接地优化：一种减少自动个人文档重写中LLM幻觉的分层工程框架
Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting
AI总结：
提出五层接地优化框架，通过时间验证、污染检测、结构不变性、提示接地和评估器，将简历重写中的幻觉率降至0.04-0.24。
摘要：
大型语言模型（LLM）越来越多地应用于针对申请人跟踪系统的简历优化，引入了与通用文本生成不同的幻觉失败：时代错误的技术注入、跨领域术语污染、结构突变和内容捏造。我们提出了接地优化，一个五层框架，结合了时间上下文验证、确定性污染检测、结构不变性强制、提示级接地和评估器代理。在跨三个LLM、四个温度设置和六个层配置的消融实验中，使用覆盖14个行业的25份合成简历，未防御的基线每份简历产生2.48-5.36个检测到的幻觉。在独立于主动防御的检测器中，所有条件下时间幻觉减少50-95%；整体检测到的幻觉率降至0.04-0.24。仅提示级接地在低温下使用能力强的指令跟随模型实现了零检测幻觉；更高的温度和较弱的模型揭示了需要确定性层作为补充。我们发布了污染分类、评估代码和原始数据。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
