As large language models (LLMs) become increasingly embedded in our daily lives, evaluating their quality and reliability across diverse contexts has become essential. While comprehensive benchmarks exist for assessing LLM performance in English, there remains a significant gap in evaluation resources for other languages. Moreover, because most LLMs are trained primarily on data rooted in European and American cultures, they often lack familiarity with non-Western cultural contexts. To address this limitation, our study focuses on the Persian language and Iranian culture. We introduce 19 new evaluation datasets specifically designed to assess LLMs on topics such as Iranian law, Persian grammar, Persian idioms, and university entrance exams. Using these datasets, we benchmarked 41 prominent LLMs, aiming to bridge the existing cultural and linguistic evaluation gap in the field.

Gilan, Iran – The Israeli military used hundreds of fighter jets, armed drones and refuelling planes to attack Iran during its 12-day war backed by the United States, but it was also heavily assisted by operations launched from deep within Iranian soil. Just hours after the Israeli army and Mossad spy agency started their attacks before dawn on June 13, they released footage that appeared to have been recorded at night from undisclosed locations inside Iran. One grainy video showed Mossad operatives, camouflaged and wearing tactical gear including night-vision goggles, crouched in what looked like desert terrain, deploying weapons that aimed to destroy Iran's air defence systems to help pave the way for incoming attack aircraft. Others showed projectiles, with mounted cameras, descending to slam into Iranian missile defence batteries, as well as ballistic missile platforms. The projectiles appeared to be Spike missiles – relatively small, precision-guided anti-armour missiles that can be programmed to fly to targets that are out of their line of sight.

Israel and Iran have carried out a new wave of attacks on key cities, fuelling fears of an all-out sustained war, with heavy exchanges now entering a third day. Iranian missiles struck northern Israel, killing at least three people and wounding 13 others, late Saturday into Sunday, according to Israeli media. Israel targeted the Iranian defence ministry headquarters in Tehran early Sunday, according to the semi-official Tasnim news agency. Iranian officials also said the Shahran oil depot, northwest of Tehran, was struck by Israel. Tasnim News said operational and rescue forces arrived at the scene and are still working to extinguish the fire.

Tehran, Iran – Iran's army and Islamic Revolutionary Guard Corps (IRGC) have been showcasing and testing new defensive and offensive weapons in large-scale military exercises for the past three months. The country is preparing for another tumultuous year amid threats by the United States and Israel to bomb Iranian nuclear facilities, critical energy infrastructure, and military sites. Iran is also promising a third iteration of its major military strikes on Israel, in retaliation for Israeli attacks amid the devastating war on Gaza. The exercises – Eqtedar, Zolfaqar and Great Prophet – have been held across Iran, the Sea of Oman and the northern Indian Ocean. The weapons tested show Iran intends to maintain its defiance of Israel and the West, refusing to negotiate with US President Donald Trump under his "maximum pressure" policy and continuing to advance its nuclear programme.

In an address to the 79th United Nations General Assembly Tuesday, Iranian President Masoud Pezeshkian claimed to be the one playing peacemaker in the Middle East and, in a juxtaposition, accused Israel of supporting terrorism. Pezeshkian called on the U.N. to "examine" modern history and said, "Iran has never initiated a war. It has only defended itself heroically against external aggression, causing the aggressors to regret their actions," Pezeshkian said, adding that Iran does not "occupy" territory or exploit resources for other countries. "It has repeatedly offered various proposals to its neighbors and international fora aimed at establishing lasting peace and stability," he said. "We have emphasized the importance of unity in the region and establishing a strong region." Iran's President Masoud Pezeshkian walks, on the sidelines of the 79th United Nations General Assembly at U.N. headquarters in New York, U.S., September 24, 2024.

Microsoft researchers said on Friday that Iran government-tied hackers tried breaking into the account of a "high-ranking official" on the US presidential campaign in June, weeks after breaching the account of a county-level US official. The breaches were part of Iranian groups' increasing attempts to influence the US presidential election in November, the researchers said in a report that did not provide any further detail on the apparent official in question. The report follows recent statements by senior US intelligence officials that they had seen Iran ramp up use of clandestine social media accounts with the aim to use them to try to sow political discord in the US. The report also reveals how Russia and China are exploiting US political polarization to advance their own divisive messaging in a consequential election year. Iran's mission to the UN in New York told Reuters in a statement that its cyber capabilities were "defensive and proportionate to the threats it faces" and that it had no plans to launch cyber-attacks.

We study an emerging and intriguing problem of multimodal temporal event forecasting with large language models. Compared to using text or graph modalities, the investigation of utilizing images for temporal event forecasting has not been fully explored, especially in the era of large language models (LLMs). To bridge this gap, we are particularly interested in two key questions of: 1) why images will help in temporal event forecasting, and 2) how to integrate images into the LLM-based forecasting framework. To answer these research questions, we propose to identify two essential functions that images play in the scenario of temporal event forecasting, i.e., highlighting and complementary. Then, we develop a novel framework, named MM-Forecast. It employs an Image Function Identification module to recognize these functions as verbal descriptions using multimodal large language models (MLLMs), and subsequently incorporates these function descriptions into LLM-based forecasting models. To evaluate our approach, we construct a new multimodal dataset, MidEast-TE-mm, by extending an existing event dataset MidEast-TE-mini with images. Empirical studies demonstrate that our MM-Forecast can correctly identify the image functions, and further more, incorporating these verbal function descriptions significantly improves the forecasting performance. The dataset, code, and prompts are available at https://github.com/LuminosityX/MM-Forecast.

U.S. intelligence officials believe that Iran is trying to sabotage former President Trump's presidential campaign through online influence operations, according to a press briefing on Monday. Speaking to reporters, an official with the Office of the Director of National Intelligence (ODNI) said U.S. spy agencies "observed Tehran working to influence the presidential election," likely because Iranian leaders want to avoid increased tensions with the U.S. The official didn't directly say that Iran was trying to undermine Trump, but that American spies "haven't observed a shift in Iran's preferences" since 2020, meaning that Iran was still targeting Trump. During the briefing, an intelligence official also said Iran is utilizing "vast webs of online personas and propaganda mills to spread disinformation," in addition to different online campaigns. U.S. intelligence officials believe Iran is meddling in the 2024 election. Earlier in July, Tehran was accused of a separate plot to kill Trump after a gunman shot the former president at a rally in Butler, Pennsylvania, on July 13.

JERUSALEM - The Iranian regime's plot to assassinate former President Trump is the latest in a string of attempts by Tehran to lethally target American officials and Iranian American dissidents. Iranian Supreme Leader Ali Khamenei has effectively put bounties on the heads of Trump, his former Secretary of State Mike Pompeo and ex-National Security Advisor John Bolton for their roles in the U.S. drone strike that eliminated the global Iranian terrorist Qassem Soleimani in 2020. According to the U.S. government, Soleimani was responsible for the murders of over 600 American military personnel in the Middle East. BOLTON CALLS IRAN ASSASSINATION PLOT AN'ACT OF WAR,' CALLS ON BIDEN ADMIN TO'TERMINATE' NUCLEAR TALKS Former President Trump, left, and Iranian leader Ali Khamenei. Fox News Digital reported on Tuesday that the Department of Homeland Security received intelligence from a human source about the planned Iranian assassination of Trump.

I last interviewed Ebrahim Raisi, the ultra-hard-line President of Iran, during his début appearance at the United Nations, in 2022. He spoke belligerently and with such speed that the interpreter struggled to keep up. He was the same on the U.N. dais, where he furiously waved a photo of General Qassem Soleimani and demanded that Donald Trump be tried for ordering his assassination--a "savage, illegal, immoral crime"--in a U.S. drone strike, in 2020. Back home, Iran was in turmoil after nationwide protests erupted in response to the death, in police custody, of a twenty-two-year-old named Mahsa Amini. She had been arrested for improper hijab; too much hair was showing.