cs.AINov 15, 2026

When Valid Decisions Are Not Enough: Evaluating Structural Constraints in Knowledge-Guided Generative Systems

Authors: Josef Pavlíček, Petra Pavlíčková, Martin Molhanec

Organizations: Department of Software Engineering, Faculty of Information Technology, Czech Technical University in Prague, Czech Republic · Faculty of Electrical Engineering, Czech Technical University in Prague, Prague 6, Czech Republic

Abstract

Knowledge-guided generative systems use explicit domain constraints to improve decision consistency and alignment with human-created solutions. However, locally valid decisions do not necessarily preserve contextual relationships in human decision-making. This paper examines when structural constraints improve or degrade agreement with human reference solutions. We introduce HARMONIX, an experimental framework using automated musical harmonization as a controlled testbed for knowledge-guided decision-making. Four configurations share the same Viterbi-based optimization mechanism: a baseline, repetition constraints, functional constraints, and their combination. Experiments cover 19,745 records and 143,634 motif pairs across training and validation partitions. Combined constraints improve reference root-interval agreement by approximately five percentage points in stable structural contexts but reduce it by nearly nine percentage points in contexts involving transposition tracking. These opposing effects are consistent across both partitions, while overall exact chord agreement changes only marginally. Contexts are identified retrospectively using reference annotations; no adaptive constraint-selection mechanism is evaluated. The findings demonstrate that interpretable constraints can introduce systematic context-specific failures concealed by aggregate accuracy metrics. They highlight the need to evaluate relationships between decisions and the contextual applicability of constraints in knowledge-guided generative systems.

Figures & tables

Explore similar work

CardsList
  1. Designing Maintainable Hybrid Generative Systems: A Quantum-Inspired Approach to Automated Music Harmony Generation

    Jul 7, 2026Josef PavlicekControllable Music GenerationSymbolic Music Generation

  2. From Individual Songs to Music Corpora: Evaluating Explainable Harmonic Decision-Making on HookTheory

    Oct 14, 2026Josef Pavlíček, Martin PelikánMusic GenerationMusic Generation Evaluation

  3. Do Language Models Need Music Supervision? Verifiable Rewards for Multi-Constraint Symbolic Music Generation

    Sep 20, 2026Haoyue Liu, Xiaoying TangMusic Generation EvaluationControllable Music Generation