Large language models (LLMs) are increasingly used as judges for code evaluation, assessing correctness without reference implementations. This study investigates whether LLM judges can fairly evaluate semantically equivalent code that differs in superficial aspects such as variable names, comments, or formatting. The authors define six types of potential bias, conduct experiments across five programming languages and multiple LLMs, and find that all tested judges exhibit both positive and negative biases, leading to inflated or unfairly low scores even when prompted to generate test cases.
arXiv:2606. 08840v1 Announce Type: new Abstract: Code generation models are typically compared using compact execution benchmarks and aggregate pass rates, but such summaries obscure how performance varies across programming languages, problem families, and failure modes.
arXiv:2609.24516v1 Announce Type: new Abstract: In recent years, large language models (LLMs) have emerged as a popular alternative for evaluation. Often referred to as LLMs as judges (LLJs), these s...
arXiv:2606. 00049v1 Announce Type: cross Abstract: Large language models (LLMs) are widely recognised for their applications in natural language generation and are increasingly used for code generation tasks.
arXiv:2606. 12864v1 Announce Type: cross Abstract: Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored.
The paper introduces PolyHuman, a dataset of human-written programs in C++, Java, and Python, to test whether large language models can judge functional equivalence across languages. Using this dataset, the authors evaluate several open-weight and proprietary LLMs, finding that models struggle more with harder problems, show language-specific biases, and rely partly on superficial similarity cues. They also observe run‑to‑run instability in GPT‑o4‑mini, concluding that current LLMs do not reliably capture functional equivalence within or across programming languages.
The paper examines LLM-as-a-Judge systems used to assess AI-generated text, questioning the assumption that judgments are derived from reasoning over responses and rubrics. It finds that classifiers trained solely on rubric text can predict judge outputs, indicating that rubrics contain recoverable evaluative signals independent of the responses. Counterfactual experiments show judges often fail to adjust decisions when either the response or rubric criterion is reversed, raising doubts about the reliability of rubric-based LLM evaluation.
arXiv:2508. 16131v3 Announce Type: replace-cross Abstract: Code completion entails the task of providing missing tokens given a surrounding context.
The paper demonstrates that large language model (LLM) evaluators, whether reward‑model based or prompted LLM‑as‑a‑Judge, exhibit significant language bias in multilingual settings. Experiments with semantically identical instruction‑response pairs across 23 languages reveal that lower‑resource languages receive higher scores, a bias that persists across eight open‑weight evaluators and is not detectable by standard pairwise accuracy metrics. The authors link the bias to model uncertainty and language identity, showing it cannot be explained by content difficulty alone.
arXiv:2609.37097v1 Announce Type: new Abstract: The rapid growth of submissions and reviewing workload has accelerated the use of large language models (LLMs) in peer review. Prior studies suggest th...
arXiv:2607. 14816v1 Announce Type: cross Abstract: Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias.
The paper introduces LongJudgeBench, a benchmark designed to evaluate large language models (LLMs) acting as judges for long-form text generation. It highlights that long-form evaluation requires complex, document-level assessments beyond simple length, such as organization, coverage, depth, consistency, and scenario-specific quality. Experiments show a significant reliability gap among current LLM judges, indicating instability across scenarios and limited effectiveness of rubrics or references.
arXiv:2510. 07315v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their vibe check.