1
Your brain on AI
用AI帮你快速验证新闻真伪，但别忘了保留独立判断。Perplexity AI提供实时信息检索与来源引用，边查边学，适合对抗假新闻。
Many people find AI-based chatbots helpful in keeping up with news, but a study by Pattie Maes and her colleagues at the MIT Media Lab points to a big…
2
Israel creates fake think tank in likely attempt to dupe AI chatbots
以色列疑似伪造智库数据集，试图暗中操纵ChatGPT等AI的回答，揭露AI信息战的全新战线。
Article URL: https://responsiblestatecraft.org/israel-influence-chatgpt/ Comments URL: https://news.ycombinator.com/item?id=49337392 Points: 41 # Comm…
3
AI/ML Research Digest — Aug 02, 2026
AI研究速览：聚焦评估污染与检索扩展，一窥模型评测新盲区。
Reliable provenance and graded trust Explicit reliability modeling cuts hallucination. Σ‑Mem stores symmetric competence states for peer agents, while…
4
Decomposed Entailment for Factuality Checking and Hallucination Detection
一句话看懂LLM幻觉检测新框架，轻量黑盒免参考，不止摘要还跨任务实测。
arXiv:2608.05823v1 Announce Type: new Abstract: The reliability of Large Language Models (LLMs) is often compromised by factual inconsistencies, inclu…
5
FACTWASH: Catching AI Rewrites That Wash Hearsay into Fact
识破AI把道听途说洗白成“事实”的新检测框架，给大模型信息可信度敲响警钟。
arXiv:2608.03372v1 Announce Type: new Abstract: AI systems rewrite information constantly: conversations become stored memories, documents become answ…
6
When Retrieval Helps and Distracts: Evaluating Evidence-Generating LLMs for Biomedical Claim Verification
探究检索对生物医学事实验证的双刃剑效应，证据生成模型何时被误导？一篇严谨的评估研究。
arXiv:2608.01409v1 Announce Type: new Abstract: Biomedical fact-checking systems must do more than predict whether a claim is supported, contradicted,…
7
SciClaimSeekers at CheckThat! 2026: Retrieving Scientific Sources for Social Media Claims with LLM Reranking
用 LLM 重排序提升社交媒体言论的科学源检索精度，为事实核查提供高效方案。
arXiv:2607.24803v1 Announce Type: cross Abstract: Scientific claims often spread on social media faster than they can be verified, while posts rarely …
8
Calibrated Selective Fact-Checking via Evidence Chain Evaluation
LLM事实核查的二元判断隐藏可靠性危机，论文提出基于证据链评估的校准选择性方法，直击AI可信度痛点。
arXiv:2607.18240v1 Announce Type: new Abstract: Large language models (LLMs) can achieve strong fact-checking accuracy, yet forced binary decisions co…
9
Show HN: Tessera – an AI agent that refuses to answer without evidence
一个坚守证据底线的AI助手，拒绝凭空作答，专治大模型胡编乱造
Article URL: https://github.com/robert-vetter/tessera Comments URL: https://news.ycombinator.com/item?id=48822458 Points: 2 # Comments: 0
10
TrendFact: A Benchmark Towards Hotspot Perception in Automatic Fact-Checking
首个面向热点感知的事实核查基准，直击虚假信息检测中时序与热度维度的盲区，想了解AI如何跟上新闻热点必读。
arXiv:2410.15135v5 Announce Type: replace Abstract: With the surge of online misinformation, Large Language Models (LLMs) and Reasoning Large Language…
11
I created an App that will do fact check for free
免费AI事实核查应用，专治AI胡诌，帮你识别虚假信息
Have you ever gotten baited by AI and believed something's true when it was not? It was something that we used to struggle with as a country and I wan…
12
Hybrid Fact-Checking that Integrates Knowledge Graphs, Large Language Models, and Search-Based Retrieval Agents Improves Interpretable Claim Verification
结合知识图谱、大模型与搜索代理的混合事实核查框架，让声明验证更透明可信。
arXiv:2511.03217v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel in generating fluent utterances but can lack reliable gro…
13
ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
多源证据动态检索与层级聚合的开源框架，让AI事实核查过程清晰可解释。
arXiv:2606.27736v1 Announce Type: new Abstract: The rapid spread of fake news poses increasing threats to information ecosystems, especially as AI-gen…
14
The Warrant Gap: Claim-Conditioned Re-scoring for Fact-Checking
论文提出SIFT方法，解决LLM事实核查中“证据缺口”问题，用claim条件重新评分提升可靠性。
arXiv:2606.24627v1 Announce Type: new Abstract: Fact-checking systems built on LLMs achieve high verdict accuracy on standard benchmarks, yet routinel…
15
KPMG pulls report on AI usage due to apparent hallucinations
知名咨询公司KPMG因AI幻觉错误，被迫撤回一份关于企业AI使用情况的报告，GPTZero揭露多处不实。
Once again, AI proves to be an unreliable source of information about AI.
16
Multilingual Fact-Checking at Scale: Fine-Tuned Compact Models vs LLMs
对比微调紧凑模型与大型语言模型在多语言事实核查中的性能，部署于Factiverse系统实现高吞吐低延迟。
arXiv:2606.08605v1 Announce Type: new Abstract: We present a multilingual fact-checking system deployed at Factiverse, designed for high-throughput an…
17
Show HN: Amanuensis – a local-first AI persona that won't fabricate facts
本地优先、杜绝AI幻觉的开源写作助手，草稿由你审核后才发布，让事实更可靠
Article URL: https://github.com/msalsas/amanuensis Comments URL: https://news.ycombinator.com/item?id=48414891 Points: 1 # Comments: 0
18
REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control
自优化事实核查新范式，用判决锚定风格控制实现可解释性突破。
arXiv:2511.20233v4 Announce Type: replace Abstract: The prevalence of fake news on social media demands automated fact-checking systems to provide acc…
19
Diagnosing LLM Arbitration Behavior over Pre-evidence Epistemic States in RAG-based Fact-Checking
用认知状态诊断LLM在RAG事实核查中的仲裁行为，ACL-2026前沿研究
arXiv:2606.01120v1 Announce Type: new Abstract: In RAG-based fact-checking, LLMs are increasingly used as verifiers to check given claims against retr…
20
Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies
将人类应试技巧引入模型判断声明事实性，有效提升大模型在证据支撑下的核查准确率。
arXiv:2605.29712v1 Announce Type: cross Abstract: Grounded claim factuality checking is important for large language model (LLM) applications such as …