AmbigNLG: Addressing Task Ambiguity in Instruction for NLG

TL;DR

This paper introduces AmbigNLG, a new task and dataset aimed at reducing instruction ambiguity in NLG, improving LLM performance by clarifying instructions, and demonstrating significant enhancements in output quality and interactive clarification.

Contribution

It proposes an ambiguity taxonomy, a dataset for research, and a method that significantly improves LLM alignment with user expectations in ambiguous instruction scenarios.

Findings

Up to 15.02-point increase in ROUGE scores

Enhanced alignment of generated text with user expectations

Effective interactive ambiguity mitigation with LLMs

Abstract

We introduce AmbigNLG, a novel task designed to tackle the challenge of task ambiguity in instructions for Natural Language Generation (NLG). Ambiguous instructions often impede the performance of Large Language Models (LLMs), especially in complex NLG tasks. To tackle this issue, we propose an ambiguity taxonomy that categorizes different types of instruction ambiguities and refines initial instructions with clearer specifications. Accompanying this task, we present AmbigSNI-NLG, a dataset comprising 2,500 instances annotated to facilitate research in AmbigNLG. Through comprehensive experiments with state-of-the-art LLMs, we demonstrate that our method significantly enhances the alignment of generated text with user expectations, achieving up to a 15.02-point increase in ROUGE scores. Our findings highlight the critical importance of addressing task ambiguity to fully harness the capabilities of LLMs in NLG tasks. Furthermore, we confirm the effectiveness of our method in practical settings involving interactive ambiguity mitigation with users, underscoring the benefits of leveraging LLMs for interactive clarification.