Metraipolis › archive › dc_63e4bf5114dc
CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs — arXiv:2609.01195
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01195
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:41:32.295Z
- SHA-256 of the archived text
b84cbcf6b2d800d4e4335c21b3272acb45fe1c2d861057764143b182f3f64983- Stable URL of this page
https://metraipolis.com/documento/dc_63e4bf5114dc
How to cite
CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs — arXiv:2609.01195 — arXiv (en), https://arxiv.org/abs/2609.01195 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_63e4bf5114dc (Metraipolis archive dc_63e4bf5114dc, sha256 b84cbcf6b2d800d4e4335c21b3272acb45fe1c2d861057764143b182f3f64983)
BibTeX
@misc{dc63e4bf5114dc,
title = {CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs — arXiv:2609.01195},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01195},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_63e4bf5114dc; sha256 b84cbcf6b2d800d4e4335c21b3272acb45fe1c2d861057764143b182f3f64983},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01195. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Given the state of an anchor record, its candidate set, and the cost, CaRL-EM adaptively chooses among different operators (Match/Compare/Select/Decide) and model capacities to maximize a quality-cost objective. The policy interacts with abstract operators, allowing the same controller to be reused with different underlying LLM backends at inference time without retraining. Experiments on 7 benchmarks show that CaRL-EM (i) learns to dynamically plan the usage of inexpensive and expensive operators based on task complexity, (ii) achieves robust zero-shot transfer across diverse datasets and domains, and (iii) consistently achieves a better quality-cost trade-off than strong LLM-based baselines and manually designed pipelines, yielding a lower inference cost at comparable or higher quality. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.01195 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:33:38.850Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).