超越相似性：面向LLM时间序列预测的覆盖感知提示选择
Beyond Similarity: Coverage-Aware Prompt Selection for Time Series Forecasting with LLMs
浏览论文内容
中文总结 AI 辅助
针对基于相似性提示选择导致时间序列预测偏置的问题，提出覆盖感知框架CASP-LLM，通过使用跟踪与饱和门控正则化器（无额外参数）在多数基准上匹配或超越现有方法。
中文摘要 AI 辅助
基于相似性的检索是条件化大型语言模型（LLM）在上下文学习、检索增强生成和基于提示的时间序列预测中的主导规则。该规则集中于近似重复的候选，这一问题推动了多样性感知检索的发展，但在其他检索条件化流程中仍未得到检验。我们以基于提示的时间序列预测作为测试平台研究该问题，其中学习到的提示池通过相似性进行检索。该设置中的主流方法通过余弦相似度检索前K个条目而不进行冗余控制，导致对主导时间模式的偏置，同时忽略罕见但信息丰富的事件。我们提出CASP-LLM，一种覆盖感知的语义提示框架，通过将使用跟踪和饱和门控技术结合到覆盖正则化器中来解决这种提示选择偏置，且不增加任何可学习参数。在六个长期基准和M4短期基准上，CASP-LLM在大多数数据集-水平设置中匹配或优于基于相似性的LLM预测器，例外情况包括Electricity、M4-Monthly和少样本长期设置。一项受控研究将失败模式定位于跨批次使用层面，而非每次检索的冗余：诸如MMR之类的检索内多样化没有帮助，而在训练中正则化锚点使用则有效。
英文摘要
Similarity-based retrieval is the dominant rule for conditioning large language models (LLMs) in in-context learning, retrieval-augmented generation, and prompt-based time series forecasting. The rule concentrates on near-duplicate candidates, an issue that has motivated diversity-aware retrieval but remains unexamined in other retrieval-conditioned pipelines. We study this issue using prompt-based time series forecasting as a test bed, where a learned prompt pool is retrieved by similarity. Dominant methods in this setting retrieve top-K entries by cosine similarity without redundancy control, producing a bias toward dominant temporal patterns while overlooking rare but informative events. We propose CASP-LLM, a coverage-aware semantic prompting framework that addresses this prompt selection bias by combining usage-tracking and saturating-gate techniques into a coverage regularizer that adds no learnable parameters. On six long-term benchmarks and the M4 short-term benchmark, CASP-LLM matches or improves on similarity-based LLM forecasters on most dataset-horizon settings, with the exceptions of Electricity, M4-Monthly, and the few-shot long-horizon setting. A controlled study locates the failure mode at the cross-batch usage level rather than per-retrieval redundancy: within-retrieval diversification such as MMR does not help, whereas regularizing anchor usage across training does.
发表机构
- Yonsei University（延世大学）
机构由 AI 辅助整理，请以论文原文为准。
