Americans pulling into a Starbucks drive thru might think they are being served by a friendly staff member. But at some locations, the voice listening to the order is actually an AI robot. Behind the counter inside the store, baristas can lean on a virtual personal assistant to recall recipes or manage schedules. In the back of the shop, a scanning tool has taken on the painstaking process of counting the inventory, relieving staff of one of retail's most tedious chores, in a bid to fix the out-of-stock gaps that have frustrated the firm. The new technology is part of the hundreds of millions of dollars the 55-year-old coffee giant has been investing as it tries to win back customers after several years of struggling sales.

This research proposes a systematic, large language model (LLM) approach for extracting product and service attributes, features, and associated sentiments from customer reviews. Grounded in marketing theory, the framework distinguishes perceptual attributes from actionable features, producing interpretable and managerially actionable insights. We apply the methodology to 20,000 Yelp reviews of Starbucks stores and evaluate eight prompt variants on a random subset of reviews. Model performance is assessed through agreement with human annotations and predictive validity for customer ratings. Results show high consistency between LLMs and human coders and strong predictive validity, confirming the reliability of the approach. Human coders required a median of six minutes per review, whereas the LLM processed each in two seconds, delivering comparable insights at a scale unattainable through manual coding. Managerially, the analysis identifies attributes and features that most strongly influence customer satisfaction and their associated sentiments, enabling firms to pinpoint "joy points," address "pain points," and design targeted interventions. We demonstrate how structured review data can power an actionable marketing dashboard that tracks sentiment over time and across stores, benchmarks performance, and highlights high-leverage features for improvement. Simulations indicate that enhancing sentiment for key service features could yield 1-2% average revenue gains per store.

The advancement of Large Language Models (LLMs) has greatly improved our ability to process complex language. However, accurately detecting logical fallacies remains a significant challenge. This study presents a novel and effective prompt formulation approach for logical fallacy detection, applicable in both supervised (fine-tuned) and unsupervised (zero-shot) settings. Our method enriches input text incorporating implicit contextual information -- counterarguments, explanations, and goals -- which we query for validity within the context of the argument. We then rank these queries based on confidence scores to inform classification. We evaluate our approach across multiple datasets from 5 domains, covering 29 distinct fallacy types, using models from the GPT and LLaMA series. The results show substantial improvements over state-of-the-art models, with F1 score increases of up to 0.60 in zero-shot settings and up to 0.45 in fine-tuned models. Extensive analyses further illustrate why and how our method excels.

Autonomous mobile app interaction has become increasingly important with growing complexity of mobile applications. Developing intelligent agents that can effectively navigate and interact with mobile apps remains a significant challenge. In this paper, we propose an Explainable Behavior Cloning LLM Agent (EBC-LLMAgent), a novel approach that combines large language models (LLMs) with behavior cloning by learning demonstrations to create intelligent and explainable agents for autonomous mobile app interaction. EBC-LLMAgent consists of three core modules: Demonstration Encoding, Code Generation, and UI Mapping, which work synergistically to capture user demonstrations, generate executable codes, and establish accurate correspondence between code and UI elements. We introduce the Behavior Cloning Chain Fusion technique to enhance the generalization capabilities of the agent. Extensive experiments on five popular mobile applications from diverse domains demonstrate the superior performance of EBC-LLMAgent, achieving high success rates in task completion, efficient generalization to unseen scenarios, and the generation of meaningful explanations.

Efficient processing of tabular data is important in various industries, especially when working with datasets containing a large number of columns. Large language models (LLMs) have demonstrated their ability on several tasks through carefully crafted prompts. However, creating effective prompts for tabular datasets is challenging due to the structured nature of the data and the need to manage numerous columns. This paper presents an innovative auto-prompt generation system suitable for multiple LLMs, with minimal training. It proposes two novel methods; 1) A Reinforcement Learning-based algorithm for identifying and sequencing task-relevant columns 2) Cell-level similarity-based approach for enhancing few-shot example selection. Our approach has been extensively tested across 66 datasets, demonstrating improved performance in three downstream tasks: data imputation, error detection, and entity matching using two distinct LLMs; Google flan-t5-xxl and Mixtral 8x7B.

Solving this problem can improve precision by removing duplicates, and can enrich detail by (for example) merging a phone Location matters in many businesses and services today, number from one record with the hours of operation particularly for transportation and delivery, scenarios from another, once these records are known to refer in which it is important to find the correct pickup to the same thing. This problem is referred to as entity and drop-off locations very quickly. User experience resolution (see (Talburt, 2011)), and it occurs with can be negatively affected if the location information various datasets, including those representing people, is inaccurate or insufficient. Inaccuracies products, works of literature, etc. can originate from imprecise GPS data, manual error happening in the process of data entry, or the lack of For Grab, one entity resolution problem that arises effective data quality control. Insufficiencies can also for spatial data is the alignment of transportation destinations take many forms, including lack of coverage, and lack and restaurants. Currently Grab maintains of detail -- for example, we may know the latitude two tables separately for transportation and food delivery, and longitude of a restaurant location in a mall, but because each use case requires some specific this might not include information about where passengers features, i.e., food delivery needs information about should be dropped off, or where a delivery the estimated delivery time, cuisine types, and opening courier should park to collect food for delivery. Or hours which are absent in the POI table. However, the location of a business may be known, but not its it is highly likely that some entities from both tables contact details or opening hours.

We present Deep Search DocQA. This application enables information extraction from documents via a question-answering conversational assistant. The system integrates several technologies from different AI disciplines consisting of document conversion to machine-readable format (via computer vision), finding relevant data (via natural language processing), and formulating an eloquent response (via large language models). Users can explore over 10,000 Environmental, Social, and Governance (ESG) disclosure reports from over 2000 corporations. The Deep Search platform can be accessed at: https://ds4sd.github.io.

While it upends the art world, AI-powered technology is sweeping through another industry: Fast food. Technology powered by AI has been used in restaurants for some time to improve customer experience and monitor internal expenses. Now, AI-powered voice bots will be putting in your orders. Taco Bell's parent company Yum Brands recently shared that it's testing an AI-powered conversational bot that takes orders in the drive-thru lane. The AI voice bot could help the chain "potentially automate ordering," according to Business Insider.

The rise of restaurant robots is upon us. Major fast-food chains are employing robots to flip burgers, brew espressos and greet customers - and it is a fraction of the cost compared to paying human workers. White Castle is testing the Flippy robot at 100 locations and Chipotle uses a one-armed robot to make tortilla chips at 73 sites - both cost $3,000 a month - and Starbucks has $18,000 AI-powered espresso machines in at least 1,200 locations. As food costs rise and an intense labor shortage grips the US, paying monthly rentals for machines has become a cost-effective option. The National Restaurant Association recently reported that four in five operators are understaffed and have been since the COVID-19 pandemic hit in 2020.

A personalized customer experience has become the basis for competitive advantage. However, providing personalization requires more than just a technological fix. Businesses must design intelligent experience engines, which assemble high-quality, end-to-end customer experiences using AI powered by customer data. Brinks is a 163-year-old business well-known for its fleet of armored trucks. The company also licenses its brand to a lesser-known, independently operated sister company, Brinks Home. The Dallas-based smart-home-technology business has struggled to gain brand recognition commensurate with the Brinks name. It competes against better-known systems from ADT, Google Nest, and Ring, and although it has earned stellar reviews from industry analysts and customers, its market share is only 2%.