1
2
Working on documents with your AI chat
在AI聊天中直接修改文档，告别整篇重写和反复粘贴；对话式编辑让协作更高效。
Article URL: https://revise.io/blog/08-10-2026/working-on-documents-with-your-ai-chat Comments URL: https://news.ycombinator.com/item?id=49248734 Poin…
3
Grounded Optimization: A Layered Engineering Framework for Reducing LLM Hallucination in Automated Personal Document Rewriting
一份可落地的分层工程框架，专门解决LLM改写个人文档时的幻觉问题，方法清晰、案例详实。
arXiv:2607.01457v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to resume optimization for applicant tracking …
4
CounterPoint 称 iPhone Ultra 改写 2026 全球折叠面板供应格局，苹果首年贡献 29% 采购份额
IT之家 7 月 2 日消息，市场调查机构 CounterPoint Research 今天（7 月 2 日）发布博文，预估苹果首款折叠手机（上市后预估名为 iPhone Ultra）上市后， 在 2026 年全球折叠手机屏幕出货量占比中，将斩获 29% 的订单。 该机构指出迈入 2026 年后，全…
5
PASTA: A Paraphrasing And Self-Training Approach for Knowledge Updating in LLMs
用改写加自训练，搞定大模型的知识更新难题，方法新颖实用。
arXiv:2606.28898v1 Announce Type: new Abstract: Knowledge updating in pre-trained Large Language Models (LLMs) remains an important challenge. While c…
6
Paraphrasing Attack Resilience of Various AI-Generated Text Detection Methods
探究多种AI生成文本检测方法在面对改写攻击时的鲁棒性，为内容安全提供新视角。
arXiv:2605.14240v1 Announce Type: cross Abstract: The recent large-scale emergence of LLMs has left an open space for dealing with their consequences,…
7
CoRe: A Continuously Reward-Finetuned LLM Query Rewriter for Multi-Stage Context-Aware Relevance in Web-Scale Video Search
将大规模视频搜索中的查询改写难题转化为连续奖励微调任务，实现多阶段上下文感知的相关性提升。
arXiv:2606.14127v1 Announce Type: cross Abstract: LLM-based query rewriters in production face a tension: the training reward must reflect how the rew…
8
Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion
用改写反转来无监督学习文本风格，精准识别AI生成内容，方法新颖且实用。
arXiv:2606.10099v1 Announce Type: cross Abstract: The rapid development of large language models (LLMs) has raised concerns about misuse such as plagi…
9
今年 4000 名新人入职美国银行，将面对正被 AI 改写的华尔街
4000名新员工入职美国银行，AI如何重塑华尔街的就业生态与人才需求。
IT之家 6 月 3 日消息，据《商业内幕》3 日（今天）晚间报道，美国银行今年招聘了 近 4000 名暑期实习生和全职校招新人 ，两类人员大致各占一半，规模与去年基本一致。 美国银行全球人才主管乔希 · 布朗斯坦表示，今年 约有 24 万人申请不到 2000 个实习岗位 ，录取率约为 0.8%。今…
10
Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization
用约束策略优化让大模型改写文本以逃逸检测，最新arXiv研究揭秘AI攻防新方法。
arXiv:2606.00392v1 Announce Type: new Abstract: AI-text detectors are vulnerable to paraphrasing and detector-guided paraphrasing attacks, but existin…
11
FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks
一次改写质量审计揭露了数学推理基准中语义漏洞，排名翻盘只需移除3.1%错误项，单一模型评估的盲区由此暴露。
arXiv:2605.29001v1 Announce Type: cross Abstract: A paraphrase-quality audit of MathCheck (ICLR 2025) detected 4 semantically incorrect paraphrases in…
12
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
用协同训练改写器和密集编码器，跨越自然语言与API技术词汇的鸿沟，大幅提升LLM工具检索准确率。
arXiv:2605.29271v1 Announce Type: new Abstract: Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in col…
13
AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing
顶级AI会议ICML 2026接收，提出新方法大幅提升句子级文本水印对抗改写攻击的鲁棒性。
arXiv:2605.29434v1 Announce Type: cross Abstract: Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring waterma…
14
Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization
深度解析Lean 4自动形式化中同义改写引发的失败模式，推动形式化验证技术发展
arXiv:2604.23135v2 Announce Type: replace Abstract: Lean 4 autoformalization has become increasingly popular in recent years, with frontier language m…