Deterministic vs. Probabilistic Summarisation: An Empirical Trade-off Study in Design Pattern Centric Java Code

TL;DR

This study empirically compares deterministic and probabilistic code summarisation methods in Java, revealing a trade-off between semantic depth and reproducibility.

Contribution

It provides a controlled empirical analysis of these paradigms using design-pattern-centric Java code, highlighting their respective strengths and limitations.

Findings

Probabilistic summaries have better semantic alignment and contextual coverage.

Deterministic approaches produce more concise and reproducible summaries.

Variability exists in LLM outputs, but overall trends are consistent.

Abstract

Background: Automated code summarisation supports program comprehension and documentation, yet the relative strengths and limitations of deterministic (heuristic-based) and probabilistic (LLM-based) pipelines remain unclear. Aims: This paper presents a controlled empirical comparison of these paradigms for intent-oriented design-pattern code summarisation. Method: Using design-pattern-centric Java code as a structured testbed (150 files from three open-source repositories covering nine patterns), we compare a rule-based natural language generation (NLG) pipeline, a Software Word Usage Model (SWUM)-based approach, and a probabilistic pipeline based on the Mixtral LLM. Summaries are evaluated against human references using BERTScore and cosine similarity, complemented by rubric-based judgements produced by Llama 3 across five dimensions: accuracy, conciseness, adequacy, code-context awareness, and design-pattern fidelity. Statistical analysis includes Wilcoxon signed-rank tests (with effect sizes), Friedman tests with post-hoc corrections, and Spearman correlation for sensitivity analysis of rubric consistency. Results: Probabilistic summaries show stronger semantic alignment and richer contextual coverage, while deterministic approaches produce more concise and fully reproducible outputs. Prompt-sensitivity and multi-run analyses indicate variability in LLM outputs, though relative trends remain stable. Conclusions: A clear trade-off emerges: probabilistic methods favour semantic depth and contextual accuracy, whereas deterministic pipelines are preferable for brevity and reproducibility. These findings provide practical guidance for selecting code summarisation techniques.