跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1199新增论文
+950其中 AI 相关
+132已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 08:48 · 全站最近入库:2026-11-20 16:53各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 18:44 — 2026-11-20 18:44(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-20 08:48最近发现新增版本:2026-11-20 16:53库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

28,609 已收录论文23,738 AI 相关8,785 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 2 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 08:46(北京时间)
版本更新 · v2arXiv:2606.28725

DriftGuard: Safety-Aware Multi-Monitor Detection and Selective Adaptation for Evolving Toxicity Moderation

Yuting Xin, Hanyu Cai, Binqi Shen, Lier Jin, Lan Hu

原文摘要

Automated toxicity moderation systems operate in dynamic online environments where harmful behavior evolves through coded language, shifting targets, and strategic adaptation to enforcement. Existing drift detection methods often focus on global distributional change, but such signals may miss safety-relevant shifts that emerge in localized harm subspaces or high-risk model-error regions. This paper introduces DriftGuard, a safety-aware adaptive moderation framework that combines multi-monitor drift detection with selective model updating. The framework tracks global text drift, identity-harm drift, model uncertainty, toxic-risk drift, and false-negative-risk drift. When safety-relevant change is detected, the model is updated using a hard-mix adaptation set that prioritizes likely false negatives, identity-related high-risk examples, false-positive-risk examples, and uncertain boundary cases. Experiments on Civil Comments temporal shift and Jigsaw-to-DynaHate cross-dataset shift show that safety-aware monitors detect risks missed by global drift alone. Hard-mix adaptation improves toxic recall and accuracy over no-update and random-balanced baselines. It raises toxic recall from 0.8453 to 0.8777 on Civil Comments and from 0.7107 to 0.8523 on DynaHate. Bootstrap analysis further shows stable DynaHate safety gains, with toxic recall increasing by 0.1418 and false-negative prevalence decreasing by 0.0781. Overall, DriftGuard links safety-aware drift detection with targeted, lightweight model updating for more robust adaptive toxicity moderation.

cs.CL

版本更新 · v2arXiv:2608.08942

Prompt Privilege in Large Language Models: Measuring and Mitigating Barriers to Equitable AI Access

Lier Jin, Lan Hu, Binqi Shen, Hanyu Cai, Yuting Xin

原文摘要

Large language models (LLMs) are increasingly used in healthcare, education, public services, and everyday decision making. They should provide comparable assistance regardless of users' literacy, communication style, or prompt-engineering expertise. However, research on prompt robustness primarily focuses on adversarial attacks, prompt injection, and prompt optimization, overlooking whether semantically equivalent requests receive different responses simply because they are phrased differently. We call this accessibility challenge "Prompt Privilege": users with greater prompting expertise obtain better model performance despite expressing the same underlying intent. To address this problem, we propose the Prompt Equity Score (PES), a metric for evaluating performance consistency across user populations, and the Prompt Equity Transformer (PET), an LLM-based agent that automatically transforms user requests into semantically equivalent prompts while preserving their intent. PET shifts prompt optimization from users to AI systems, serving as an accessibility layer between users and foundation models. Experiments on MedQA reveal measurable prompt privilege, with statistically significant performance disparities between low-literacy and expert-prompting cohorts. Applying PET reduces these differences, with no pairwise cohort differences reaching statistical significance in our evaluation. These results suggest that accessibility-oriented prompt normalization can improve equitable AI access. By introducing prompt privilege as a new dimension of AI accessibility and PET as a practical solution, this work advances system-centered accessibility and provides a foundation for fairer, more trustworthy, and more inclusive AI systems.

cs.CL