Keyword-Centric Prompting for One-Shot Event Detection with Self-Generated Rationale Enhancements

TL;DR

This paper introduces KeyCP++, a keyword-centric prompting method that enhances one-shot event detection by guiding LLMs to generate meaningful rationales and reduce over-reliance on keywords, significantly improving detection accuracy.

Contribution

It proposes a novel prompt construction that incorporates trigger keywords to improve one-shot event detection with LLMs by generating and judging candidate triggers.

Findings

KeyCP++ outperforms baseline methods in one-shot event detection.

The approach effectively reduces over-interpretation of triggers.

Experimental results show significant accuracy improvements.

Abstract

Although the LLM-based in-context learning (ICL) paradigm has demonstrated considerable success across various natural language processing tasks, it encounters challenges in event detection. This is because LLMs lack an accurate understanding of event triggers and tend to make over-interpretation, which cannot be effectively corrected through in-context examples alone. In this paper, we focus on the most challenging one-shot setting and propose KeyCP++, a keyword-centric chain-of-thought prompting approach. KeyCP++ addresses the weaknesses of conventional ICL by automatically annotating the logical gaps between input text and detection results for the demonstrations. Specifically, to generate in-depth and meaningful rationale, KeyCP++ constructs a trigger discrimination prompting template. It incorporates the exemplary triggers (a.k.a keywords) into the prompt as the anchor to simply trigger profiling, let LLM propose candidate triggers, and justify each candidate. These propose-and-judge rationales help LLMs mitigate over-reliance on the keywords and promote detection rule learning. Extensive experiments demonstrate the effectiveness of our approach, showcasing significant advancements in one-shot event detection.