让大模型自己发现并修正偏见，提升公平性。
Self-Debias: Self-correcting for Debiasing Large Language Models
- 将去偏视为资源重分配，动态调整推理路径概率
- 仅用2万标注样本即实现高效去偏，保持推理能力
- 支持在线自我优化，无需持续人工干预
尽管大语言模型展现出卓越的推理能力，但内在的社会偏见常在思维链（CoT）过程中传播，导致持续的“偏见扩散”。现有方法多依赖静态约束或外部干预，无法在偏见产生后及时识别并中断。为此，我们提出Self-Debias，一种渐进式框架，旨在赋予模型内在的自我修正能力。具体地，我们将去偏过程重构为战略资源再分配问题，将模型输出的概率质量视为有限资源，从有偏启发式路径重新分配至无偏推理路径。与标准偏好优化中广泛施加惩罚不同，Self-Debias采用细粒度轨迹级目标，并受动态去偏约束，使模型能选择性修正有偏推理后缀，同时保留有效的上下文前缀。此外，我们引入在线自进化机制，通过一致性过滤自主生成监督信号。仅需20,000个标注样本，Self-Debias即可激活高效自我修正，在不依赖持续外部监督的前提下，显著提升去偏效果并保持通用推理能力。
原文摘要 · Abstract (English)
Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Thought (CoT) process, leading to continuous "Bias Propagation". Existing debiasing methods primarily focus on static constraints or external interventions, failing to identify and interrupt this propagation once triggered. To address this limitation, we introduce Self-Debias, a progressive framework designed to instill intrinsic self-correction capabilities. Specifically, we reformulate the debiasing process as a strategic resource redistribution problem, treating the model's output probability mass as a limited resource to be reallocated from biased heuristics to unbiased reasoning paths. Unlike standard preference optimization which applies broad penalties, Self-Debias employs a fine-grained trajectory-level objective subject to dynamic debiasing constraints. This enables the model to selectively revise biased reasoning suffixes while preserving valid contextual prefixes. Furthermore, we integrate an online self-improvement mechanism utilizing consistency filtering to autonomously synthesize supervision signals. With merely 20k annotated samples, Self-Debias activates efficient self-correction, achieving superior debiasing performance while preserving general reasoning capabilities without continuous external oversight.
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。