1
Hackers can use 9 of the most popular AI tools to assemble massive botnets
黑客利用9大AI工具"幻觉"漏洞组建僵尸网络，揭示新型HalluSquatting攻击风险。
"HalluSquatting" weaponizes LLMs' inability to say "I don't know."
2
Tech pundit Cringely cofounds startup '2Brains Inc' to solve LLM hallucinations
科技评论家Cringely联手创办2Brains Inc，专攻大模型“幻觉”难题
Article URL: https://slashdot.org/story/26/06/20/0556251/tech-pundit-cringely-co-founds-startup-2brains-inc-to-solve-llm-hallucinations Comments URL: …
3
Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning
针对大语言模型在知识图谱推理中易产生幻觉的痛点，提出了一套新的检测框架与评估方法。
arXiv:2606.19351v1 Announce Type: cross Abstract: Knowledge graph (KG) reasoning infers new knowledge from existing facts and is widely applied in que…
4
Zero-source LLM Hallucination Detection with Human-like Criteria Probing
零资源检测大模型幻觉，引入人类标准探测法，被ICML 2026接收的新方法。
arXiv:2606.12900v1 Announce Type: new Abstract: Large language models (LLMs) often hallucinate by generating factually incorrect or unfaithful content…
5
NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning
提出NTS-CoT方法，用思维链推理大幅减少LLM在新闻时间线摘要中的幻觉问题
arXiv:2606.13171v1 Announce Type: cross Abstract: The rapid updates of online news make tracking event developments challenging, highlighting the need…
6
Constrained Paraphrase Consistency for LLM Hallucination Detection
利用约束性释义一致性检测大模型幻觉，已被顶会ICASSP 2026接收，提供新颖可靠方案。
arXiv:2606.08158v1 Announce Type: new Abstract: Large language models (LLMs) can generate factually inconsistent claims, motivating accurate and scala…
7
Anatomy of a Learning Stall – How LLM Hallucinations Become Human Hallucinations
从LLM幻觉到人类认知偏差：学习停滞的解剖，揭示正确性与真理的鸿沟
Article URL: https://tagide.com/blog/llm/the-anatomy-of-a-learning-stall/ Comments URL: https://news.ycombinator.com/item?id=48435840 Points: 2 # Comm…
8
DECK: A Consistency x Confidence Taxonomy of LLM Hallucinations
提出DECK分类法，将LLM幻觉分为四种行为模式，帮助精准检测
arXiv:2606.02289v1 Announce Type: new Abstract: Existing hallucination taxonomies classify LLM errors by what is wrong with the output -- memorised mi…
9
DiffLens: Using LangGraph to verify line-range coordinates in LLM code reviews
用LangGraph驯服AI代码审查的行号幻觉，64%的有价值评论不再被GitHub API无情丢弃
Article URL: https://github.com/ywu593412-afk/difflens Comments URL: https://news.ycombinator.com/item?id=48346869 Points: 1 # Comments: 0
10
CiteCheck: Retrieval-Grounded Detection of LLM Citation Hallucinations in Scientific Text
针对大模型“瞎编引用”问题，提出检索验证的检测方法，提升科学文献可信度。
arXiv:2605.27700v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to generate scientific reports, but they can prod…
11
Evaluating the Relevance of Uncertainty Estimators for LLM Hallucination
这篇论文系统评估了多种不确定性估计方法在检测大模型幻觉上的实际效果，为提升LLM可靠性提供关键参考。
arXiv:2605.27016v1 Announce Type: cross Abstract: Large language models (LLMs) are prone to hallucinations, i.e., statements unsupported by the input …
12
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations
从线性化表示角度拆解大模型在结构化知识上产生幻觉的深层机理，ACL 2026论文揭示推理缺陷。
arXiv:2605.26362v1 Announce Type: cross Abstract: In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as…
13
Empirical Analysis and Detection of Hallucinations in LLM-Generated Bug Report Summaries
系统研究LLM生成Bug报告摘要时的幻觉问题，实证分析并提出检测方法，对软件工程与AI可靠性有参考价值。
arXiv:2605.24137v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to generate summaries of software bug reports, in…
14
Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
颠覆认知：研究发现大模型在知道正确答案时仍会产生幻觉，本质是「承诺失败」而非知识缺失。
arXiv:2605.22007v1 Announce Type: new Abstract: Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectl…