English(EN) Circuit Oracle: Automating Attribution Graph Analysis via Natural-Language Queries

新AI工具可自动分析语言模型归因图

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-04 05:00

研究人员开发了“Circuit Oracle”系统，旨在自动化机械可解释性中归因图的分析。该系统使用多代理工具和自然语言查询来解释这些图，这些图映射了语言模型中特征之间的因果边。虽然Circuit Oracle在检测虚假特征方面显示出潜力，准确率达到78.2%，但在提取禁忌微调模型的隐藏知识和进行抑制越狱方面不如现有方法有效。 AI

影响该工具可以通过自动化分析复杂的模型行为来加速安全研究，尽管目前在某些任务上的表现表明还需要进一步开发。

排序理由该条目描述了一篇关于机械可解释性中归因图分析新颖系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

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: 42 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了一篇关于机械可解释性中归因图分析新颖系统的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
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, infra; 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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Shariar Kabir, Hong Kiat Tan, Swastik Agrawal, Sai V R Chereddy, Sriram Balasubramanian · 2026-11-04 05:00

Circuit Oracle：通过自然语言查询自动化归因图分析

arXiv:2611.00420v1 Announce Type: new Abstract: Attribution graphs, an emerging tool in mechanistic interpretability, use transcoders to decompose language model computations into sparse interpretable features connected by causal edges. However, turning a graph into a safety-rele…

本文如何被排名

报道来源 [1]

Circuit Oracle：通过自然语言查询自动化归因图分析

相关实体

相关话题