Measuring Determinism in Large Language Models for Software Code Review

• URL: http://arxiv.org/abs/2502.20747v1
• Date: Fri, 28 Feb 2025 05:53:16 GMT
• Title: Measuring Determinism in Large Language Models for Software Code Review
• Authors: Eugene Klishevich, Yegor Denisov-Blanch, Simon Obstbaum, Igor Ciobanu, Michal Kosinski,
• Abstract summary: Large Language Models (LLMs) promise to streamline software code reviews, but their ability to produce consistent assessments remains an open question.<n>We tested four leading LLMs on 70 Java commits from both private and public repositories.
• Score: 7.46879002825422
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs) promise to streamline software code reviews, but their ability to produce consistent assessments remains an open question. In this study, we tested four leading LLMs -- GPT-4o mini, GPT-4o, Claude 3.5 Sonnet, and LLaMA 3.2 90B Vision -- on 70 Java commits from both private and public repositories. By setting each model's temperature to zero, clearing context, and repeating the exact same prompts five times, we measured how consistently each model generated code-review assessments. Our results reveal that even with temperature minimized, LLM responses varied to different degrees. These findings highlight a consideration about the inherently limited consistency (test-retest reliability) of LLMs -- even when the temperature is set to zero -- and the need for caution when using LLM-generated code reviews to make real-world decisions.

Related papers

• Empirical Evaluation of Generalizable Automated Program Repair with Large Language Models [4.757323827658957]
  Automated Program Repair proposes bug fixes to aid developers in maintaining software.<n>Recent works have shown that LLMs can be used to generate repairs.<n>We evaluate a diverse set of 13 recent models, including open ones (e.g., Llama 3.3, Qwen 2.5 Coder, and DeepSeek R1 (dist.)) and closed ones (e.g., o3-mini, GPT-4o, Claude 3.7 Sonnet, Gemini 2.0 Flash)
  arXiv  Detail & Related papers  (2025-06-03T18:15:14Z)
• An Empirical Study of Many-to-Many Summarization with Large Language Models [82.10000188179168]
  Large language models (LLMs) have shown strong multi-lingual abilities, giving them the potential to perform Many-to-many summarization (M2MS) in real applications.<n>This work presents a systematic empirical study on LLMs' M2MS ability.
  arXiv  Detail & Related papers  (2025-05-19T11:18:54Z)
• DeepCritic: Deliberate Critique with Large Language Models [77.5516314477878]
  We focus on studying and enhancing the math critique ability of Large Language Models (LLMs) Our developed critique model built on Qwen2.5-7B-Instruct significantly outperforms existing LLM critics on various error identification benchmarks.
  arXiv  Detail & Related papers  (2025-05-01T17:03:17Z)
• See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknesses [51.975495361024606]
  We propose a Self-Challenge evaluation framework with human-in-the-loop. Starting from seed instances that GPT-4 fails to answer, we prompt GPT-4 to summarize error patterns that can be used to generate new instances. We then build a benchmark, SC-G4, consisting of 1,835 instances generated by GPT-4 using these patterns, with human-annotated gold responses.
  arXiv  Detail & Related papers  (2024-08-16T19:01:52Z)
• UBENCH: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions [10.28688988951815]
  UBENCH is a benchmark for evaluating large language models. It includes 3,978 multiple-choice questions covering knowledge, language, understanding, and reasoning abilities. We also evaluate the reliability of 15 popular LLMs, finding GLM4 to be the most outstanding.
  arXiv  Detail & Related papers  (2024-06-18T16:50:38Z)
• Evaluating Students' Open-ended Written Responses with LLMs: Using the RAG Framework for GPT-3.5, GPT-4, Claude-3, and Mistral-Large [0.0]
  evaluating open-ended written responses from students is an essential yet time-intensive task for educators. Recent developments in Large Language Models (LLMs) present a promising opportunity to balance the need for thorough evaluation with efficient use of educators' time.
  arXiv  Detail & Related papers  (2024-05-08T22:23:58Z)
• PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion [96.47420221442397]
  We construct adversarial user instructions by attacking user instructions at sentence, semantic, and multi-language levels. We test 3 closed-source and 4 open-source LLMs using a benchmark that incorporates robustness settings. We find that GPT-4 exhibits the highest performance and strong robustness in our benchmark.
  arXiv  Detail & Related papers  (2024-03-06T15:33:32Z)
• Fine-Tuning and Prompt Engineering for Large Language Models-based Code Review Automation [4.941630596191807]
  Fine-tuning and prompting are common approaches to leveraging Large Language Models (LLMs) for code review automation. We use model fine-tuning and inference techniques (i.e., zero-shot learning, few-shot learning and persona) on LLMs-based code review automation. Our results show that GPT-3.5 with zero-shot learning achieves 73.17% -74.23% higher EM than the Guo et al.'s approach.
  arXiv  Detail & Related papers  (2024-02-01T03:10:26Z)
• Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment [82.60594940370919]
  We propose the FlipFlop experiment to study the multi-turn behavior of Large Language Models (LLMs) We show that models flip their answers on average 46% of the time and that all models see a deterioration of accuracy between their first and final prediction, with an average drop of 17% (the FlipFlop effect) We conduct finetuning experiments on an open-source LLM and find that finetuning on synthetically created data can mitigate - reducing performance deterioration by 60% - but not resolve sycophantic behavior entirely.
  arXiv  Detail & Related papers  (2023-11-14T23:40:22Z)
• PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion [96.47420221442397]
  We introduce the PowerPoint Task Completion benchmark to assess the ability of Large Language Models to finish multi-turn, multi-modal instructions. We also propose the PPTX-Match Evaluation System that evaluates if LLMs finish the instruction based on the prediction file rather than the label API sequence. The results show that GPT-4 outperforms other LLMs with 75.1% accuracy in single-turn dialogue testing but faces challenges in completing entire sessions, achieving just 6% session accuracy.
  arXiv  Detail & Related papers  (2023-11-03T08:06:35Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)
• Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness [16.35655151252159]
  We introduce BSDetector, a method for detecting bad and speculative answers from a pretrained Large Language Model. Our uncertainty quantification technique works for any LLM accessible only via a black-box API.
  arXiv  Detail & Related papers  (2023-08-30T17:53:25Z)

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.