1
I Tried Proton’s Privacy-First AI Chatbot to See If It’s Better Than ChatGPT
隐私优先的AI助手Lumo 2.0来了，能否挑战ChatGPT？实测对比告诉你答案
Proton's AI assistant now has image generation and deep-thinking capabilities.
2
Prompting GPT-5 on Scrum Certification Questions: An Empirical Accuracy Study
GPT-5挑战Scrum认证考试，实证准确率研究新发现
arXiv:2607.00049v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in Agile Software Development for documentation, …
3
WildIFEval: Instruction Following in the Wild
新基准WildIFEval带你从实验室走进真实世界的指令跟随能力评估
arXiv:2503.06573v3 Announce Type: replace-cross Abstract: Recent LLMs have shown remarkable success in following user instructions, yet handling instr…
4
MiniMax M3一手实测：老黄PPT上74个Logo，我以为能难住它
实测MiniMax M3：能准确识别老黄PPT上74个Logo，甚至纠正路径逻辑，闭源模型中也仅“御三家”能做到。
还能带你打卡老黄同款南锣路线
5
Evaluating Relational Reasoning in LLMs with REL
新基准REL系统性评估大模型关系推理能力，揭示现有LLM的短板与潜力。
arXiv:2604.12176v2 Announce Type: replace Abstract: Relational reasoning is the ability to infer relations that jointly bind multiple entities, attrib…
6
Preference-Aware Rubric Learning for Personalized Evaluation
提出偏好感知评分标准学习方法，让AI评估更贴合个人标准，解决评测千人千面难题
arXiv:2605.31545v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve from general-purpose assistants to user-centric agents, persona…
7
Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation
探索LLM代码生成中的“护城河”偏见：它们会偷偷偏袒自家云生态吗？
arXiv:2605.28515v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become an integral part of software development, especially with t…
8
MultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing
基于LLM隐藏状态探测的多语言幻觉检测新方法，有效应对非英语场景的可靠性挑战。
arXiv:2605.24919v1 Announce Type: new Abstract: Hallucinations in Large Language Models (LLMs) represent a critical barrier to their reliable deployme…
9
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
通过证据校准的查询聚类精准捕捉大模型能力边界，为LLM评估提供全新方法论。
arXiv:2605.17110v1 Announce Type: cross Abstract: Query clustering organizes queries into groups that reflect shared latent capability demands, enabli…