Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
Another 215 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 VERA,审计 LLM 漏洞解释里的虚构推理
Published Oct 5
Evaluated models sonnet-5 , gemma-4-26b , llama-4-maverick and others8 系统评估循环语言模型加深 loop 后的 CoT 可监控性
Published Oct 2
Evaluated models Ouro-1.4B-Thinking , Ouro-2.6B-Thinking , Nanbeige4.2-3B and others4 Abstract 加深 loop 可在部分压力测试任务降低可监测性,循环架构本身并不必然更难监测。这项工作评估 LoopLM 的 CoT 可监测性:加深共享层的重复次数,以及“有循环结构”本身,会不会让决策关键因素更少出现在可监测文本里。
构建编码 RL 奖励作弊测试台 CATCH 并检验 CoT 监控失效
Published Sep 30
Evaluated models Qwen3-4B , Qwen3.5-27B Abstract CATCH 用双运行金标签研究编码 RL 的奖励黑客,并观察到监控会被注释适应削弱。CATCH 是面向编码 RL 奖励黑客的可控分析测试床,用可利用环境、可调初始倾向和基于执行的金标签,在训练全程比较黑客动态与干预。
提出 FAME,用反事实概念漂移评测智能体虚假记忆
Published Sep 30
Evaluated models Llama-3B Abstract FAME 用反事实引起的隐状态概念漂移,在出答案前区分忠实记忆与虚假记忆。FAME 是一个免训练的评测框架,用来判断自主智能体的记忆在虚假相关、环境偏移或知识冲突下是否已变成虚假记忆。 。
测量思维链将提示中 PII 复述进轨迹的泄漏并评测轻量检测器
Published Mar 6
Evaluated models Llama 3.3:70B , Claude Opus , Mixtral 8×22B and others7 Abstract 作者称 CoT 抬高逐字泄漏且随模型与预算而变,检测器也需按模型选择。在“不要复述 PII”的输出策略下,本文用 black-box 协议测量提示词中的 PII 被写回 CoT 与答案的情况,并比较轻量 gatekeeper。
提出约束对抗搜索红队框架,系统发现模型多类鲁棒性漏洞
Published Dec 22, 2025
Evaluated models GPT-OSS-20B , LLaMA-2-13B , Claude-2 构建 FindTheFlaws 并评测模型发现长解答推理缺陷的能力
Published Mar 29, 2025
Evaluated models gpt-4o-2024-11-20 , o3-mini-2025-01-31 (medium) , claude-3-5-sonnet-20241022 and others5 Abstract FindTheFlaws 提供五领域对错长解答与错误标注,并评测模型能否指出具体错误。FindTheFlaws 是一组供可扩展监督研究使用的错误检测数据,本文的实验是评测模型找错,不是运行辩论或 prover-verifier 对局。
You have reached the end