The field of visually rich document understanding (VRDU) aims to solve a multitude of well-researched NLP tasks in a multi-modal domain. Several datasets exist for research on specific tasks of VRDU such as document classification (DC), key entity extraction (KEE), entity linking, visual question answering (VQA), inter alia. These datasets cover documents like invoices and receipts with sparse annotations such that they support one or two co-related tasks (e.g., entity extraction and entity linking). Unfortunately, only focusing on a single specific of documents or task is not representative of how documents often need to be processed in the wild - where variety in style and requirements is expected. In this paper, we introduce BuDDIE (Business Document Dataset for Information Extraction), the first multi-task dataset of 1,665 real-world business documents that contains rich and dense annotations for DC, KEE, and VQA. Our dataset consists of publicly available business entity documents from US state government websites. The documents are structured and vary in their style and layout across states and types (e.g., forms, certificates, reports, etc.). We provide data variety and quality metrics for BuDDIE as well as a series of baselines for each task. Our baselines cover traditional textual, multi-modal, and large language model approaches to VRDU.

The rapid progress of large language models (LLMs) has seen them excel and frequently surpass human performance on standard benchmarks. This has enabled many downstream applications, such as LLM agents, to rely on their sophisticated reasoning to navigate complex task requirements. However, LLMs are known to unexpectedly falter in simple tasks and under seemingly straightforward circumstances - underscoring the need for better and more diverse evaluation setups to measure their true capabilities. To this end, we choose to study compositional and conditional reasoning, two cornerstones of human cognition, and introduce GroundCocoa - a lexically diverse benchmark connecting these reasoning skills to the real-world problem of flight booking. Our task involves aligning detailed user preferences with available flight options presented in a multiple-choice format. Results indicate a significant disparity in performance among current state-of-the-art LLMs with even the best performing model, GPT-4 Turbo, not exceeding 67% accuracy despite advanced prompting techniques.

People rely on social skills like conflict resolution to communicate effectively and to thrive in both work and personal life. However, practice environments for social skills are typically out of reach for most people. How can we make social skill training more available, accessible, and inviting? Drawing upon interdisciplinary research from communication and psychology, this perspective paper identifies social skill barriers to enter specialized fields. Then we present a solution that leverages large language models for social skill training via a generic framework. Our AI Partner, AI Mentor framework merges experiential learning with realistic practice and tailored feedback. This work ultimately calls for cross-disciplinary innovation to address the broader implications for workforce development and social equality.

This paper explores cost-efficient methods to adapt pretrained Large Language Models (LLMs) to new lower-resource languages, with a specific focus on Estonian. Leveraging the Llama 2 model, we investigate the impact of combining cross-lingual instruction-tuning with additional monolingual pretraining. Our results demonstrate that even a relatively small amount of additional monolingual pretraining followed by cross-lingual instruction-tuning significantly enhances results on Estonian. Furthermore, we showcase cross-lingual knowledge transfer from high-quality English instructions to Estonian, resulting in improvements in commonsense reasoning and multi-turn conversation capabilities. Our best model, named \textsc{Llammas}, represents the first open-source instruction-following LLM for Estonian. Additionally, we publish Alpaca-est, the first general task instruction dataset for Estonia. These contributions mark the initial progress in the direction of developing open-source LLMs for Estonian.

Socially assistive robots (SARs) have shown great success in providing personalized cognitive-affective support for user populations with special needs such as older adults, children with autism spectrum disorder (ASD), and individuals with mental health challenges. The large body of work on SAR demonstrates its potential to provide at-home support that complements clinic-based interventions delivered by mental health professionals, making these interventions more effective and accessible. However, there are still several major technical challenges that hinder SAR-mediated interactions and interventions from reaching human-level social intelligence and efficacy. With the recent advances in large language models (LLMs), there is an increased potential for novel applications within the field of SAR that can significantly expand the current capabilities of SARs. However, incorporating LLMs introduces new risks and ethical concerns that have not yet been encountered, and must be carefully be addressed to safely deploy these more advanced systems. In this work, we aim to conduct a brief survey on the use of LLMs in SAR technologies, and discuss the potentials and risks of applying LLMs to the following three major technical challenges of SAR: 1) natural language dialog; 2) multimodal understanding; 3) LLMs as robot policies.

To govern smart contracts running on Ethereum, multiple Ethereum Request for Comment (ERC) standards have been developed, each containing a set of rules to guide the behaviors of smart contracts. Violating the ERC rules could cause serious security issues and financial loss, signifying the importance of verifying smart contracts follow ERCs. Today's practices of such verification are to either manually audit each single contract or use expert-developed, limited-scope program-analysis tools, both of which are far from being effective in identifying ERC rule violations. This paper presents a tool named AuditGPT that leverages large language models (LLMs) to automatically and comprehensively verify ERC rules against smart contracts. To build AuditGPT, we first conduct an empirical study on 222 ERC rules specified in four popular ERCs to understand their content, their security impacts, their specification in natural language, and their implementation in Solidity. Guided by the study, we construct AuditGPT by separating the large, complex auditing process into small, manageable tasks and design prompts specialized for each ERC rule type to enhance LLMs' auditing performance. In the evaluation, AuditGPT successfully pinpoints 418 ERC rule violations and only reports 18 false positives, showcasing its effectiveness and accuracy. Moreover, AuditGPT beats an auditing service provided by security experts in effectiveness, accuracy, and cost, demonstrating its advancement over state-of-the-art smart-contract auditing practices.

Sentences containing multiple semantic operators with overlapping scope often create ambiguities in interpretation, known as scope ambiguities. These ambiguities offer rich insights into the interaction between semantic structure and world knowledge in language processing. Despite this, there has been little research into how modern large language models treat them. In this paper, we investigate how different versions of certain autoregressive language models -- GPT-2, GPT-3/3.5, Llama 2 and GPT-4 -- treat scope ambiguous sentences, and compare this with human judgments. We introduce novel datasets that contain a joint total of almost 1,000 unique scope-ambiguous sentences, containing interactions between a range of semantic operators, and annotated for human judgments. Using these datasets, we find evidence that several models (i) are sensitive to the meaning ambiguity in these sentences, in a way that patterns well with human judgments, and (ii) can successfully identify human-preferred readings at a high level of accuracy (over 90% in some cases).

With the growth of model sizes and scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these. While there is a vast literature about reducing model sizes, we investigate a more traditional type of compression -- one that compresses the model to a smaller form and is coupled with a decompression algorithm that returns it to its original size -- namely lossless compression. Somewhat surprisingly, we show that such lossless compression can gain significant network and storage reduction on popular models, at times reducing over $50\%$ of the model size. We investigate the source of model compressibility, introduce compression variants tailored for models and categorize models to compressibility groups. We also introduce a tunable lossy compression technique that can further reduce size even on the less compressible models with little to no effect on the model accuracy. We estimate that these methods could save over an ExaByte per month of network traffic downloaded from a large model hub like HuggingFace.

Math Word Problem (MWP) solving presents a challenging task in Natural Language Processing (NLP). This study aims to provide MWP solvers with a more diverse training set, ultimately improving their ability to solve various math problems. We propose several methods for data augmentation by modifying the problem texts and equations, such as synonym replacement, rule-based: question replacement, and rule based: reversing question methodologies over two English MWP datasets. This study extends by introducing a new in-context learning augmentation method, employing the Llama-7b language model. This approach involves instruction-based prompting for rephrasing the math problem texts. Performance evaluations are conducted on 9 baseline models, revealing that augmentation methods outperform baseline models. Moreover, concatenating examples generated by various augmentation methods further improves performance.

Although there has been a growing interest among industries to integrate generative LLMs into their services, limited experiences and scarcity of resources acts as a barrier in launching and servicing large-scale LLM-based conversational services. In this paper, we share our experiences in developing and operating generative AI models within a national-scale search engine, with a specific focus on the sensitiveness of user queries. We propose a taxonomy for sensitive search queries, outline our approaches, and present a comprehensive analysis report on sensitive queries from actual users.