SOURCE-LINKED INTELLIGENCE

CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Entity matching (EM) requires fine-grained contextual understanding and domain knowledge. Recent work shows that large language models (LLMs) can serve as strong matchers across domains, but most methods either make independent pairwise decisions or rely on manually designed composite pipelines, thus lacking flexibility in realistic multi-candidate settings. At the same time, they typically ignore inference cost at scale. We formulate LLM-based EM with candidates as a cost-aware sequential decision problem and propose CaRL-EM, a reinforcement learning controller that manages LLM operations. Gi

Read original source ↗ Open in workspace

recordType

paper

region

Global