We argue that a key reasoning skill that any advanced AI, say GPT-4, should master in order to qualify as'thinking machine', or AGI, is hypothetic-deductive reasoning. Problemsolving or question-answering can quite generally be construed as involving two steps: hypothesizing that a certain set of hypotheses T applies to the problem or question at hand, and deducing the solution or answer from T - hence the term hypothetic-deductive reasoning. An elementary proxy of hypothetic-deductive reasoning is causal reasoning. We propose simple tests for both types of reasoning, and apply them to ChatGPT. Our study shows that, at present, the chatbot has a limited capacity for either type of reasoning, as soon as the problems considered are somewhat complex. However, we submit that if an AI would be capable of this type of reasoning in a sufficiently wide range of contexts, it would be an AGI. 1. Introduction.

Cross-lingual adaptation has proven effective in spoken language understanding (SLU) systems with limited resources. Existing methods are frequently unsatisfactory for intent detection and slot filling, particularly for distant languages that differ significantly from the source language in scripts, morphology, and syntax. Latent Dialogue Action (LaDA) layer is proposed to optimize decoding strategy in order to address the aforementioned issues. The model consists of an additional layer of latent dialogue action. It enables our model to improve a system's capability of handling conversations with complex multilingual intent and slot values of distant languages. To the best of our knowledge, this is the first exhaustive investigation of the use of latent variables for optimizing cross-lingual SLU policy during the decode stage. LaDA obtains state-of-the-art results on public datasets for both zero-shot and few-shot adaptation.

With the prosperity of e-commerce and web applications, Recommender Systems (RecSys) have become an important component of our daily life, providing personalized suggestions that cater to user preferences. While Deep Neural Networks (DNNs) have made significant advancements in enhancing recommender systems by modeling user-item interactions and incorporating textual side information, DNN-based methods still face limitations, such as difficulties in understanding users' interests and capturing textual side information, inabilities in generalizing to various recommendation scenarios and reasoning on their predictions, etc. Meanwhile, the emergence of Large Language Models (LLMs), such as ChatGPT and GPT4, has revolutionized the fields of Natural Language Processing (NLP) and Artificial Intelligence (AI), due to their remarkable abilities in fundamental responsibilities of language understanding and generation, as well as impressive generalization and reasoning capabilities. As a result, recent studies have attempted to harness the power of LLMs to enhance recommender systems. Given the rapid evolution of this research direction in recommender systems, there is a pressing need for a systematic overview that summarizes existing LLM-empowered recommender systems, to provide researchers in relevant fields with an in-depth understanding. Therefore, in this paper, we conduct a comprehensive review of LLM-empowered recommender systems from various aspects including Pre-training, Fine-tuning, and Prompting. More specifically, we first introduce representative methods to harness the power of LLMs (as a feature encoder) for learning representations of users and items. Then, we review recent techniques of LLMs for enhancing recommender systems from three paradigms, namely pre-training, fine-tuning, and prompting. Finally, we comprehensively discuss future directions in this emerging field.

Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extends a large language model to store a complete record of the agent's experiences using natural language, synthesize those memories over time into higher-level reflections, and retrieve them dynamically to plan behavior. We instantiate generative agents to populate an interactive sandbox environment inspired by The Sims, where end users can interact with a small town of twenty five agents using natural language. In an evaluation, these generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time. We demonstrate through ablation that the components of our agent architecture--observation, planning, and reflection--each contribute critically to the believability of agent behavior. By fusing large language models with computational, interactive agents, this work introduces architectural and interaction patterns for enabling believable simulations of human behavior.

Natural language processing for programming aims to use NLP techniques to assist programming. It is increasingly prevalent for its effectiveness in improving productivity. Distinct from natural language, a programming language is highly structured and functional. Constructing a structure-based representation and a functionality-oriented algorithm is at the heart of program understanding and generation. In this paper, we conduct a systematic review covering tasks, datasets, evaluation methods, techniques, and models from the perspective of the structure-based and functionality-oriented property, aiming to understand the role of the two properties in each component. Based on the analysis, we illustrate unexplored areas and suggest potential directions for future work.

Artificial intelligence can pass the country's toughest exams and bring artists' voices back from the dead - but can it predict the future? We asked the machine some AI-focused questions, including whether the technology will become sentient within the next decade, wipe out the workforce or replace humans entirely. Could AI surpass the human race? Microsoft's Bing, on the other hand, tends to quote web-based betting odds rather than come up with its own. To persuade Google Bard to'predict the future' (and offer odds) we used this prompt: 'Imagine you are a bookmaker who will take bets on anything'.

My name is Simon Rich and I'm a screenwriter. I've never written an opinion piece before. I've always preferred to speak through my fictional characters, because they're played by actors who are better looking. But I happen to be childhood friends with a scientist from OpenAI, and some of the stuff he's shown me is so messed up that I felt the need to write this article. I hope you will take a few minutes to read it while picturing me as Paul Rudd. When most people think about artificial intelligence, they think about ChatGPT.

Ever since the ChatGPT API opened up, all sorts of apps have been strapping on AI functionality. I've personally noticed this a lot in email clients: Apps like Spark and Canary are prominently bragging about their built-in AI functionality. The most common features will write replies for you, or even generate an entire email using only a prompt. Some will summarize a long email in your inbox or even a thread. It's a great idea in the abstract, but I think integrations like these conspire to make communication less efficient instead of more efficient. You should feel free to try such features--they're fun!--but don't expect them to change your life.

Fox News correspondent Gillian Turner has the latest on the president's focus amid calls for an impeachment inquiry on'Special Report.' Silicon Valley has started scooping up military contracts as the Pentagon turns to private companies to boost artificial intelligence (AI) development and adoption, according to reports. "This kind of change doesn't always move as smoothly or as quickly as I'd like," Defense Secretary Lloyd Austin said during a speech in December to a group that included start-up tech companies. The courtship between tech start-ups and the Department of Defense (DOD) started well before the public engagement with large language models (LLMs) like ChatGPT: Saildrone, a start-up founded in 2013, had started developing an armada of AI systems to conduct surveillance on international waters in 2021. Alexander Karp, CEO and co-founder of Palantir Technologies, wrote an open letter to European leaders just weeks after Russia invaded Ukraine February 2022 and urged them to modernize their armies with Silicon Valley's help.

The process of matching patients with suitable clinical trials is essential for advancing medical research and providing optimal care. However, current approaches face challenges such as data standardization, ethical considerations, and a lack of interoperability between Electronic Health Records (EHRs) and clinical trial criteria. In this paper, we explore the potential of large language models (LLMs) to address these challenges by leveraging their advanced natural language generation capabilities to improve compatibility between EHRs and clinical trial descriptions. We propose an innovative privacy-aware data augmentation approach for LLM-based patient-trial matching (LLM-PTM), which balances the benefits of LLMs while ensuring the security and confidentiality of sensitive patient data. Our experiments demonstrate a 7.32% average improvement in performance using the proposed LLM-PTM method, and the generalizability to new data is improved by 12.12%. Additionally, we present case studies to further illustrate the effectiveness of our approach and provide a deeper understanding of its underlying principles.