用少量示例提示检测技术需求翻译中的语义漂移，效果优于复杂多智能体方案。
IDRAAK: From Multi-Agent NLP to Few-Shot Prompting for Semantic Drift Detection in Technical Requirements
- 基于语言无关的语义需求表示，用少样本提示实现漂移检测
- 单次大模型调用即达F1=0.983，优于多阶段与多智能体方法
- 适合需快速验证技术需求一致性的工程团队使用
技术需求跨语言翻译可能引入语义漂移，改变数值约束、极性或关键含义。本文提出可解释的IDRAAK框架，通过语言无关的语义需求表示（SRR）检测此类漂移，评估了六种检测流程，涵盖确定性比较、多智能体验证及少样本提示。在10个工程领域共300条需求上生成的890个合成扰动中，仅需一次LLM调用加六个少样本示例，即可达到MCC=0.888、F1=0.983，超越所评估的结构化与多阶段方法。在PAWS-X（805对，5语言）和XNLI（700对，7语言）上的进一步评估揭示了结构化与基于LLM方法的互补优劣：确定性SRR比较在技术需求上表现良好（F1=0.898），但在通用文本上极差（F1=0.012）；结构化证据在对抗性改写中提升性能。事后Platt缩放进一步改善置信度校准。结果表明，智能体复杂度增加未必提升检测效果，简单少样本提示已是高效强效替代方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。