Newest papers

Temporal Evidence-Parameter Co-Alignment for LLM Reasoning over Temporal Knowledge Graphs

Jiapu Wang · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28176 · open-access PDF

Chinese

大型语言模型(LLMs)经常与时间基础的推理作斗争,因为它们的静态参数记忆与现实世界知识的动态演变不一致.虽然RAG和参数效率精细调整(PEFT)提供了增强LLM的实际方法,但它们仍然不够用于时间推理。现有的检索方法通常优先考虑语义相关性,同时忽视时间有效性,事件顺序和进化依赖性,导致证据在孤立但时间上分裂。

Machine translation (Meta M2M100); the English original follows.

Abstract

Large Language Models (LLMs) often struggle with temporally grounded reasoning because their static parametric memory is misaligned with the dynamic evolution of real-world knowledge. Although RAG and Parameter-Efficient Fine-Tuning (PEFT) provide practical ways to enhance LLMs, they remain insufficient for temporal reasoning. Existing retrieval methods typically prioritize semantic relevance while overlooking temporal validity, event order, and evolutionary dependencies, resulting in evidence that is relevant in isolation but temporally fragmented. Meanwhile, conventional PEFT methods usually

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange