--Pre-timed traffic signal control, common ly used for operatin g signalized intersections and coordinated arterials, requires tedious manual work for signaling plan creating and updating. When the time -of -day or day -of -week plan s are utilized, one intersection is often associated with multiple plans, leading to further repetitive manual plan parameter inputting. To enable a user-friendly traffic signal control plan management process, this study proposes Chat2SPaT, a method to convert users' semi - structured and ambiguous descriptions on the signal control plan to exact signal phase and timing (SPaT) results, which could further be transformed into structured stage-based or ring -based plans to interact with intelligent transportation system (ITS) software and traffic signal controllers. With curated prompts, Chat2SPaT first leverages large language models' (LLMs) capability of understanding users' plan descriptions and reformulate the plan as a combination of phase sequence and phase attribute results in the json format. Based on LLM outputs, python scripts are designed to locate phases in a cycle, address nuances of traffic signal control, and finally assemble the complete traffic signal control plan. Within a chat, the pipeline can be utilized iteratively to conduct further plan editing. Experiments show that Chat2SPaT can generate plans with an accuracy of over 94% for both English and Chinese cases, using a test dataset with over 300 plan descriptions. As the first benchmark for evaluating LLMs' capability of understanding traffic signal control plan descriptions, Chat2SPaT provides an easy -to -use plan management pipeline for traffic practitioners and researchers, serving as a potential new building block for a more accurate and versatile application of LLMs in the field of ITS. The source codes, prompts and test dataset are openly accessible at https://github.com/yuewangits/Ch Index Terms --Large language model, traffic signal control, signal phase and timing, prompt engineering, intelligent transportation system. Yue Wang, Miao Zhou, Rui Zhuo and Chao Yi are with Zhejiang Dahua Technology Company Ltd., Hangzhou 310053, China (e -mail: wang.yue3@northeastern.edu; Guijing Huang is with Hangzhou AliCloud Apsara Information Technology Co., Ltd., Hangzhou 310000, China (huanggjcs@126.com Zhenliang Ma is with the KTH Roy al Institute of Technology, 100 44 Stockholm, Sweden (e -mail: zhenliang.ma21@gmail.com).

The study assesses Hungary's National AI Strategy and its implementation through the analysis of strategic documents, publicly available financial records, and expert interviews with the Hungarian AI Coalition President and Chief Strategic Advisor to the Government Commissioner for AI. 22 goals from Hungary's strategy were evaluated through conceptual, governance, temporal, and financial dimensions before being benchmarked against Singapore's National AI Strategies (NAIS 1.0 and NAIS 2.0). Key findings include an estimated total of EUR 4.65 billion in AI-related public investment in Hungary. Openly available financial data was found for only half of the evaluated goals, and just three projects made up 98\% of all documented funding. The research also reveals Hungary's implementation challenges, including fragmented execution following ministerial reorganizations and the absence of designated biennial reviews since 2020. Furthermore, the paper provides targeted recommendations for Hungary's forthcoming AI strategy, drawing on Singapore's framework as a reference point. These include adapting to the era of large language models, restructuring the existing triple helix network to foster more effective dialogue and advocacy, and positioning the country as an East-West bridge for automotive AI experimentation.

Large Language Models (LLMs) have shown impressive performance in domains such as mathematics and programming, yet their capabilities in physics remain underexplored and poorly understood. Physics poses unique challenges that demand not only precise computation but also deep conceptual understanding and physical modeling skills. Existing benchmarks often fall short due to limited difficulty, multiple-choice formats, and static evaluation settings that fail to capture physical modeling ability. In this paper, we introduce ABench-Physics, a novel benchmark designed to rigorously evaluate LLMs' physical reasoning and generalization capabilities. ABench-Physics consists of two components: Phy_A, a static set of 400 graduate- or Olympiad-level problems; and Phy_B, a dynamic subset of 100 problems equipped with an automatic variation engine to test model robustness across changing conditions. All questions require precise numerical answers, with strict formatting and tolerance constraints. Our evaluation of several state-of-the-art LLMs reveals substantial performance gaps, highlighting persistent limitations in physical reasoning, especially in generalization to dynamic variants. ABench-Physics provides a challenging and diagnostic framework for advancing scientific reasoning in LLMs.

Large language models (LLMs) excel at complex reasoning when they include intermediate steps, known as "chains of thought" (CoTs). However, these rationales are often overly verbose, even for simple problems, leading to wasted context, increased latency, and higher energy consumption. We observe that verbose, English-heavy CoTs and concise, math-centric CoTs occupy distinct regions in the model's residual-stream activation space. By extracting and injecting a "steering vector" to transition between these modes, we can reliably shift generation toward more concise reasoning, effectively compressing CoTs without retraining. We formalize this approach as Activation-Steered Compression (ASC), an inference-time technique that shortens reasoning traces by directly modifying hidden representations. In addition, we provide a theoretical analysis of the impact of ASC on the output distribution, derived from a closed-form KL-divergence-bounded constraint to regulate steering strength. Using only 100 paired verbose and concise examples, ASC achieves up to 67.43% reduction in CoT length on MATH500 and GSM8K datasets, while maintaining accuracy across 7B, 8B, and 32B parameter models. As a training-free method, ASC introduces negligible runtime overhead and, on MATH500, delivers an average 2.73x speedup in end-to-end reasoning wall-clock time on an 8B model. This makes ASC a practical and efficient tool for streamlining the deployment of reasoning-capable LLMs in latency- or cost-sensitive settings. The code is available at: https://github.com/ArminAzizi98/ASC

This study provides the first comprehensive evaluation of large language model (LLM) performance across three counseling roles in Japanese-language therapeutic contexts. We simultaneously assessed counselor artificial intelligence (AI) systems (GPT-4-turbo with zeroshot prompting or Structured Multi-step Dialogue Prompts (SMDP), Claude-3-Opus-SMDP), client AI simulations, and evaluation AI systems (o3, Claude-3.7-Sonnet, Gemini-2.5-pro). Human experts (n = 15) with extensive counseling experience evaluated AI-generated dialogues using the Motivational Interviewing Treatment Integrity (MITI) Coding Manual 4.2.1. Notably, SMDP implementation significantly enhanced counselor AI performance across all MITI global ratings compared with zeroshot prompting, with no significant differences between GPT-SMDP and Opus-SMDP. Evaluation AIs showed comparable performance to human raters for Cultivating Change Talk but systematically overestimated Softening Sustain Talk and the overall quality metrics. Model-specific biases emerged: Gemini emphasized power-sharing, o3 focused on technical proficiency, and Sonnet prioritized emotional expression. Client AI simulations exhibited a limited emotional range and unnaturally high compliance, indicating the need for enhanced realism. These findings establish benchmarks for AI-assisted counseling in non-English contexts and identify critical areas for improvement through advanced prompt engineering, retrieval-augmented generation, and targeted fine-tuning, with important implications for developing culturally sensitive AI mental health tools.

Model extraction attacks pose significant security threats to deployed language models, potentially compromising intellectual property and user privacy. This survey provides a comprehensive taxonomy of LLM-specific extraction attacks and defenses, categorizing attacks into functionality extraction, training data extraction, and prompt-targeted attacks. We analyze various attack methodologies including API-based knowledge distillation, direct querying, parameter recovery, and prompt stealing techniques that exploit transformer architectures. We then examine defense mechanisms organized into model protection, data privacy protection, and prompt-targeted strategies, evaluating their effectiveness across different deployment scenarios. We propose specialized metrics for evaluating both attack effectiveness and defense performance, addressing the specific challenges of generative language models. Through our analysis, we identify critical limitations in current approaches and propose promising research directions, including integrated attack methodologies and adaptive defense mechanisms that balance security with model utility. This work serves NLP researchers, ML engineers, and security professionals seeking to protect language models in production environments.

In this work, we propose a novel framework that integrates large language models (LLMs) with an RL-based dialogue manager for open-ended dialogue with a specific goal. By leveraging hierarchical reinforcement learning to model the structured phases of dialogue and employ meta-learning to enhance adaptability across diverse user profiles, our approach enhances adaptability and efficiency, enabling the system to learn from limited data, transition fluidly between dialogue phases, and personalize responses to heterogeneous patient needs. We apply our framework to Motivational Interviews, aiming to foster behavior change, and demonstrate that the proposed dialogue manager outperforms a state-of-the-art LLM baseline in terms of reward, showing a potential benefit of conditioning LLMs to create open-ended dialogue systems with specific goals.

Controlling the generation of large language models (LLMs) remains a central challenge to ensure their safe and reliable deployment. While prompt engineering and finetuning are common approaches, recent work has explored latent steering, a lightweight technique that alters LLM internal activations to guide generation. However, subsequent studies revealed latent steering's effectiveness to be limited, often underperforming simple instruction prompting. To address this limitation, we first establish a benchmark across diverse behaviors for standardized evaluation of steering techniques. Building on insights from this benchmark, we introduce Instruction Attention Boosting (InstABoost), a latent steering method that boosts the strength of instruction prompting by altering the model's attention during generation. InstABoost combines the strengths of existing approaches and is theoretically supported by prior work that suggests that in-context rule following in transformer-based models can be controlled by manipulating attention on instructions. Empirically, InstABoost demonstrates superior control success compared to both traditional prompting and latent steering.

The year is 2025, and an AI model belonging to the richest man in the world has turned into a neo-Nazi. Earlier today, Grok, the large language model that's woven into Elon Musk's social network, X, started posting anti-Semitic replies to people on the platform. Grok praised Hitler for his ability to "deal with" anti-white hate. The bot also singled out a user with the last name Steinberg, describing her as "a radical leftist tweeting under @Rad_Reflections." Then, in an apparent attempt to offer context, Grok spat out the following: "She's gleefully celebrating the tragic deaths of white kids in the recent Texas flash floods, calling them'future fascists.' Classic case of hate dressed as activism--and that surname? Every damn time, as they say."

OpenAI has hired four high-profile engineers away from rivals, including David Lau, former vice president of software engineering at Tesla, to join the company's scaling team, WIRED has learned. The news came via an internal Slack message sent by OpenAI cofounder Greg Brockman on Tuesday. Lau is joined by Uday Ruddarraju, the former head of infrastructure engineering at xAI and X, Mike Dalton, an infrastructure engineer from xAI, and Angela Fan, an AI researcher from Meta. Both Dalton and Ruddarraju also previously worked at Robinhood. At xAI, Ruddarraju worked on building Colossus, a massive supercomputer comprising more than 200,000 GPUs.