Measuring and Mitigating Bias in Code Generated by Large Language Models

• URL: http://arxiv.org/abs/2606.00049v1
• Date: Tue, 05 May 2026 14:03:16 GMT
• Title: Measuring and Mitigating Bias in Code Generated by Large Language Models
• Abstract summary: This paper focuses on GPT-4o and Gemini, mainstream tools for code generation, and proposes a framework for evaluating bias in LLM-generated code.<n>We use two metrics: the code bias score (CBS) and the attribute change ratio (ACR), to quantify the prevalence of bias and the degree of influence of different attributes.<n>In addition, we investigate four lightweight mitigation strategies: Few-Shot, Chain-of-Thought, Few-Shot Chain-of-Thought, and Multi-agent, aimed at mitigating bias in generated code.
• Score: 1.3314577932913607
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) are widely recognised for their applications in natural language generation and are increasingly used for code generation tasks. However, concerns about bias in their generated outputs remain significant. This paper focuses on GPT-4o and Gemini, mainstream tools for code generation, and proposes a framework for evaluating bias in LLM-generated code, specifically examining the influence of protected attributes, prompts and web-search capability. We use two metrics: the code bias score (CBS) and the attribute change ratio (ACR), to quantify the prevalence of bias and the degree of influence of different attributes, respectively. In addition, we investigate four lightweight mitigation strategies: Few-Shot, Chain-of-Thought, Few-Shot Chain-of-Thought, and Multi-agent, aimed at mitigating bias in generated code. Our findings reveal that bias remains prevalent across different protected attributes and datasets even after applying mitigation strategies, highlighting the need for more effective approaches to reduce bias in AI-driven code generation systems.

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)
• An Ensemble Framework for Unbiased Language Model Watermarking [60.99969104552168]
  We propose ENS, a novel ensemble framework that enhances the detectability and robustness of unbiased watermarks.<n>ENS sequentially composes multiple independent watermark instances, each governed by a distinct key, to amplify the watermark signal.<n> Empirical evaluations show that ENS substantially reduces the number of tokens needed for reliable detection and increases resistance to smoothing and paraphrasing attacks.
  arXiv  Detail & Related papers  (2025-09-28T19:37:44Z)
• Unmasking Conversational Bias in AI Multiagent Systems [1.0705399532413618]
  biases that may arise in multi-agent systems involving generative models remain under-researched.<n>We present a framework designed to quantify biases within multi-agent systems of conversational Large Language Models.<n>The bias observed in the echo-chamber experiment remains undetected by current state-of-the-art bias detection methods.
  arXiv  Detail & Related papers  (2025-01-24T09:10:02Z)
• Towards Resource Efficient and Interpretable Bias Mitigation in Large Language Models [1.787433808079955]
  Large language models (LLMs) have been observed to perpetuate unwanted biases in training data.<n>In this paper, we mitigate bias by leveraging small biased and anti-biased expert models to obtain a debiasing signal.<n> Experiments on mitigating gender, race, and religion biases show a reduction in bias on several local and global bias metrics.
  arXiv  Detail & Related papers  (2024-12-02T16:56:08Z)
• Responsible AI in NLP: GUS-Net Span-Level Bias Detection Dataset and Benchmark for Generalizations, Unfairness, and Stereotypes [6.30817290125825]
  We introduce the GUS-Net Framework, comprising the GUS dataset and a multi-label token-level detector for span-level analysis of social bias.<n>The GUS dataset contains 3,739 unique snippets across multiple domains, with over 69,000 token-level annotations.<n>We formulate bias detection as multi-label token-level classification and benchmark both encoder-based models and decoder-based large language models.
  arXiv  Detail & Related papers  (2024-10-10T21:51:22Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• Identifying and Mitigating Social Bias Knowledge in Language Models [52.52955281662332]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.<n>FAST surpasses state-of-the-art baselines with superior debiasing performance.<n>This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• Learnable Item Tokenization for Generative Recommendation [113.80559032128065]
  We propose LETTER (a LEarnable Tokenizer for generaTivE Recommendation), which integrates hierarchical semantics, collaborative signals, and code assignment diversity.<n> LETTER incorporates Residual Quantized VAE for semantic regularization, a contrastive alignment loss for collaborative regularization, and a diversity loss to mitigate code assignment bias.
  arXiv  Detail & Related papers  (2024-05-12T15:49:38Z)
• GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models [83.30078426829627]
  Large language models (LLMs) have gained popularity and are being widely adopted by a large user community. The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability. We propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs to assess bias in models.
  arXiv  Detail & Related papers  (2023-12-11T12:02:14Z)
• Bias Testing and Mitigation in LLM-based Code Generation [27.997232692723767]
  This paper presents a novel bias testing framework specifically designed for code generation tasks.<n>We conduct an empirical study on the biases in code generated by five widely studied LLMs.<n>We study five bias mitigation prompt strategies that are commonly used in current code generation scenarios.
  arXiv  Detail & Related papers  (2023-09-03T07:14:49Z)
• A Simple, Yet Effective Approach to Finding Biases in Code Generation [16.094062131137722]
  This work shows that current code generation systems exhibit undesired biases inherited from their large language model backbones. We propose the "block of influence" concept, which enables a modular decomposition and analysis of the coding challenges.
  arXiv  Detail & Related papers  (2022-10-31T15:06:15Z)
• Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders [51.691585766702744]
  We propose a variant of Adversarial Autoencoder which uses a mirrored Wasserstein loss in the discriminator to enforce better semantic-level reconstruction. We put forward an alternative measure of anomaly score to replace the reconstruction-based metric. Our method outperforms the current state-of-the-art methods for anomaly detection on several OOD detection benchmarks.
  arXiv  Detail & Related papers  (2020-03-24T08:26:58Z)

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.