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:
- Pseudo-Neighbor Guided DocID Learning: Constructs a globally static hierarchical index using multi-level residual quantization and k-NN pseudo-supervision, ensuring semantically related code snippets share prefixes.
- Dual-Phase DocID Generation Guidance: Combines training-side ranking enhancements (using hard negatives and rank distillation) with inference-side candidate constraints and prefix-aware decoding.
Experiments on CoSQA and ProCQA datasets demonstrate its effectiveness.
More from Research
- How LLMs Self-Correct Mid-Generation: The Role of Reasoning RL and Instructions — dejanseo · 2026-08-26
- U. de Chile Students Publish Book on Maturana and Varela's Relevance in AI — PolarBearby · 2026-08-26
- Face Anything: 4D Face Reconstruction from Any Image Sequence (ECCV 2026) — rsasaki0109 · 2026-08-26
- Gemini 3.7 Flash helps revive interactive CMA-ES explainer site — doodlestein · 2026-08-26
- From PDE Numerical Solvers to Neural Emulators and Back: PhD Thesis — chaumian · 2026-08-26
- Combining PSGD-Kron and KL-Shampoo yields an optimizer without eig/inverse/solve — YouJiacheng · 2026-08-26