Yuxiao Luo

SHIFT: Self-reconstruction Harnesses Implicit Fine-grained Thinking for Retrieval

This work proposes SHIFT, a retrieval training framework based on LLMs that transfers LLMs into reasoning-efficient retrievers with residual projection and task-oriented bidirectional attention aggregation in the latent space, and alleviates the mismatch between contrastive learning and implicit reasoning using fine-grained next-token-prediction-based reconstruction.