AmbigNLG: Addressing Task Ambiguity in Instruction for NLG
This addresses a critical bottleneck for users of LLMs in NLG tasks, though it is incremental as it builds on existing methods for instruction refinement.
The paper tackles the problem of task ambiguity in instructions for Natural Language Generation (NLG), which hinders Large Language Models, by introducing a taxonomy and refinement method that improves alignment with user expectations, achieving up to a 15.02-point increase in ROUGE scores.
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.