Goto

Collaborating Authors

 korea


N Korea's Kim unveils 50 rocket launchers ahead of key congress

Al Jazeera

N Korea's Kim unveils 50 rocket launchers ahead of key congress North Korean leader Kim Jong Un has unveiled dozens of nuclear-capable rocket launchers ahead of a key congress of the governing Workers' Party, according to state media. Kim hailed the 600mm-calibre rocket launchers as "wonderful" and "attractive" during the ceremony on Wednesday, adding that new military and construction goals will be set during the upcoming congress. "When this weapon is used, actually, no force would be able to expect God's protection," Kim said, according to the KCNA "It is really a wonderful and attractive weapon," Kim said, according to South Korea's Yonhap News Agency. He described the launchers as the "world's most advantageous weapon for concentrated super-powerful attack", according Yonhap. Photos released by state media showed dozens of launch vehicles parked in neat rows on the plaza of Pyongyang's House of Culture, which will host the congress.


South Korea says civilians sent drones to North Korea four times, harming ties

The Japan Times

Fragments of a drone lie scattered on the ground in the Muksan-ri area, Kaepung District, Kaesong City, North Korea, after North Korea said on Saturday that South Korea sent another drone into North Korean airspace on Jan. 4, according to North Korean state media KCNA, in this picture released on Jan. 10. SEOUL - South Korea's Unification Minister Chung Dong-young said on Wednesday that three civilians had sent drones to North Korea on four occasions since President Lee Jae Myung took office last year, harming inter-Korean ties. The trio flew the aircraft between September and January, Chung said, citing an ongoing investigation by police and the military. Drones crashed on two occasions in North Korea, in line with claims made by Pyongyang, he said. On two other attempts the drones returned to Paju, a border settlement in South Korea, after flying over Kaesong, a city in North Korea, Chung said.


North Korea's Kim Yo Jong urges South Korea to investigate drone incidents

The Japan Times

North Korea's Kim Yo Jong urges South Korea to investigate drone incidents Kim Yo Jong, sister of North Korean leader Kim Jong Un, arrives at the Vostochny Сosmodrome before a meeting between Russian President Vladimir Putin and Kim Jong Un, in Russia's far eastern Amur region in September 2023. Seoul - North Korea's Kim Yo Jong, the powerful sister of leader Kim Jong Un, urged South Korea to investigate recent drone incidents for detailed explanations, in a statement carried by state media Sunday. Kim said she personally appreciates Seoul for making a wise decision to announce its official stance that it has no intention of provocation, warning that any provocations will result in terrible situations, the official Korean Central News Agency said. Drones were flown from South Korea into North Korea earlier this month, after another intrusion in September, North Korea's military said on Saturday, which was soon followed by South Korea's response that they were not operated by the military. South Korea also said there would be a thorough investigation of a civilian possibly having operated the drones, making clear its stance of having no intention of provocation. Clear is just the fact that the drone from the ROK violated the airspace of our country, Kim said.



Language over Content: Tracing Cultural Understanding in Multilingual Large Language Models

Cho, Seungho, Ko, Changgeon, Hwang, Eui Jun, Lee, Junmyeong, Lee, Huije, Park, Jong C.

arXiv.org Artificial Intelligence

Large language models (LLMs) are increasingly used across diverse cultural contexts, making accurate cultural understanding essential. Prior evaluations have mostly focused on output-level performance, obscuring the factors that drive differences in responses, while studies using circuit analysis have covered few languages and rarely focused on culture. In this work, we trace LLMs' internal cultural understanding mechanisms by measuring activation path overlaps when answering semantically equivalent questions under two conditions: varying the target country while fixing the question language, and varying the question language while fixing the country. We also use same-language country pairs to disentangle language from cultural aspects. Results show that internal paths overlap more for same-language, cross-country questions than for cross-language, same-country questions, indicating strong language-specific patterns. Notably, the South Korea-North Korea pair exhibits low overlap and high variability, showing that linguistic similarity does not guarantee aligned internal representation.


When Language Shapes Thought: Cross-Lingual Transfer of Factual Knowledge in Question Answering

Kang, Eojin, Kim, Juae

arXiv.org Artificial Intelligence

Multilingual large language models (LLMs) offer promising opportunities for cross-lingual information access, yet their use of factual knowledge remains highly sensitive to the input language. Prior work has addressed this through English prompting and evaluation, assuming that English-based reasoning is universally beneficial. In this work, we challenge that assumption by exploring factual knowledge transfer from non-English to English through the lens of Language and Thought Theory. We introduce Language-to-Thought (L2T) prompting, which aligns the model's internal ''thinking'' language with the source of knowledge. Across three languages and four models, L2T consistently outperforms English-based reasoning, reversing the expected advantage of English prompts. Our code is available at https://github.com/GeomeunByeol/Language2Thought.


AI-Driven Development of a Publishing Imprint: Xynapse Traces

Zimmerman, Fred

arXiv.org Artificial Intelligence

Xynapse Traces is an experimental publishing imprint created via a fusion of human and algorithmic methods using a configuration-driven architecture and a multi-model AI integration framework. The system achieved a remarkable 90% reduction in time-to-market (from a typical 6-12 months to just 2-4 weeks), with 80% cost reduction compared to traditional imprint development, while publishing 52 books in its first year and maintaining exceptional quality metrics, including 99% citation accuracy and 100% validation success after initial corrections. Key technical innovations include a continuous ideation pipeline with tournament-style evaluation, a novel codex design for transcriptive meditation practice, comprehensive automation spanning from ideation through production and distribution, and publisher personas that define and guide the imprint's mission. The system also integrates automated verification with human oversight, ensuring that gains in speed do not compromise publishing standards. This effort has significant implications for the future of book publishing, suggesting new paradigms for human-AI collaboration that democratize access to sophisticated publishing capabilities and make previously unviable niche markets accessible.



A Dual-Layered Evaluation of Geopolitical and Cultural Bias in LLMs

Kim, Sean, Kim, Hyuhng Joon

arXiv.org Artificial Intelligence

As large language models (LLMs) are increasingly deployed across diverse linguistic and cultural contexts, understanding their behavior in both factual and disputable scenarios is essential, especially when their outputs may shape public opinion or reinforce dominant narratives. In this paper, we define two types of bias in LLMs: model bias (bias stemming from model training) and inference bias (bias induced by the language of the query), through a two-phase evaluation. Phase 1 evaluates LLMs on factual questions where a single verifiable answer exists, assessing whether models maintain consistency across different query languages. Phase 2 expands the scope by probing geopolitically sensitive disputes, where responses may reflect culturally embedded or ideologically aligned perspectives. We construct a manually curated dataset spanning both factual and disputable QA, across four languages and question types. The results show that Phase 1 exhibits query language induced alignment, while Phase 2 reflects an interplay between the model's training context and query language. This paper offers a structured framework for evaluating LLM behavior across neutral and sensitive topics, providing insights for future LLM deployment and culturally aware evaluation practices in multilingual contexts.


North Korea's Kim oversees test of AI-powered suicide drones

FOX News

During a press conference with Japans Prime Minister Shigeru Ishiba, President Trump said relations with North Korea will happen. North Korean dictator Kim Jong Un has overseen tests of newly developed AI-powered suicide drones and called for their increased production, North Korean state media said Thursday. Photos released from the communist country show Kim inspecting new upgraded reconnaissance drones that are capable of detecting various tactical targets and enemy activities on land and at sea, KCNA state news agency said. Kim said unmanned control and AI capability must be the top priorities in modern arms development. North Korean leader Kim Jong Un has overseen tests of newly developed AI-powered suicide drones and called for their increased production, North Korean state media said.