English(EN) Robust Explanations for User Trust in Enterprise NLP Systems

新框架评估黑盒企业系统中NLP解释的鲁棒性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-04-28 04:00

提出了一种评估企业NLP系统中解释鲁棒性的新框架。该框架使用留一法遮挡方法来评估token级解释在各种扰动下的稳定性。研究发现，与较小的encoder-based模型相比，像Llama 70B这样较大的decoder-based LLM提供了更稳定的解释，稳定性的提高与模型规模相关。 AI

影响为企业使用，尤其是在合规敏感应用中，选择更可靠的NLP模型提供了一种方法。

排序理由学术论文，提出了一种新的NLP解释评估框架。

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 学术论文，提出了一种新的NLP解释评估框架。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 163 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.CL TIER_1 English(EN) · Guilin Zhang, Kai Zhao, Jeffrey Friedman, Xu Chu, Amine Anoun, Jerry Ting · 2026-04-28 04:00

企业NLP系统中用户信任的稳健解释

arXiv:2604.12069v2 Announce Type: replace Abstract: Robust explanations are increasingly required for user trust in enterprise NLP, yet pre-deployment validation is difficult in the common case of black-box deployment (API-only access) where representation-based explainers are in…