# Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation Source: [Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation]() Collection index: [llms.txt]() Data updated: 2026-08-04T05:00:15.721Z Authors: Hanwen Shen, Ting Ying, Jiajie Lu, Shanshan Wang Published: 2026-03-14T01:37:23.000Z ## Abstract Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts. We demonstrate via out-of-distribution (OOD) detection that these high-bias prompts cause a distribution shift, degrading static model performance. To enable real-time correction, we propose CAP-TTA, a test-time adaptation framework. CAP-TTA triggers context-aware LoRA updates only when a bias-risk score exceeds a set threshold. By utilizing an offline precomputed diagonal preconditioner, it ensures fast and stable optimization. Across multiple benchmarks and human evaluations, CAP-TTA effectively reduces toxicity/bias score with significantly lower latency than standard optimization methods (e.g., AdamW or SGD). Furthermore, it prevents catastrophic forgetting, and substantially improves narrative fluency over state-of-the-art baselines without compromising debiasing performance. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Bias Mitigation in Text Generation on BiasBench toxic prompts](): Bias mitigation in text generation; BiasBench toxic prompts; Perplexity: 13.119. - [Bias Evaluation on Human Evaluation Toxic Prompts](): Bias Evaluation; Human Evaluation Toxic Prompts; Biased Item Count: 2. ## Original sources and implementation [Original paper]() [PDF]()