让大模型假装只掌握截止日期前的知识，提升过时信息的判断力。
Can LLMs Be Constrained to the Past? Improving Knowledge Cutoff through Recall-Based Prompting
- 用自我复述和问题回忆两种新提示法，强制模型遵守知识截止时间。
- 在多个测试集上超越传统方法，尤其对假设性问题效果显著。
- 适合需要严格控制知识时效性的场景，如历史研究或法律审查。
知识截止提示要求大语言模型表现得如同在指定截止日期后信息不可用。然而，以往方法主要依赖直接回答，当后期知识未被明确提问但仅与问题存在因果关联时，表现不佳。为此，我们提出两种基于回忆的提示策略：自我回忆（SR），要求模型重述其截止约束；问题回忆（QR），要求模型回忆在截止条件下相关的信息。在三个现有基准测试中，我们的方法优于直接回答提示和传统分步推理基线，尤其在反事实问题上提升明显。为检验不同截止设置下的鲁棒性，我们构建了多截止年份历史事件基准（MHEB），评估同一问题在多个截止年份的表现。结果显示，知识截止性能随截止距离变化，而结合SR与QR始终取得最佳效果。
原文摘要 · Abstract (English)
Prompted knowledge cutoff instructs a large language model (LLM) to act as if information beyond a specified cutoff date were unavailable. However, prior work mainly relies on direct-answer generation, which struggles when post-cutoff knowledge is not explicitly queried but is only causally related to the question. To address this limitation, we propose two recall-based prompting strategies: Self-Recall (SR), which asks the model to restate its cutoff constraint, and Question-Recall (QR), which requires the model to recall question-relevant information valid under the cutoff. Across three existing benchmarks, our methods outperform both direct-answer prompting and conventional step-by-step reasoning baselines, with particularly strong improvements on counterfactual questions. To investigate robustness across different cutoff settings, we further construct the Multi-cutoff Historical Event Benchmark (MHEB), which evaluates the same question under multiple cutoff years. Results show that knowledge cutoff performance varies with cutoff distance, while combining SR and QR consistently yields the best performance.
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。