Large Language Models (LLMs) have significantly enhanced Information Retrieval (IR) across various modules, such as reranking. Despite impressive performance, current zero-shot relevance ranking with LLMs heavily relies on human prompt engineering. Existing automatic prompt engineering algorithms primarily focus on language modeling and classification tasks, leaving the domain of IR, particularly reranking, underexplored. Directly applying current prompt engineering algorithms to relevance ranking is challenging due to the integration of query and long passage pairs in the input, where the ranking complexity surpasses classification tasks. To reduce human effort and unlock the potential of prompt optimization in reranking, we introduce a novel automatic prompt engineering algorithm named APEER. APEER iteratively generates refined prompts through feedback and preference optimization. Extensive experiments with four LLMs and ten datasets demonstrate the substantial performance improvement of APEER over existing state-of-the-art (SoTA) manual prompts. Furthermore, we find that the prompts generated by APEER exhibit better transferability across diverse tasks and LLMs. Code is available at https://github.com/jincan333/APEER.

Did you miss a session from GamesBeat Summit Next 2022? All sessions are now available for viewing in our on-demand library. Click here to start watching. With Google Assistant inside and conversational AI, these speakers can do a great range of things. Here's 10 worth trying, drawn from VentureBeat coverage over the course of the past year. Before getting into the more dynamic features Google Assistant provides through Home smart speakers, start with the most popular ways people use speakers with intelligent assistants.

The machine learning models can determine the intent of the words being used, from audio commands to windshield wipers or even finding a five-star- …

At the end of a long week filled with too many deadlines and too little sleep, you wake up one morning woozy with a strange pain in your arm. You call your doctor, and she asks you a series of questions over the phone. She then tells you to go to the emergency room pronto: "I suspect you're having a heart attack." The doctor reached that conclusion not by simply making an educated guess, but by evaluating the data and using deductive reasoning. In medical school, physicians learn to estimate probabilities of disease based on symptoms, patient history, examination findings and labs or images.

Looking at the literature and current work done on Artificial Intelligence (AI), the focus is usually on aspects related with aggregating, learning and reasoning. The use cases and benefits are mainly derived from these key aspects. However, one important aspect of AI in the future will be the integration capability as AI can play a role as an integrator of knowledge, processes, decisions and actions. Today, it is possible to define AI in terms of a set of key components including machine learning, computer vision, natural language processing and natural language understanding. These components represent both the key technology pillars and the key enablers of myriad of business use-cases.

Artificial intelligence has been making waves in recent years, enabling us to solve problems faster than traditional computing could ever allow. Recently, for example, Google's artificial intelligence subsidiary DeepMind developed AlphaFold2, a program that solved the protein-folding problem. This is a problem that has had baffled scientists for 50 years. Advances in AI have allowed us to make progress in all kinds of disciplines – and these are not limited to applications on this planet. From designing missions to clearing Earth's orbit of junk, here are a few ways artificial intelligence can help us venture further into space. Do you remember Tars and Case, the assistant robots from the film Interstellar?

Artificial intelligence has been making waves in recent years, enabling us to solve problems faster than traditional computing could ever allow. Recently, for example, Google's artificial intelligence subsidiary DeepMind developed AlphaFold2, a program which solved the protein-folding problem. This is a problem which has had baffled scientists for 50 years. Advances in AI have allowed us to make progress in all kinds of disciplines – and these are not limited to applications on this planet. From designing missions to clearing Earth's orbit of junk, here are a few ways artificial intelligence can help us venture further in space.

By 2050, the Internet will become a truly global network and it will permeate every part of our planet and our everyday lives. We won't be able to imagine our lives without being connected to the internet. Everything and everyone will be connected to the global network, cars, home appliances, public transport, elevators, traffic light signals, etc. All devices will be network-enabled. Satellites in lower orbits will provide total global network coverage.

Intelligent assistants that follow commands or answer simple questions, such as Siri and Google search, are among the most economically important applications of AI. Future conversational AI assistants promise even greater capabilities and a better user experience through a deeper understanding of the domain, the user, or the user's purposes. But what domain and what methods are best suited to researching and realizing this promise? In this article we argue for the domain of voice document editing and for the methods of model-based reinforcement learning. The primary advantages of voice document editing are that the domain is tightly scoped and that it provides something for the conversation to be about (the document) that is delimited and fully accessible to the intelligent assistant. The advantages of reinforcement learning in general are that its methods are designed to learn from interaction without explicit instruction and that it formalizes the purposes of the assistant. Model-based reinforcement learning is needed in order to genuinely understand the domain of discourse and thereby work efficiently with the user to achieve their goals. Together, voice document editing and model-based reinforcement learning comprise a promising research direction for achieving conversational AI.

These AI-enabled conversational agents can quickly identify the customer and help answer a variety of questions. If the customer needs to be transferred to a human agent, the intelligent assistant can be used in an augmented manner to help the customer service representative better identify customer issues while on the phone. This kind of personal assistant AI has upside for companies wanting to improve their customer support systems. Unlike human agents who can only handle a handful of conversations at a time, chatbots can be easily scaled to manage thousands of discussions without hindering the speed or accuracy of responses. Intelligent assistants have also become more common in the workplace, as they have the ability to act as augmentative resources for organizations. Rather than having an employee handle repetitive tasks, companies have turned to AI-enabled assistants that are available around the clock to assist with their organizational needs.