paper-with-me

홈 › Papers

Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation

2026-03-14 · Hanwen Shen, Ting Ying, Jiajie Lu, Shanshan Wang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.13683

Code (0)

등록된 구현이 없습니다.

Tasks

Test-time Adaptation

Similar Papers 제목 키워드 기반

Selective Test-Time Debiasing for CLIP via Reward Gating

2026-07-01 · Jaeho Han, Jisoo Yang, Hyeondong Woo, Mingyu Jeon 외 arxiv

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 Adaptation

Technical note on Sequential Test-Time Adaptation via Martingale-Driven Fisher Prompting

2025-10-04 · Behraj Khan, Tahir Qasim Syed arxiv

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 Adaptation

BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision-Language Models

2026-01-05 · Sunny Gupta, Shounak Das, Amit Sethi arxiv

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 Adaptation

Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation

2026-02-12 · Xiangyu Wu, Dongming Jiang, Feng Yu, Yueying Tian 외 arxiv

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 Adaptation

Quantum Fisher-Preconditioned Reinforcement Learning: From Single-Qubit Control to Rayleigh-Fading Link Adaptation

2025-06-18 · Oluwaseyi Giwa, Muhammad Ahmed Mohsin, Muhammad Ali Jamshed

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…