Scoring Verifiers: Evaluating Synthetic Verification in Code and Reasoning

• URL: http://arxiv.org/abs/2502.13820v1
• Date: Wed, 19 Feb 2025 15:32:11 GMT
• Title: Scoring Verifiers: Evaluating Synthetic Verification in Code and Reasoning
• Authors: Aleksander Ficek, Somshubra Majumdar, Vahid Noroozi, Boris Ginsburg,
• Abstract summary: We introduce benchmarks designed to evaluate the impact of synthetic verification methods on assessing solution correctness. We analyze synthetic verification methods in standard, reasoning-based, and reward-based LLMs. Our results show that recent reasoning models significantly improve test case generation and that scaling test cases enhances verification accuracy.
• Score: 59.25951947621526
• License:
• Abstract: Code verification has recently found great success as a critical component in training large scale reasoning models for coding. Synthetic techniques such as self-generated test cases and reward models provide a way to enhance code capabilities beyond predefined tests. Building on these advancements, we propose new benchmarks designed to systematically evaluate the impact of synthetic verification methods on assessing solution correctness. We introduce HE-R, HE-R+, MBPP-R, and MBPP-R+, which transform existing coding benchmarks into scoring and ranking datasets to evaluate the effectiveness of synthetic verifiers. Using these benchmarks, we analyze synthetic verification methods in standard, reasoning-based, and reward-based LLMs. Our results show that recent reasoning models significantly improve test case generation and that scaling test cases enhances verification accuracy.

Related papers

• Automated Refactoring of Non-Idiomatic Python Code: A Differentiated Replication with LLMs [54.309127753635366]
  We present the results of a replication study in which we investigate GPT-4 effectiveness in recommending and suggesting idiomatic actions. Our findings underscore the potential of LLMs to achieve tasks where, in the past, implementing recommenders based on complex code analyses was required.
  arXiv  Detail & Related papers  (2025-01-28T15:41:54Z)
• Human-Calibrated Automated Testing and Validation of Generative Language Models [3.2855317710497633]
  This paper introduces a comprehensive framework for the evaluation and validation of generative language models (GLMs) It focuses on Retrieval-Augmented Generation (RAG) systems deployed in high-stakes domains such as banking.
  arXiv  Detail & Related papers  (2024-11-25T13:53:36Z)
• Aligning Model Evaluations with Human Preferences: Mitigating Token Count Bias in Language Model Assessments [2.1370543868467275]
  This follow-up paper explores methods to align Large Language Models evaluator preferences with human evaluations. We employed Bayesian statistics and a t-test to quantify this bias and developed a recalibration procedure to adjust the GPTScorer. Our findings significantly improve aligning the recalibrated LLM evaluator with human evaluations across multiple use cases.
  arXiv  Detail & Related papers  (2024-07-05T09:26:40Z)
• Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models [89.88010750772413]
  Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs) Our work delves into these specific flaws associated with question-answer (Q-A) pairs, a prevalent type of synthetic data, and presents a method based on unlearning techniques to mitigate these flaws. Our work has yielded key insights into the effective use of synthetic data, aiming to promote more robust and efficient LLM training.
  arXiv  Detail & Related papers  (2024-06-18T08:38:59Z)
• Improving the Validity and Practical Usefulness of AI/ML Evaluations Using an Estimands Framework [2.4861619769660637]
  We propose an estimands framework adapted from international clinical trials guidelines. This framework provides a systematic structure for inference and reporting in evaluations. We demonstrate how the framework can help uncover underlying issues, their causes, and potential solutions.
  arXiv  Detail & Related papers  (2024-06-14T18:47:37Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• Don't Make Your LLM an Evaluation Benchmark Cheater [142.24553056600627]
  Large language models(LLMs) have greatly advanced the frontiers of artificial intelligence, attaining remarkable improvement in model capacity. To assess the model performance, a typical approach is to construct evaluation benchmarks for measuring the ability level of LLMs. We discuss the potential risk and impact of inappropriately using evaluation benchmarks and misleadingly interpreting the evaluation results.
  arXiv  Detail & Related papers  (2023-11-03T14:59:54Z)
• From Static Benchmarks to Adaptive Testing: Psychometrics in AI Evaluation [60.14902811624433]
  We discuss a paradigm shift from static evaluation methods to adaptive testing. This involves estimating the characteristics and value of each test item in the benchmark and dynamically adjusting items in real-time. We analyze the current approaches, advantages, and underlying reasons for adopting psychometrics in AI evaluation.
  arXiv  Detail & Related papers  (2023-06-18T09:54:33Z)
• Energy-bounded Learning for Robust Models of Code [16.592638312365164]
  In programming, learning code representations has a variety of applications, including code classification, code search, comment generation, bug prediction, and so on. We propose the use of an energy-bounded learning objective function to assign a higher score to in-distribution samples and a lower score to out-of-distribution samples in order to incorporate such out-of-distribution samples into the training process of source code models.
  arXiv  Detail & Related papers  (2021-12-20T06:28:56Z)

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.