针对简历优化中大模型幻觉问题，提出分层防御框架
Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting
- 五层架构融合时间验证、污染检测与结构约束
- 幻觉检测率降至每份简历0.04至0.24次，降幅超90%
- 适合需高可靠性文本生成的求职/简历类应用
大语言模型在申请人追踪系统中的简历优化应用中引入了独特幻觉：技术时间错位、跨领域术语污染、结构变异和内容虚构。我们提出地面化优化（Grounded Optimization）框架，包含五个层级：时间上下文验证、确定性污染检测、结构不变性强制、提示级接地及评估代理。在三款模型、四种温度设置、六种层级配置下，对25份涵盖14个行业的合成简历进行消融实验。未加防护的基线模型每份简历产生2.48至5.36次可检测幻觉。独立检测器显示，所有条件下时间幻觉减少50%-95%；总体幻觉率降至0.04-0.24次。提示级接地在低温度与强指令跟随模型下实现零幻觉；高温及弱模型则凸显确定性层级的必要性。我们公开了污染分类体系、评估代码与原始数据。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly applied to resume optimization for applicant tracking systems, introducing hallucination failures distinct from general text generation: anachronistic technology injection, cross-domain terminology contamination, structural mutation, and content fabrication. We present Grounded Optimization, a five-layer framework combining temporal context validation, deterministic contamination detection, structural invariant enforcement, prompt-level grounding, and an evaluator agent. In ablation experiments across three LLMs, four temperature settings, and six layer configurations on 25 synthetic resumes spanning 14 industries, undefended baselines produce 2.48-5.36 detected hallucinations per resume. Among detectors independent of the active defenses, temporal hallucinations are reduced by 50-95% across all conditions; overall detected hallucination rate falls to 0.04-0.24. Prompt-level grounding alone achieves zero detected hallucinations at low temperature with a capable instruction-following model; higher temperatures and weaker models reveal the need for the deterministic layers as a complement. We release the contamination taxonomy, evaluation code, and raw data.
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。