Beyond Generation: Leveraging LLM Creativity to Overcome Label Bias in Classification

Large Language Models (LLMs) exhibit impressive capabilities in In-Context Learning (ICL) but are prone to label bias-an undesirable tendency to favor certain answers. Existing calibration methods mitigate bias by leveraging in-domain data, yet such data is often unavailable in real-world scenarios. To address this limitation, we propose SDC (Synthetic Data Calibration), a simple-yet-effective approach that generates synthetic in-domain data from a few in-context demonstrations and utilizes it for calibration. By approximating the benefits of real in-domain data, SDC effectively reduces label bias without requiring access to actual domain-specific inputs. Experimental evaluations on 279 classification and multiple-choice tasks from the SUPER-NATURALINSTRUCTIONS benchmark. The results show that SDC significantly reduces label bias, achieving an average Bias Score reduction of 57.5%, and outperforming all competitive baselines. Moreover, when combined with Leave-One-Out Calibration (LOOC), SDC further improves performance, underscoring its effectiveness and generalizability in enhancing the reliability of LLMs.