Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Test-time AdaptationSimilar Papers 제목 키워드 기반
Selective Test-Time Debiasing for CLIP via Reward Gating
Vision language models (VLMs) demonstrate strong zero-shot performance, but often perpetuate social stereotypes in person-centric queries, yielding skewed demographic distributions. Current debiasing methods apply unifor…
Reinforcement LearningTest-time AdaptationTechnical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting
We present a theoretical framework for M-FISHER, a method for sequential distribution shift detection and stable adaptation in streaming data. For detection, we construct an exponential martingale from non-conformity sco…
Test-time AdaptationBiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision-Language Models
Vision language foundation models such as CLIP exhibit impressive zero-shot generalization yet remain vulnerable to spurious correlations across visual and textual modalities. Existing debiasing approaches often address …
Zero-shot GeneralizationTest-time AdaptationAdaptive Debiasing Tsallis Entropy for Test-Time Adaptation
Mainstream Test-Time Adaptation (TTA) methods for adapting vision-language models, e.g., CLIP, typically rely on Shannon Entropy (SE) at test time to measure prediction uncertainty and inconsistency. However, since CLIP …
Test-time AdaptationQuantum Fisher-Preconditioned Reinforcement Learning: From Single-Qubit Control to Rayleigh-Fading Link Adaptation
In this letter, we propose Quantum-Preconditioned Policy Gradient (QPPG), a natural gradient-based algorithm for link adaptation that whitens policy updates using the full inverse quantum Fisher information with Tikhonov…