一句话：提出 VS Code 扩展 FairLint-DL，在训练前用信息论 QID 指标检测并定位深度学习模型中的公平性偏见。
现有公平性工具多为训练后评估框架，需走完整个模型开发流程才能发现偏见。本文提出 FairLint-DL：一个 VS Code 扩展，把公平性测试“左移”到训练前，直接在表格数据集上做 IDE 原生检测。它训练可配置深度网络作代理模型，用基于 Shannon 熵与最小熵的量化个体歧视（QID）指标度量受保护属性对预测的因果影响，并实现两阶段梯度引导搜索发现歧视实例、经敏感度分析把偏见定位到层与神经元的因果调试流水线，以及基于 SHAP 与 LIME 的可解释性引擎。在 Adult、German Credit、Bank Marketing 上评估，各数据集问题差异显著：Adult 有 96.0% 实例的 QID 超过 0.1 bit 阈值，均值 0.619 bit，disparate impact ratio 为 0.581，违反五分之四法则；缓存模型下 12 秒内即可给出结果。
Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model development lifecycle before assessing bias. We present FairLint-DL, a Visual Studio Code extension that implements a shift-left approach to fairness testing by enabling pre-training, IDE-native bias detection directly on tabular datasets. FairLint-DL trains a configurable deep neural network as a proxy model and applies information-theoretic Quantitative Individual Discrimination (QID) metrics. Grounded in Shannon and min-entropy, QID quantifies the causal influence of protected attributes on predictions. The system implements a two-phase gradient-guided search algorithm for discovering discriminatory instances, a causal de- bugging pipeline that localizes bias to specific network layers and neurons via sensitivity analysis, and dual explainability engines using SHAP and LIME for feature-level attribution. Evaluation on three tabular benchmarks (Adult Census Income, German Credit, and Bank Marketing) reveals fairness concerns that vary widely across datasets: on Adult, 96.0% of analyzed instances exhibit QID above the 0.1-bit significance threshold, with a mean QID of 0.619 bits and a disparate impact ratio of 0.581, violating the four-fifths legal rule. FairLint-DL produces these results within 12 seconds on cached models, demonstrating the feasibility of integrating fairness analysis into the developer workflow without significant overhead.