CodeHID: Generative Code Retrieval via Hierarchical Indexing

_reachsumit · x · 2026-08-26

The paper "CodeHID: Learning an Addressable Hierarchical Code Index for Generative Code Retrieval" proposes a generative code retrieval framework. It reformulates code retrieval from flat candidate matching to coarse-to-fine semantic address generation. Key components include:

Experiments on CoSQA and ProCQA datasets demonstrate its effectiveness.

Original post →

More from Research

Research channel →