1
Are LLMs ready for HardChoices?
大模型能否应对"HardChoices"？这篇Konvens 2026论文给出了前瞻性测评。
arXiv:2607.11471v1 Announce Type: new Abstract: A lot of research attention has been devoted to checking whether large language models (LLMs) are poli…
2
借鉴多邻国？曝谷歌翻译将推出“连续打卡天数”小组件
谷歌翻译将上线连续打卡小组件，模仿多邻国激励日常语言练习，让学习更有动力。
IT之家 6 月 29 日消息，据科技媒体 Android Authority 今天报道，谷歌翻译近年来正逐渐从一款翻译工具，跨界成为语言学习工具。例如谷歌去年推出的“练习”模式可以模拟真实对话，帮助用户提升口语、听力。 IT之家在此援引 Android Authority，谷歌翻译练习模式拥有“连…
3
LLM and Human Modes of Representation
探讨大语言模型与人类表征模式的差异，从认知科学视角剖析AI理解能力
arXiv:2606.21616v1 Announce Type: new Abstract: Much work on the cognitive foundations of AI has focussed on comparisons between the ways in which Lar…
4
VideoLatent: Video-Language Learning via Latent Self-Forcing
新方法「潜在自强制」提升视频语言学习效率，无需逐帧解码即可对齐语义。
arXiv:2606.22870v1 Announce Type: cross Abstract: Recent advancements in chain-of-thought (CoT) reasoning have shown promise in enhancing video unders…
5
Show HN: Chatty Lingo – A language practicing app
用AI教练陪你练习真实场景口语，支持多语言，24/7耐心陪练，还能与母语者聊天。
Hey all, I've built a web app for practicing spoken conversations in a language you're learning. It was driven by my own needs when I learn Korean. Th…
6
Best LLM Models for Conversational AI in Language Learning
用大模型打造语言学习对话伙伴，实战代码与模型选择指南
We are going to build a conversational language tutor that corrects mistakes in real time, adapts its complexity to your proficiency, and maintains co…
7
How Preply combines AI and human tutors to personalize learning
Preply巧用OpenAI，将AI与真人导师结合，打造个性化语言学习体验。
Preply uses OpenAI to launch AI-generated lesson summaries, providing personalised feedback and language learning exercises.
8
CakewordAI
手指一戳，万物皆可学：指哪学哪的多语言AI学习神器，让语言学习变成游戏。
Point at anything to learn its name in any language Discussion | Link
9
The Dynamics of Human and AI-Generated Language: How Semantics Fluctuates across Different Timescales
揭秘人类与AI语言在语义上的时间波动，看不同尺度下两者的动态差异。
arXiv:2606.11371v1 Announce Type: cross Abstract: Spoken language, whether produced by humans or large language models (LLM), unfolds over time with v…
10
Why AI conversation mode beats vocabulary lists
颠覆传统背单词，AI对话模式用可理解输入让语言习得更高效。
Article URL: https://manateavagner.com/news/translate-conversation-mode-language-learning Comments URL: https://news.ycombinator.com/item?id=48487243 …
11
Large Language Models as Modal Models in Linguistics
探讨LLM作为语言学模态模型的新视角，论文从理论层面解析大语言模型的语言学应用价值
arXiv:2606.10467v1 Announce Type: new Abstract: The rapid advancement of large language models (LLMs) has intensified debates about their significance…
12
Leveraging Morphology for Historical Script Metrological Analysis
用形态学分析历史手稿的计量特征，这项研究为数字人文提供了新的技术视角。
arXiv:2606.09446v1 Announce Type: new Abstract: Advances in handwritten text recognition have enabled large-scale transcription of historical document…
13
Ask HN: Any good language learning apps/sites that don't use LLMs/GenAI?
寻找不使用AI的语言学习应用？HN社区有真实推荐，避开GenAI的纯净学习工具。
I'm looking to learn a language interactively with an app/program/website, but a lot of the "household names" I know from the past seem to use AI now,…
14
Noisy memory encoding explains negative polarity illusions
用噪音记忆编码模型揭示“负极性词”语法幻觉的认知根源，颠覆传统语法判断认知
arXiv:2606.04340v1 Announce Type: new Abstract: A sentence like "The authors that no critics recommended have ever received acknowledgment for a best-…
15
Linguistic Productivity in Large Language Models: Models Coerce, but do not Preempt
揭示大语言模型的语言生成机制：模型会强制修正而非抢占规则，挑战传统语言生产力理论。
arXiv:2606.02953v1 Announce Type: new Abstract: Usage-based theories of grammars posit that creative productivity of the structures of language is bot…
16
Linguistics-Aware Non-Distortionary LLM Watermarking
语言学感知的LLM水印新方案，无失真同时保证高检测率，平衡文本质量与版权保护。
arXiv:2606.00613v1 Announce Type: cross Abstract: Watermarking should identify language-model output without degrading quality or limiting verificatio…
17
Multilinguality of Large Language Models From a Structural Perspective
从结构视角解析大模型的多语言能力，揭示语言间共性与差异的深层机制。
arXiv:2606.01800v1 Announce Type: cross Abstract: Large language models (LLMs) have excelled in processing multiple languages through pre- and post-tr…
18
To model human linguistic prediction, make LLMs less superhuman
让大语言模型更像人类，研究者提出降低其“超人”能力以模拟语言预测机制
arXiv:2510.05141v2 Announce Type: replace Abstract: When we read, we make predictions about upcoming words; these predictions influence our reading be…
19
Probing Minimalist Phase Structure in LLMs: What Universal Dependencies Cannot Represent
深入探测13个LLM，发现最小主义短语结构与通用依赖（UD）的表征边界
arXiv:2605.26431v1 Announce Type: new Abstract: Structural probes train on Universal Dependencies (UD), which does not encode formal-syntactic abstrac…
20
Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators
用虚拟受访者进行心理测量项目验证，特质-响应中介模型带来全新范式
arXiv:2507.05890v4 Announce Type: replace-cross Abstract: As psychometric surveys are increasingly used to assess the traits of large language models …