A Preliminary Study on Explaining Risk of Code Changes using LLM-Based Prediction Models

• URL: http://arxiv.org/abs/2607.02782v1
• Date: Thu, 02 Jul 2026 21:31:09 GMT
• Title: A Preliminary Study on Explaining Risk of Code Changes using LLM-Based Prediction Models
• Abstract summary: We leverage attention weights from an LLM-based Diff Risk Score model to highlight parts of a software change.<n>We evaluate our approach using expert-labeled changes that have caused real outages.
• Score: 12.235188801401153
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predictions by machine learning (ML) and artificial intelligence (AI) models are often received skeptically unless they are paired with intelligible explanations. In the context of just-in-time defect prediction, highlighting small portions of a software change (diff) -- beyond rule-based lints -- where risk may be concentrated has not yet been extensively investigated. In this work, we leverage attention weights from an LLM-based Diff Risk Score (DRS) model to highlight parts of a diff that the model focuses on when predicting risk. We aggregate token-level attention into interpretable code units (lines, hunks, and files), and present the top-K units to developers as a lightweight form of guidance during code review. We evaluate our approach using expert-labeled changes that have caused real outages. Results show that the highlighted snippets cover expert-labeled outage-causing change lines 53.85% of the time when highlighting the top-2 hunks, while requiring developers to review 26.28% of the changed lines on average. Because attention is produced during standard model inference, the approach is scalable for large development workflows and can be surfaced in the code review UI with low additional latency.

Related papers

• Deployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video [0.4310167974376404]
  Current change control approaches use blanket deployment freezes that block all changes regardless of risk.<n>We introduce a framework centered on diff-aware features, characteristics derived directly from code modifications.<n>We employ LLMs as multi-language feature extractors, demonstrating their effectiveness for code analysis beyond generation tasks.
  arXiv  Detail & Related papers  (2026-07-07T19:54:16Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• Dynamic analysis enhances issue resolution [53.50448142467294]
  DAIRA (Dynamic Analysis-enhanced Issue Resolution Agent) is an automated repair framework that embeds dynamic analysis into the agent's reasoning cycle.<n> Driven by a Test Tracing-Driven methodology, DAIRA utilizes lightweight monitors to extract critical runtime data.<n>When powered by Gemini 3 Flash Preview, DAIRA establishes a new state-of-the-art (SOTA) performance, achieving a 79.4% resolution rate on the SWE-bench Verified dataset.
  arXiv  Detail & Related papers  (2026-03-23T14:48:54Z)
• Adapting Language Balance in Code-Switching Speech [60.296574524609575]
  Large foundational models still struggle against code-switching test cases.<n>We use differentiable surrogates to mitigate context bias during generation.<n>Experiments with Arabic and Chinese-English showed that the models are able to predict the switching places more correctly.
  arXiv  Detail & Related papers  (2025-10-21T15:23:55Z)
• Evaluating Line-level Localization Ability of Learning-based Code Vulnerability Detection Models [9.543689542888599]
  We propose an explainability-based evaluation procedure for vulnerability detectors.<n>Our approach, defined as Detection Alignment (DA), quantifies the agreement between the input source code lines.<n>We show how the predictions of such models are consistently biased by non-vulnerable lines.
  arXiv  Detail & Related papers  (2025-10-13T09:34:40Z)
• Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders [0.0]
  We apply sparse autoencoders to decompose Large Language Models, identifying directions that correspond to code correctness.<n>We find that code correctness directions in LLMs reliably predict incorrect code, while correction capabilities, though statistically significant, involve tradeoffs between fixing errors and preserving correct code.<n>Our mechanistic insights suggest three practical applications: prompting strategies should prioritize test examples over elaborate problem descriptions, predictor directions can serve as error alarms for developer review, and these same predictors can guide selective steering, intervening only when errors are anticipated to prevent the code corruption from constant steering.
  arXiv  Detail & Related papers  (2025-10-03T11:44:21Z)
• LLM-Based Detection of Tangled Code Changes for Higher-Quality Method-Level Bug Datasets [8.166584296080805]
  We investigate the utility of Large Language Models for detecting tangled code changes by leveraging both commit messages and method-level code diffs.<n>Our results demonstrate that combining commit messages with code diffs significantly enhances model performance.<n>Applying our approach to 49 open-source projects improves the distributional separability of code metrics between buggy and non-buggy methods.
  arXiv  Detail & Related papers  (2025-05-13T06:26:13Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• Uncertainty-Aware Decoding with Minimum Bayes Risk [70.6645260214115]
  We show how Minimum Bayes Risk decoding, which selects model generations according to an expected risk, can be generalized into a principled uncertainty-aware decoding method.<n>We show that this modified expected risk is useful for both choosing outputs and deciding when to abstain from generation and can provide improvements without incurring overhead.
  arXiv  Detail & Related papers  (2025-03-07T10:55:12Z)
• If LLMs Would Just Look: Simple Line-by-line Checking Improves Vulnerability Localization [33.42741297088634]
  Traditional methods for vulnerability localization, such as manual code audits or rule-based tools, are often time-consuming and limited in scope.<n>This paper introduces LOVA, a novel framework leveraging the self-attention mechanisms inherent in large language models.<n>We demonstrate that LOVA significantly outperforms existing LLM-based approaches, achieving up to a 5.3x improvement in F1-scores.
  arXiv  Detail & Related papers  (2024-10-20T05:02:18Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• IRJIT: A Simple, Online, Information Retrieval Approach for Just-In-Time Software Defect Prediction [10.084626547964389]
  Just-in-Time software defect prediction (JIT-SDP) prevents the introduction of defects into the software by identifying them at commit check-in time. Current software defect prediction approaches rely on manually crafted features such as change metrics and involve expensive to train machine learning or deep learning models. We propose an approach called IRJIT that employs information retrieval on source code and labels new commits as buggy or clean based on their similarity to past buggy or clean commits.
  arXiv  Detail & Related papers  (2022-10-05T17:54:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.