What question did this study set out to answer?

The aim is to evaluate the effectiveness of context-aware language models in detecting ambiguity in requirements.

July 4, 2026Open Access

Context-aware large language models for ambiguity detection in requirements

Key Points

The aim is to evaluate the effectiveness of context-aware language models in detecting ambiguity in requirements.
Investigated ambiguity detection using a hybrid dataset of NASA JWST requirements and injected defects.
Compared a context-aware approach to a baseline domain-agnostic model.
Utilized auto-extracted domain knowledge to enhance model performance.
Context-aware models significantly improved ambiguity detection compared to domain-agnostic baselines.
Findings indicate enhanced accuracy in distinguishing ambiguous requirements from acceptable ones.

Abstract

ABSTRACT: Requirements quality shapes engineering design, yet natural language specifications remain vulnerable to ambiguity. We investigate how LLMs support ambiguity detection using a hybrid dataset combining NASA JWST requirements with systematically injected defects. Using auto-extracted domain knowledge, we compare a domain-agnostic baseline with a context-aware approach. Incorporating domain knowledge helps LLMs better distinguish genuinely ambiguous requirements from acceptable ones, highlighting the potential of context-aware AI assistants for requirements engineering and early-stage design.

AIに質問

Bookmark

View Full Paper