DeFuzzRAG:處理模糊時間表達以提升檢索增強生成的時間穩定性

Abstract

大型語言模型（Large Language Models, LLMs）在推理與知識密集型任務中展現出卓越表現，然而其靜態的預訓練特性使其難以處理快速變化或具領域特定性的知識。檢索增強生成（Retrieval-Augmented Generation, RAG）透過引入動態檢索的證據以強化 LLM 的輸出內容，進而提升其事實正確性並降低幻覺現象的發生。然而，傳統的 RAG 在面對具有時間敏感性的查詢時表現不佳，特別是在文件中出現模糊或間接的時間表述（例如「幾年之後」）時。這將導致時間錯置（Temporal Misalignment）現象，即檢索結果在主題上雖然相關，卻在時間上不正確。為了解決此問題，我們提出 DeFuzzRAG，一個提升 RAG 時間穩定性的輕量級架構。DeFuzzRAG 採用小型本地語言模型來從模糊的時間表達中推斷具體的時間範圍，並運用以時間中介資料為基礎的過濾機制，使檢索結果重新對齊查詢的時間意圖。我們在一套模糊化查詢基準上進行實驗，結果顯示 DeFuzzRAG 能顯著提升檢索準確率，將命中率提高 15.7%，同時維持運算效率並具備模型無關的整合能力。實驗結果凸顯時間推理在 RAG 架構中的重要性，並確立 DeFuzzRAG 作為一種可實用、可即插即用的解決方案，適用於部署在現實應用情境中的時間魯棒 LLM 系統。

Large Language Models (LLMs) have achieved remarkable success across reasoning and knowledge-intensive tasks, yet their static pretraining leaves them unable to handle rapidly evolving or domain-specific knowledge. Retrieval-Augmented Generation (RAG) addresses this by grounding LLM outputs in dynamically retrieved evidence, improving factual accuracy and reducing hallucinations. However, standard RAG pipelines struggle with temporally sensitive queries, especially when documents contain fuzzy or indirect time expressions (e.g., “a few years later”). This leads to Temporal Misalignment, where topically relevant but temporally incorrect results are retrieved. To overcome this, we propose DeFuzzRAG, a lightweight framework that enhances temporal robustness in RAG. DeFuzzRAG employs a small local language model to infer concrete time scopes from vague expressions and applies metadata-based filtering to realign retrieval with the query’s temporal intent. Experiments on a benchmark of fuzzified queries demonstrate that DeFuzzRAG substantially improves retrieval accuracy, raising Hit Rate by 15.7% while maintaining efficiency and model-agnostic integration. Our findings highlight the importance of temporal reasoning in RAG and establish DeFuzzRAG as a practical, plug-and-play solution for deploying temporally robust LLM systems in real-world settings.