发表机构
Stony Brook University（石溪大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
IDRAAK是基于语义需求表示的可解释框架，通过含6个少样本示例的LLM单次调用检测技术需求语义漂移，性能优于多种替代方案，证明少样本提示是高效替代方法。
AI 中文摘要
跨语言翻译技术需求会引入语义漂移，改变数值约束、极性、模态或其他对规范至关重要的含义。本文提出IDRAAK，这是一个可解释框架，采用与语言无关的语义需求表示（SRR）来检测此类漂移，评估了六种检测工作流，范围从确定性比较到多智能体验证和少样本提示。在来自10个工程领域的300个需求上的890个合成扰动中，使用6个少样本示例的单次大语言模型（LLM）调用达到马修斯相关系数（MCC）=0.888、F1值=0.983，优于所评估的结构化和多阶段替代方案。在PAWS-X（805对、5种语言）和XNLI（700对、7种语言）上的进一步评估揭示了结构化方法和基于LLM方法的互补优势与局限。确定性SRR比较在技术需求上表现强劲（F1=0.898），但在通用领域文本上表现很差（F1=0.012），而结构化证据可提升对抗性释义的性能。事后Platt缩放进一步改善了置信度校准。结果表明，增加智能体复杂度不一定能提升语义漂移检测性能，简单的少样本提示可提供强大且高效的替代方案。
英文摘要
Translating technical requirements across languages can introduce semantic drift, altering numerical constraints, polarities, modalities, or other specification-critical meaning. IDRAAK is presented as an interpretable framework for detecting such drift using a language-independent Semantic Requirement Representation (SRR), with six detection workflows evaluated, ranging from deterministic comparison to multi-agent verification and few-shot prompting. On 890 synthetic perturbations across 300 requirements from 10 engineering domains, a single LLM call with six few-shot examples achieves MCC=0.888 and F1=0.983, outperforming the evaluated structured and multi-stage alternatives. Further evaluation on PAWS-X (805 pairs, 5 languages) and XNLI (700 pairs, 7 languages) exposes complementary strengths and limitations of structured and LLM-based approaches. Deterministic SRR comparison performs strongly on technical requirements (F1=0.898) but poorly on general-domain text (F1=0.012), while structured evidence improves performance on adversarial paraphrases. Post-hoc Platt scaling further improves confidence calibration. The results demonstrate that increased agentic complexity does not necessarily improve semantic-drift detection and that simple few-shot prompting can provide a strong and efficient alternative.
