A Decomposed Retrieval-Edit-Rerank Framework for Chord Generation
Qiqi He, Dichucheng Li, Xiaoheng Sun, and Anqi Huang

TL;DR
This paper introduces a Retrieval-Edit-Rerank framework for chord generation that separates candidate retrieval, minimal editing, and reranking to improve control, interpretability, and balance between diversity and feasibility.
Contribution
It proposes a novel decomposed system that explicitly separates retrieval, editing, and reranking stages, enhancing controllability and interpretability in chord generation.
Findings
Outperforms end-to-end baselines in balancing diversity and feasibility.
Each stage contributes uniquely to creative exploration and constraint satisfaction.
Ablation studies confirm the effectiveness of the decomposed pipeline.
Abstract
Chord generation is an inherently constrained creative task that requires balancing stylistic diversity with music-theoretic feasibility. Existing approaches typically entangle candidate generation and constraint enforcement within a single model, making the diversity-feasibility trade-off difficult to control and interpret. In this work, we approach chord generation from a system-level perspective, introducing a Retrieval-Edit-Rerank (RER) framework that decomposes the task into three explicit stages: i) retrieval, which defines a stylistically plausible candidate space; ii) editing, which enforces music-theoretic feasibility through minimal modifications; and iii) reranking, which resolves soft preferences among feasible candidates. This separation provides a controllable pipeline, where each component addresses a distinct aspect of the generation process, thereby enhancing both the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
