We introduce Fraud-R1, a benchmark designed to evaluate LLMs' ability to defend against internet fraud and phishing in dynamic, real-world scenarios. Fraud-R1 comprises 8,564 fraud cases sourced from phishing scams, fake job postings, social media, and news, categorized into 5 major fraud types. Unlike previous benchmarks, Fraud-R1 introduces a multi-round evaluation pipeline to assess LLMs' resistance to fraud at different stages, including credibility building, urgency creation, and emotional manipulation. Furthermore, we evaluate 15 LLMs under two settings: 1. Helpful-Assistant, where the LLM provides general decision-making assistance, and 2. Role-play, where the model assumes a specific persona, widely used in real-world agent-based interactions. Our evaluation reveals the significant challenges in defending against fraud and phishing inducement, especially in role-play settings and fake job postings. Additionally, we observe a substantial performance gap between Chinese and English, underscoring the need for improved multilingual fraud detection capabilities.

End-to-end Task-Oriented Dialog (TOD) systems typically require extensive training datasets to perform well. In contrast, large language model (LLM) based TOD systems can excel even with limited data due to their ability to learn tasks through in-context exemplars. However, these models lack alignment with the style of responses in training data and often generate comprehensive responses, making it difficult for users to grasp the information quickly. In response, we propose SyncTOD that synergizes LLMs with task-specific hints to improve alignment in low-data settings. SyncTOD employs small auxiliary models to provide hints and select exemplars for in-context prompts. With ChatGPT, SyncTOD achieves superior performance compared to LLM-based baselines and SoTA models in low-data settings, while retaining competitive performance in full-data settings.

Dark pools are electronic trading platforms that have emerged in the past decade in advanced markets. They allow traders to buy or sell large blocks of shares without having to disclose their identities, the volumes or prices, unlike traditional exchanges. They are popular with asset-management companies, pension funds and insurance firms which need to conduct a lot of large transactions, because they are cheaper and easier to carry out via electronic trading platforms. Merrin founded Liquidnet in 2001 in the US and later expanded into Europe and Asia-Pacific. The platform has seen trading volume in Asia-Pacific of US$42 billion so far this year, up 57 per cent from a year earlier.

A humanised robot named Sophia who was created and programmed locally advised Hong Kong's leader on Wednesday on how to succeed with plans for a smart city. In a nine-minute dialogue with Chief Executive Carrie Lam Cheng Yuet-ngor at the American Chamber of Commerce's smart city forum in Wan Chai, Sophia anticipated "even greater things" in Hong Kong's blueprint for innovation as unveiled by the top official last December. Dressed in a dark blue sleeveless top and at times blinking her eyes and smiling gently, Sophia gave Lam a pat on the back when answering a question on which part of the blueprint was her favourite. "My favourite part, unsurprisingly, is initiatives to attract a venture capital fund to support entrepreneurship and promote technology to parks such as Science Park, which is my home base, and facilitate research and development for universities," Sophia said, as she addressed Lam as "chief executive". Though Hong Kong slipped one notch to second after the United States as the world's most competitive economy in a ranking last month, Lam said the city was striving to become smarter by boosting innovation and technology in areas such as transport, payment systems and government data-sharing.

A common problem for companies with strong business growth is that it is hard to find enough experienced staff to support expansion needs. This problem is particular pronounced for operations planners and controllers who must be very highly knowledgeable and experienced with the business domain. This article is a case study of how one of the largest travel agencies in Hong Kong alleviated this problem by using AI to support decision-making and problem-solving so that their planners and controllers can work more effectively and efficiently to sustain business growth while maintaining consistent quality of service. AI is used in a mission critical fleet management system (FMS) that supports the scheduling and management of a fleet of luxury limousines for business travelers. The AI problem was modeled as a constraint satisfaction problem (CSP). The use of AI enabled the travel agency to sign up additional hotel partners, handle more orders and expand their fleet with their existing team of planners and controllers. Using modern web 2.0 architecture and proven AI technology, we were able to achieve low-risk implementation and deployment success with concrete and measurable business benefits.