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

German

Große Sprachmodelle (LLMs) kämpfen oft mit zeitlich begründeter Argumentation, weil ihr statisches parametrisches Gedächtnis mit der dynamischen Entwicklung des realen Wissens nicht in Einklang gebracht wird. Obwohl RAG und Parameter-Effizient Fine-Tuning (PEFT) praktische Wege zur Verbesserung von LLMs bieten, bleiben sie für zeitliche Argumentation unzureichend. Bestehende Abrufmethoden priorisieren in der Regel semantische Relevanz, während sie zeitliche Gültigkeit, Ereignisordnung und evolutionäre Abhängigkeiten übersehen, was zu Beweisen führt, die isoliert, aber zeitlich fragmentiert sind.

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

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