让大模型推理更公平，不重训就能大幅降低偏见。
COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models
- 解码时通过反事实提示和对齐机制抑制属性偏见。
- 在多个基准上减少30%-55%的偏见，准确率几乎不变。
- 无需重训练或额外模型，适合安全敏感场景使用。
大语言模型在链式思维生成过程中可能暴露并放大社会偏见。我们提出COFT（公平链式思维），一种无需训练的解码方法，在推理阶段实现细粒度的公平性控制，并对任意冻结的因果语言模型提供分布无关的边际有效性保证（在可交换性假设下）。COFT分三步：首先，用中性标记替换敏感信息生成反事实提示；其次，通过轻量级对数融合比较真实与反事实的输出分布，抑制属性驱动偏见；最后，采用双分支分割-合取校准，在用户设定的风险水平下认证每一步的候选词集合。我们在六个模型和多个偏见评测集上评估，方法使标准偏见指标平均降低38%（范围30%-55%），任务性能与语言质量基本保持不变，推理准确性波动在运行间噪声范围内。计算开销极小，相当于一次额外缓存前向传播（≤11%）。COFT为更安全的链式思维生成提供了清晰、可审计的路径，显著降低偏见，几乎无性能损失，且无需重新训练、辅助分类器或权重访问。
原文摘要 · Abstract (English)
Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought), a training-free decoding method that applies token-level fairness control at decode time, with distribution-free marginal validity guarantees (under exchangeability) for any frozen causal language model. COFT operates in three stages. First, it creates a masked counterfactual prompt by replacing sensitive spans with neutral tokens. Second, it compares the factual and masked logit distributions through lightweight logit fusion to attenuate attribute-driven biases. Third, it uses dual-branch split-conformal calibration to certify per-step candidate token sets at a user-chosen risk level. We evaluate COFT across six models and multiple bias benchmarks. Our method reduces standard bias metrics by 30-55% (median 38%) while preserving task utility and language quality. Reasoning accuracies remain unchanged within run-to-run noise margins. The computational overhead is modest, equivalent to one additional cached forward pass (<=11%). COFT offers a clear, auditable path to safer CoT generation with significant bias reduction, negligible utility loss, and no requirement for retraining, auxiliary classifiers, or weight access.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。