1
特朗普签署行政令把 AI 改叫 SI，推出美国政府对话式问答网站
IT之家 9 月 30 日消息，美东时间周二（9 月 29 日），美国总统特朗普正式签署行政令，下令所有行政部门和机构 使用“超级智能”（Super Intelligence，简称 SI）一词代替人工智能（AI） 。 特朗普在行政令中表示：美国创新者开创的非凡技术远超“人工智能”一词初次出现时的设想…
2
SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering
结构感知+证据引导，让知识型视觉问答的推理过程更可信、可验证。
arXiv:2608.21796v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning…
3
Performance of a domain-specific large language model in answering patient questions in psychiatry
精神病学专用模型对战通用聊天机器人，评测医疗问答的临床准确性，AI落地医疗的新探索。
arXiv:2608.22797v1 Announce Type: new Abstract: Background This study was designed to evaluate whether a domain-specific large language model (LLM) tr…
4
CyrillicQA: The Influence of Phonetically Encoded Secret Language on LLM Performance
用西里尔字母谐音伪装提问，检验大模型能否破解这层“密语”并保持问答性能，脑洞与严谨兼备
arXiv:2608.21462v1 Announce Type: cross Abstract: Due to the selection of their training data, large language models (LLMs) perform best on standard-l…
5
Enhancing LLMs in Predictive Political QA with Semi-Structured Data
半结构化数据让大模型预测政治走向更靠谱？看这项研究如何提升问答准确性。
arXiv:2608.21218v1 Announce Type: new Abstract: Predictive political question answering (QA), such as predicting how a political actor will vote, goes…
6
Qworld: Question-Specific Evaluation Criteria for LLMs
针对开放式问答的评估难题，提出问题级专属评估标准，让LLM评分更贴合上下文需求。
arXiv:2603.23522v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) on open-ended questions is difficult because response qual…
7
STAIR: Semantic-Temporal Automaton for Interpretable Reasoning in Temporal Question Answering
时间问答遇上可解释推理：用语义时间自动机拆解复杂时序问题，让模型推理过程透明可控。
arXiv:2608.16224v1 Announce Type: cross Abstract: By leveraging large-scale pretraining, LLMs can interpret diverse temporal expressions and question …
8
Tesla wants to build a $10B solar factory in Texas
ChatGPT 让这篇英文科技报道秒变核心观点，支持追问工厂选址细节，免费易上手。
Tesla wants to build a massive solar factory in Texas, but first it wants the state to chip in to defray the costs.
9
Asymptotic Risk Calibration for Selective Question Answering
不看全文也能“有把握放弃回答”？这项研究为选择性问答系统提供了风险校准的理论保障。
arXiv:2608.12008v1 Announce Type: new Abstract: Large language models (LLMs) may generate fluent but incorrect answers, making uncertainty quantificat…
10
CARE: Confidence-Aware Reasoning for Reliable Medical VQA
医疗视觉问答也能“知道何时不懂”，置信度感知推理让AI诊断更可靠
arXiv:2608.10964v1 Announce Type: new Abstract: Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produc…
11
KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs
用自动知识图谱构建让大模型条件问答更可解释，复杂问题也能追根溯源。
arXiv:2608.09779v1 Announce Type: cross Abstract: Answering complex conditional questions using Large Language Models (LLMs) and Retrieval-Augmented G…
12
NeSy-RAG: Neuro-Symbolic RAG for Explainable Question Answering
把神经符号推理融入RAG，让问答系统不仅能答，还能说清为什么。
arXiv:2608.06292v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves question answering by grounding large language models (L…
13
The Hottest New AI Chatbot Is Just a Guy Answering Your Questions
号称“AI”的新晋网红聊天机器人，背后其实是真人秒回，既幽默又真实，一秒戳中笑点。
Article URL: https://www.wired.com/story/this-chatbot-is-just-a-random-guy-lol/ Comments URL: https://news.ycombinator.com/item?id=49208550 Points: 2 …
14
SimulRAG: Simulator-based RAG for Grounding LLMs in Long-form Scientific QA
用模拟器增强检索，让大模型在长科学问答中更精准地锚定事实，RAG落地新思路。
arXiv:2509.25459v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) show promise in generating long-form scientific explanations th…
15
Gaokerena: A Small Persian Medical Language Model Family
波斯语医疗问答专用语言模型，填补低资源语言空白，精准高效。
arXiv:2608.00932v1 Announce Type: new Abstract: The integration of artificial intelligence into medical question-answering systems has advanced rapidl…
16
Leveraging Synthetic Data for Question Answering with Multilingual LLMs in the Agricultural Domain
用合成数据驯服农业领域多语言大模型，破解低资源语言问答难题，实验严谨、方法可复用。
arXiv:2507.16974v3 Announce Type: replace-cross Abstract: Enabling farmers to access accurate agriculture-related information in their native language…
17
ViewMind3D: Modular View-Aware Inference for Training-Free 3D-QA
无需3D训练数据，模块化视图感知让大模型直接推理3D问答，机器人感知新思路。
arXiv:2607.28442v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and vision-language models (VLMs) have enabled new pos…
18
LoMeVQA: A Comprehensive Benchmark for Longitudinal Medical VQA
首个纵向医学视觉问答基准，覆盖时序影像推理，直击临床动态病情评估痛点。
arXiv:2607.27806v1 Announce Type: new Abstract: In clinical practice, patients often undergo multiple imaging examinations over successive visits, yie…
19
Ask HN: I lost any interest in technology. What do I do?
技术激情消退，AI带来的异化感让一位资深程序员陷入迷茫，社区热议如何重拾热情。
Dear HN, For the past months, maybe a year, I have lost any interest in technology, software and hardware. When I was a teenager, I had very big passi…
20
Google’s Gemini nears billion-user milestone
Google Gemini 接近十亿用户里程碑，AI问答模式驱动搜索增长并降低成本，展现AI领域强劲势头。
Gemini had over 750 million monthly users in February.