temporal-reasoning

Tag

Cards List
#temporal-reasoning

LiFT: Does Instruction Fine-Tuning Improve In-Context Learning for Longitudinal Modelling by Large Language Models?

arXiv cs.CL · 2026-04-21 Cached

LiFT is a longitudinal instruction fine-tuning framework that unifies diverse temporal NLP tasks under a shared instruction schema with curriculum-based training. Evaluated across OLMo, LLaMA, and Qwen models, LiFT consistently outperforms base-model in-context learning, especially on out-of-distribution data and rare change events.

0 favorites 0 likes
#temporal-reasoning

Zep: A Temporal Knowledge Graph Architecture for Agent Memory

Papers with Code Trending · 2025-01-20 Cached

This paper introduces Zep, a temporal knowledge graph architecture for agent memory that outperforms MemGPT in benchmarks like DMR and LongMemEval. It highlights Zep's ability to handle dynamic knowledge integration and temporal reasoning for enterprise use cases.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback