Papers by Zhisheng Huang
CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Entity matching (EM) requires fine-grained contextual understanding and domain knowledge. |
| Approach: | They propose a reinforcement learning controller that manages LLM operations by combining multiple operators and a set of model capacities. |
| Outcome: | The proposed controller can be reused with different LLM backends at inference time without retraining. |