift, domain shift, and language shift. Our findings challenge the previously asserted general superiority of in-context learning (ICL) for OOD. We find that the efficacy of such learning paradigms varies with the type of OOD. Specifically, while ICL excels for domain shifts, prompt-based fine-tuning surpasses for topic shifts. To sum up, we navigate the heterogeneity of OOD scenarios in CA and empirically underscore the potential of base-sized LMs in overcoming these challenges.