研究：推理 token 能纠正部分偏见
用 CDPG 与 BTM 追踪思考如何改变反事实公平翻转
- arXiv
- 2609.30768
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Evaluated models
- QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, Qwen3-32B and others5
- RiskBias and discrimination
- ComponentReasoning chains
All papers
Filter5
Impact
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Another 233papers do not have category tags yet and are not included in filtered results.
SCHEMA：面向科学 Agent 幻觉的拓扑感知评测框架
提出 SCHEMA，用概念图与轨迹分评测科学 Agent 幻觉
- arXiv
- 2608.00711
- Published
- Layer
- Application layer
- Setting
- science agent
- Evaluated models
- Kimi-K2.5, Qwen3.6-Plus, Llama-4-Scout and others10
- RiskHallucination and fabrication
- ComponentReasoning chains
AbstractSCHEMA 用知识拓扑评估科学智能体幻觉，终答正确仍可能来自有缺陷的中间推理。
SCHEMA 是面向科学智能体幻觉的证据锚定评测框架，实例化在生物医学的 Protein Domain 与 PathVQA-Enhanced。作者在摘要中称它是首个同时做到证据锚定和拓扑感知的此类框架。
- Risky behaviorarXiv 2607.14345
Truthful AI 提出价值泄漏评估：模型答案被自身价值观悄然左右
提出价值泄漏评估，测量模型回答受自身价值倾向的隐蔽影响
- arXiv
- 2607.14345
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Evaluated models
- Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6 and others15
- RiskMisalignment and value divergence
- ComponentReasoning chains
Abstract论文揭示前沿模型回答常受自身价值隐蔽塑造，提出反事实评估量化偏见及其思维链隐瞒，指出当前对齐未能有效防范该失效。
- AttacksarXiv 2607.00422
KidnapRAG：黑盒投毒攻击劫持 Agentic RAG 的推理链
提出 KidnapRAG，用投毒文档黑盒劫持 Agentic RAG 的推理链
- arXiv
- 2607.00422
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Qwen2.5-32B-Instruct, Llama-3.3-70B-Instruct, QwQ-32B and others5
- AttacksPoisoning and backdoors
- TechniqueSelection manipulation
- ComponentReasoning chains
Abstract顺序投毒可把多步推理拖向指定应答，作者称关键在持续引导而非单次注入。
KidnapRAG 是针对 Agentic RAG 的 black-box 语料投毒：攻击者不能访问模型、提示词、检索器或私有轨迹，只能发布可能被检索的文档，并利用公开界面上的推理与搜索查询。
- AttacksarXiv 2604.12201
AdversarialCoT: single-document retrieval poisoning for LLM reasoning
Proposes AdversarialCoT single-document retrieval poisoning to manipulate RAG reasoning answers
- arXiv
- 2604.12201
- Published
- Layer
- Application layer
- Setting
- LLM applications
- Evaluated models
- DeepSeek-R1, Qwen3, GLM4.5 and others5
- AttacksPoisoning and backdoors
- TechniqueReasoning-chain manipulation
- ComponentRAG
- AttacksarXiv 2602.18514
招聘中的特洛伊木马：标准模型与推理模型间接提示注入的红队测试案例研究
用简历中的不可见指令做间接提示注入，操纵招聘推荐
- arXiv
- 2602.18514
- Published
- Layer
- Application layer
- Setting
- LLM applications
- Evaluated models
- Qwen 3 30B A3B Instruct 2507, Qwen 3 30B A3B Thinking 2507
- AttacksPrompt injection
- TechniqueEncoding and obfuscation
- ComponentReasoning chains
Abstract作者称推理在简单注入下会帮攻击圆谎，在不合逻辑的复杂注入下又会把欺骗漏出来。
You have reached the end