Output Format Biases in the Evaluation of Large Language Models for Code Translation

• URL: http://arxiv.org/abs/2403.17214v2
• Date: Mon, 13 Oct 2025 01:19:11 GMT
• Title: Output Format Biases in the Evaluation of Large Language Models for Code Translation
• Authors: Marcos Macedo, Yuan Tian, Filipe R. Cogo, Bram Adams,
• Abstract summary: It is crucial to understand and address variations in output format.<n>Non-code elements can interfere with evaluation metrics, resulting in biased assessments of model performance and comparisons.<n>We propose a strategic combination of prompt engineering and regular expressions that effectively extracts source code from mixed-format outputs.
• Score: 6.75681623173699
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Code translation between programming languages (PLs) is a critical task in software engineering, facilitating the modernization of legacy systems, ensuring cross-platform compatibility, and enhancing software performance. Most existing studies instruct LLMs to perform code translation and evaluate their performance by either running the generated outputs through test suites or comparing them to reference outputs (ground truth). These outputs, however, may contain not only executable source code but also additional non-code elements, such as natural language explanations or formatting tokens. We refer to the combination of source code and non-code elements as the output format. It is crucial to understand and address variations in output format, as non-code elements can interfere with evaluation metrics, resulting in biased assessments of model performance and comparisons. We conduct an empirical analysis of the outputs from eleven instruct-tuned open-source LLMs, across five PLs: C, C++, Go, Java, and Python. The results show that between 26.4% and 73.7% of outputs produced by our evaluated LLMs necessitate post-processing. To mitigate output format bias, we propose a strategic combination of prompt engineering and regular expressions that effectively extracts source code from mixed-format outputs, enabling the eleven open-source models to achieve an average Code Extraction Success Rate (CSR) of 92.73%. Our empirical study confirms that output format bias affects widely used execution-based metrics, i.e., Computational Accuracy (CA), and text-based metrics, i.e., BLEU, CodeBLEU and CrystalBLEU. Additionally, we test five closed-source LLMs and observe that they also generate varying distributions of output formats, which could lead to output format biases. Our results highlight the need to mitigate the output format bias to enable reliable evaluations in LLMs for code translation.

Related papers

• The Hidden Cost of Readability: How Code Formatting Silently Consumes Your LLM Budget [13.419222464653425]
  We evaluate the impact of code formatting on large language models (LLMs) performance and efficiency.<n>Key findings indicate that LLMs can maintain performance across formatted code and unformatted code, achieving an average input token reduction of 24.5%.<n>We develop a bidirectional code transformation tool for format processing, which can be seamlessly integrated into existing inference.
  arXiv  Detail & Related papers  (2025-08-19T09:13:48Z)
• IFEvalCode: Controlled Code Generation [69.28317223249358]
  The paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs.<n>The authors present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages.
  arXiv  Detail & Related papers  (2025-07-30T08:08:48Z)
• NL in the Middle: Code Translation with LLMs and Intermediate Representations [66.41928783565795]
  Large language models (LLMs) produce buggy code translations.<n>We consider whether code translation using LLMs can benefit from intermediate representations via natural language (NL) and abstract syntax trees (ASTs)
  arXiv  Detail & Related papers  (2025-07-11T14:29:21Z)
• ExeCoder: Empowering Large Language Models with Executability Representation for Code Translation [57.604506522287814]
  Existing large language models (LLMs) only learn the contextual semantics of code during pre-training.<n>We propose ExeCoder to utilize executability representations such as functional semantics, syntax structures, and variable dependencies.<n>We show that ExeCoder achieves state-of-the-art performance in code translation, surpassing existing open-source code LLMs by over 10.88% to 38.78% and over 27.44% to 42.97% on two metrics.
  arXiv  Detail & Related papers  (2025-01-30T16:18:52Z)
• Provenance: A Light-weight Fact-checker for Retrieval Augmented LLM Generation Output [49.893971654861424]
  We present a light-weight approach for detecting nonfactual outputs from retrieval-augmented generation (RAG) We compute a factuality score that can be thresholded to yield a binary decision. Our experiments show high area under the ROC curve (AUC) across a wide range of relevant open source datasets.
  arXiv  Detail & Related papers  (2024-11-01T20:44:59Z)
• RAC: Efficient LLM Factuality Correction with Retrieval Augmentation [8.207682890286957]
  Large Language Models (LLMs) exhibit impressive results across a wide range of natural language processing (NLP) tasks, yet they can often produce factually incorrect outputs. This paper introduces a simple but effective low-latency post-correction method, textbfRetrieval Augmented Correction (RAC), aimed at enhancing the factual performance of LLMs without requiring additional fine-tuning.
  arXiv  Detail & Related papers  (2024-10-21T06:11:38Z)
• Large Language Models as Code Executors: An Exploratory Study [29.545321608864295]
  This paper pioneers the exploration of Large Language Models (LLMs) as code executors. We are the first to examine this feasibility across various LLMs, including OpenAI's o1, GPT-4o, GPT-3.5, DeepSeek, and Qwen-Coder. We introduce an Iterative Instruction Prompting (IIP) technique that processes code snippets line by line, enhancing the accuracy of weaker models by an average of 7.22%.
  arXiv  Detail & Related papers  (2024-10-09T08:23:22Z)
• What do Large Language Models Need for Machine Translation Evaluation? [12.42394213466485]
  Large language models (LLMs) can achieve results comparable to fine-tuned multilingual pre-trained language models. This paper explores what translation information, such as the source, reference, translation errors and annotation guidelines, is needed for LLMs to evaluate machine translation quality.
  arXiv  Detail & Related papers  (2024-10-04T09:50:45Z)
• LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs [69.40865293066885]
  We present the first systematic evaluation examining format bias in performance of large language models (LLMs)<n>We present our empirical format bias evaluation spanning four commonly used categories -- multiple-choice question-answer, wrapping, list, and mapping.
  arXiv  Detail & Related papers  (2024-08-16T10:45:45Z)
• Large Language Models for cross-language code clone detection [3.5202378300682162]
  Cross-lingual code clone detection has gained traction with the software engineering community. Inspired by the significant advances in machine learning, this paper revisits cross-lingual code clone detection.
  arXiv  Detail & Related papers  (2024-08-08T12:57:14Z)
• From Effectiveness to Efficiency: Uncovering Linguistic Bias in Large Language Model-based Code Generation [30.914387085368734]
  Large Language Models (LLMs) have demonstrated promising capabilities for code generation. In this paper, we aim to investigate the potential linguistic bias through the lens of English and Chinese.
  arXiv  Detail & Related papers  (2024-06-02T03:22:30Z)
• Grammar-Aligned Decoding [30.972850034752884]
  Large Language Models (LLMs) struggle with reliably generating highly structured outputs, such as program code, mathematical formulas, or well-formed markup. Constrained decoding approaches mitigate this problem by greedily restricting what tokens an LLM can output at each step to guarantee that the output matches a given constraint. In this paper, we demonstrate that GCD techniques can distort the LLM's distribution, leading to outputs that are grammatical but appear with likelihoods that are not proportional to the ones given by the LLM.
  arXiv  Detail & Related papers  (2024-05-31T17:39:15Z)
• SpecTra: Enhancing the Code Translation Ability of Language Models by Generating Multi-Modal Specifications [17.60108067953814]
  Large language models (LLMs) are increasingly being used for the task of automated code translation. We propose SpecTra, a multi-stage approach that uses a novel self-consistency filter to first generate high-quality specifications.
  arXiv  Detail & Related papers  (2024-05-28T20:48:30Z)
• Code Needs Comments: Enhancing Code LLMs with Comment Augmentation [91.52444946362547]
  We introduce a novel data augmentation method that generates comments for existing code, coupled with a data filtering strategy that filters out code data poorly correlated with natural language. We conducted experiments on three code-focused Large Language Models and observed consistent improvements in performance on two widely-used programming skill benchmarks.
  arXiv  Detail & Related papers  (2024-02-20T13:56:38Z)
• Large Language Model-Aware In-Context Learning for Code Generation [75.68709482932903]
  Large language models (LLMs) have shown impressive in-context learning (ICL) ability in code generation. We propose a novel learning-based selection approach named LAIL (LLM-Aware In-context Learning) for code generation.
  arXiv  Detail & Related papers  (2023-10-15T06:12:58Z)
• CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model [58.127534002232096]
  This paper introduces CodeFuse-13B, an open-sourced pre-trained code LLM. It is specifically designed for code-related tasks with both English and Chinese prompts. CodeFuse achieves its effectiveness by utilizing a high quality pre-training dataset.
  arXiv  Detail & Related papers  (2023-10-10T02:38:44Z)
• L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models [102.00201523306986]
  We present L2CEval, a systematic evaluation of the language-to-code generation capabilities of large language models (LLMs) We analyze the factors that potentially affect their performance, such as model size, pretraining data, instruction tuning, and different prompting methods. In addition to assessing model performance, we measure confidence calibration for the models and conduct human evaluations of the output programs.
  arXiv  Detail & Related papers  (2023-09-29T17:57:00Z)
• LeTI: Learning to Generate from Textual Interactions [60.425769582343506]
  We explore LMs' potential to learn from textual interactions (LETI) that not only check their correctness with binary labels but also pinpoint and explain errors in their outputs through textual feedback. Our focus is the code generation task, where the model produces code based on natural language instructions. LETI iteratively fine-tunes the model, using the objective LM, on a concatenation of natural language instructions, LM-generated programs, and textual feedback.
  arXiv  Detail & Related papers  (2023-05-17T15:53:31Z)
• From Words to Code: Harnessing Data for Program Synthesis from Natural Language [12.665932954069476]
  We introduce semantic reranking, a technique to rerank the programs generated by large language models (LLMs) We also introduce temperature mixing, where we combine samples generated by LLMs using both high and low temperatures. We observe substantial gains across domains, with improvements of up to 45% in top-1 accuracy and 34% in top-3 accuracy.
  arXiv  Detail & Related papers  (2023-05-02T16:56:32Z)
• LEVER: Learning to Verify Language-to-Code Generation with Execution [64.36459105535]
  We propose LEVER, a simple approach to improve language-to-code generation by learning to verify the generated programs with their execution results. Specifically, we train verifiers to determine whether a program sampled from the LLMs is correct or not based on the natural language input, the program itself and its execution results. LEVER consistently improves over the base code LLMs(4.6% to 10.9% with code-davinci) and achieves new state-of-the-art results on all of them.
  arXiv  Detail & Related papers  (2023-02-16T18:23:22Z)
• Summarize and Generate to Back-translate: Unsupervised Translation of Programming Languages [86.08359401867577]
  Back-translation is widely known for its effectiveness for neural machine translation when little to no parallel data is available. We propose performing back-translation via code summarization and generation. We show that our proposed approach performs competitively with state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-23T08:20:41Z)

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.