Jiapu Wang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28176 · open-access PDF
Grandes Modelos de Linguagem (LLMs) muitas vezes lutam com raciocínio baseado no tempo porque sua memória paramétrica estática está desalinhada com a evolução dinâmica do conhecimento do mundo real. Embora RAG e Parameter-Efficient Fine-Tuning (PEFT) forneçam maneiras práticas de melhorar os LLMs, eles permanecem insuficientes para raciocínio temporal. Métodos de recuperação existentes normalmente priorizam a relevância semântica enquanto ignoram a validade temporal, a ordem de eventos e as dependências evolutivas, resultando em evidências que são relevantes em isolamento, mas fragmentadas temporalmente.
Machine translation (Meta M2M100); the English original follows.
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
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28176, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange