Simulating a single trajectory of a dynamical system under some state-dependent policy is a core bottleneck in policy optimization algorithms. The many inherently serial policy evaluations that must be performed in a single simulation constitute the bulk of this bottleneck. To wit, in applying policy optimization to supply chain optimization (SCO) problems, simulating a single month of a supply chain can take several hours. We present an iterative algorithm for policy simulation, which we dub Picard Iteration. This scheme carefully assigns policy evaluation tasks to independent processes. Within an iteration, a single process evaluates the policy only on its assigned tasks while assuming a certain 'cached' evaluation for other tasks; the cache is updated at the end of the iteration. Implemented on GPUs, this scheme admits batched evaluation of the policy on a single trajectory. We prove that the structure afforded by many SCO problems allows convergence in a small number of iterations, independent of the horizon. We demonstrate practical speedups of 400x on large-scale SCO problems even with a single GPU, and also demonstrate practical efficacy in other RL environments.

The PRFashion24 dataset is a comprehensive Persian dataset collected from various online fashion stores, spanning from April 2020 to March 2024. With 767,272 reviews, it is the first dataset in its kind that encompasses diverse categories within the fashion industry in the Persian language. The goal of this study is to harness deep learning techniques, specifically Long Short-Term Memory (LSTM) networks and a combination of Bidirectional LSTM and Convolutional Neural Network (BiLSTM-CNN), to analyze and reveal sentiments towards online fashion shopping. The LSTM model yielded an accuracy of 81.23%, while the BiLSTM-CNN model reached 82.89%. This research aims not only to introduce a diverse dataset in the field of fashion but also to enhance the public's understanding of opinions on online fashion shopping, which predominantly reflect a positive sentiment. Upon publication, both the optimized models and the PRFashion24 dataset will be available on GitHub.

Product attribute extraction is an growing field in e-commerce business, with several applications including product ranking, product recommendation, future assortment planning and improving online shopping customer experiences. Understanding the customer needs is critical part of online business, specifically fashion products. Retailers uses assortment planning to determine the mix of products to offer in each store and channel, stay responsive to market dynamics and to manage inventory and catalogs. The goal is to offer the right styles, in the right sizes and colors, through the right channels. When shoppers find products that meet their needs and desires, they are more likely to return for future purchases, fostering customer loyalty. Product attributes are a key factor in assortment planning. In this paper we present PAE, a product attribute extraction algorithm for future trend reports consisting text and images in PDF format. Most existing methods focus on attribute extraction from titles or product descriptions or utilize visual information from existing product images. Compared to the prior works, our work focuses on attribute extraction from PDF files where upcoming fashion trends are explained. This work proposes a more comprehensive framework that fully utilizes the different modalities for attribute extraction and help retailers to plan the assortment in advance. Our contributions are three-fold: (a) We develop PAE, an efficient framework to extract attributes from unstructured data (text and images); (b) We provide catalog matching methodology based on BERT representations to discover the existing attributes using upcoming attribute values; (c) We conduct extensive experiments with several baselines and show that PAE is an effective, flexible and on par or superior (avg 92.5% F1-Score) framework to existing state-of-the-art for attribute value extraction task.

This paper introduces a novel approach using Large Language Models (LLMs) integrated into an agent framework for flexible and effective personal mobility generation. LLMs overcome the limitations of previous models by effectively processing semantic data and offering versatility in modeling various tasks. Our approach addresses three research questions: aligning LLMs with real-world urban mobility data, developing reliable activity generation strategies, and exploring LLM applications in urban mobility. The key technical contribution is a novel LLM agent framework that accounts for individual activity patterns and motivations, including a self-consistency approach to align LLMs with real-world activity data and a retrieval-augmented strategy for interpretable activity generation. We evaluate our LLM agent framework and compare it with state-of-the-art personal mobility generation approaches, demonstrating the effectiveness of our approach and its potential applications in urban mobility. Overall, this study marks the pioneering work of designing an LLM agent framework for activity generation based on real-world human activity data, offering a promising tool for urban mobility analysis.

Despite the notable advancements of existing prompting methods, such as In-Context Learning and Chain-of-Thought for Large Language Models (LLMs), they still face challenges related to various biases. Traditional debiasing methods primarily focus on the model training stage, including approaches based on data augmentation and reweighting, yet they struggle with the complex biases inherent in LLMs. To address such limitations, the causal relationship behind the prompting methods is uncovered using a structural causal model, and a novel causal prompting method based on front-door adjustment is proposed to effectively mitigate LLMs biases. In specific, causal intervention is achieved by designing the prompts without accessing the parameters and logits of LLMs. The chain-of-thought generated by LLM is employed as the mediator variable and the causal effect between input prompts and output answers is calculated through front-door adjustment to mitigate model biases. Moreover, to accurately represent the chain-of-thoughts and estimate the causal effects, contrastive learning is used to fine-tune the encoder of chain-of-thought by aligning its space with that of the LLM. Experimental results show that the proposed causal prompting approach achieves excellent performance across seven natural language processing datasets on both open-source and closed-source LLMs.

Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, without any weight updates. Newly expanded context windows allow us to investigate ICL with hundreds or thousands of examples -- the many-shot regime. Going from few-shot to many-shot, we observe significant performance gains across a wide variety of generative and discriminative tasks. While promising, many-shot ICL can be bottlenecked by the available amount of human-generated examples. To mitigate this limitation, we explore two new settings: Reinforced and Unsupervised ICL. Reinforced ICL uses model-generated chain-of-thought rationales in place of human examples. Unsupervised ICL removes rationales from the prompt altogether, and prompts the model only with domain-specific questions. We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks. Finally, we demonstrate that, unlike few-shot learning, many-shot learning is effective at overriding pretraining biases, can learn high-dimensional functions with numerical inputs, and performs comparably to fine-tuning. Our analysis also reveals the limitations of next-token prediction loss as an indicator of downstream ICL performance.

We introduce the application of online learning in a Stackelberg game pertaining to a system with two learning agents in a dyadic exchange network, consisting of a supplier and retailer, specifically where the parameters of the demand function are unknown. In this game, the supplier is the first-moving leader, and must determine the optimal wholesale price of the product. Subsequently, the retailer who is the follower, must determine both the optimal procurement amount and selling price of the product. In the perfect information setting, this is known as the classical price-setting Newsvendor problem, and we prove the existence of a unique Stackelberg equilibrium when extending this to a two-player pricing game. In the framework of online learning, the parameters of the reward function for both the follower and leader must be learned, under the assumption that the follower will best respond with optimism under uncertainty. A novel algorithm based on contextual linear bandits with a measurable uncertainty set is used to provide a confidence bound on the parameters of the stochastic demand. Consequently, optimal finite time regret bounds on the Stackelberg regret, along with convergence guarantees to an approximate Stackelberg equilibrium, are provided.

Engaging in recreational activities in public spaces poses challenges for blind people, often involving dependency on sighted help. Window shopping is a key recreational activity that remains inaccessible. In this paper, we investigate the information needs, challenges, and current approaches blind people have to recreational window shopping to inform the design of existing wayfinding and navigation technology for supporting blind shoppers in exploration and serendipitous discovery. We conduct a formative study with a total of 18 blind participants that include both focus groups (N=8) and interviews for requirements analysis (N=10). We find that there is a desire for push notifications of promotional information and pull notifications about shops of interest such as the targeted audience of a brand. Information about obstacles and points-of-interest required customization depending on one's mobility aid as well as presence of a crowd, children, and wheelchair users. We translate these findings into specific information modalities and rendering in the context of two existing AI-infused assistive applications: NavCog (a turn-by-turn navigation app) and Cabot (a navigation robot).

Online commerce relies heavily on user generated reviews to provide unbiased information about products that they have not physically seen. The importance of reviews has attracted multiple exploitative online behaviours and requires methods for monitoring and detecting reviews. We present a machine learning methodology for review detection and extraction, and demonstrate that it generalises for use across websites that were not contained in the training data. This method promises to drive applications for automatic detection and evaluation of reviews, regardless of their source. Furthermore, we showcase the versatility of our method by implementing and discussing three key applications for analysing reviews: Sentiment Inconsistency Analysis, which detects and filters out unreliable reviews based on inconsistencies between ratings and comments; Multi-language support, enabling the extraction and translation of reviews from various languages without relying on HTML scraping; and Fake review detection, achieved by integrating a trained NLP model to identify and distinguish between genuine and fake reviews.

As the popularity of Large Language Models (LLMs) grow, combining model safety with utility becomes increasingly important. The challenge is making sure that LLMs can recognize and decline dangerous prompts without sacrificing their ability to be helpful. The problem of "exaggerated safety" demonstrates how difficult this can be. To reduce excessive safety behaviours -- which was discovered to be 26.1% of safe prompts being misclassified as dangerous and refused -- we use a combination of XSTest dataset prompts as well as interactive, contextual, and few-shot prompting to examine the decision bounds of LLMs such as Llama2, Gemma Command R+, and Phi-3. We find that few-shot prompting works best for Llama2, interactive prompting works best Gemma, and contextual prompting works best for Command R+ and Phi-3. Using a combination of these prompting strategies, we are able to mitigate exaggerated safety behaviors by an overall 92.9% across all LLMs. Our work presents a multiple prompting strategies to jailbreak LLMs' decision-making processes, allowing them to navigate the tight line between refusing unsafe prompts and remaining helpful.