Code
PoLi-RL: A Point-to-List Reinforcement Learning Framework for Conditional Semantic Textual Similarity
Why Lacuna links this resource
Confirmed by the paper and resource
The paper explicitly provides the URL to the repository as its official code and checkpoints. The repository's README explicitly states the title of the paper and mentions it was accepted to ICLR 2026, confirming it is the primary resource for the paper.