In this paper, we introduce LLMind, an AI framework that utilizes large language models (LLMs) as a central orchestrator. The framework integrates LLMs with domain-specific AI modules, enabling IoT devices to collaborate effectively in executing complex tasks. The LLM engages in natural conversations with human users via a user-friendly social media platform to come up with a plan to execute complex tasks. In particular, the execution of a complex task, which may involve the collaborations of multiple domain-specific AI modules and IoT devices, is realized through a control script. The LLM generates the control script using a Language-Code transformation approach based on finite-state machines (FSMs). The framework also incorporates semantic analysis and response optimization techniques to enhance speed and effectiveness. Ultimately, this framework is designed not only to innovate IoT device control and enrich user experiences but also to foster an intelligent and integrated IoT device ecosystem that evolves and becomes more sophisticated through continuing user and machine interactions.

Despite increasing awareness and research around fake news, there is still a significant need for datasets that specifically target racial slurs and biases within North American political speeches. This is particulary important in the context of upcoming North American elections. This study introduces a comprehensive dataset that illuminates these critical aspects of misinformation. To develop this fake news dataset, we scraped and built a corpus of 40,000 news articles about political discourses in North America. A portion of this dataset (4000) was then carefully annotated, using a blend of advanced language models and human verification methods. We have made both these datasets openly available to the research community and have conducted benchmarking on the annotated data to demonstrate its utility. We release the best-performing language model along with data. We encourage researchers and developers to make use of this dataset and contribute to this ongoing initiative.

Language models (LMs) have achieved notable success in numerous NLP tasks, employing both fine-tuning and in-context learning (ICL) methods. While language models demonstrate exceptional performance, they face robustness challenges due to spurious correlations arising from imbalanced label distributions in training data or ICL exemplars. Previous research has primarily concentrated on word, phrase, and syntax features, neglecting the concept level, often due to the absence of concept labels and difficulty in identifying conceptual content in input texts. This paper introduces two main contributions. First, we employ ChatGPT to assign concept labels to texts, assessing concept bias in models during fine-tuning or ICL on test data. We find that LMs, when encountering spurious correlations between a concept and a label in training or prompts, resort to shortcuts for predictions. Second, we introduce a data rebalancing technique that incorporates ChatGPT-generated counterfactual data, thereby balancing label distribution and mitigating spurious correlations. Our method's efficacy, surpassing traditional token removal approaches, is validated through extensive testing.

Personality plays a pivotal role in shaping human expression patterns, thus regulating the personality of large language models (LLMs) holds significant potential in enhancing the user experience of LLMs. Previous methods either relied on fine-tuning LLMs on specific corpora or necessitated manually crafted prompts to elicit specific personalities from LLMs. However, the former approach is inefficient and costly, while the latter cannot precisely manipulate personality traits at a fine-grained level. To address the above challenges, we have employed a novel Unsupervisedly-Built Personalized Lexicons (UBPL) in a pluggable manner during the decoding phase of LLMs to manipulate their personality traits. UBPL is a lexicon built through an unsupervised approach from a situational judgment test dataset (SJTs4LLM). Users can utilize UBPL to adjust the probability vectors of predicted words in the decoding phase of LLMs, thus influencing the personality expression of LLMs. Extensive experimentation demonstrates the remarkable effectiveness and pluggability of our method for fine-grained manipulation of LLM's personality.

Marketers spend billions of dollars on advertisements but to what end? At the time of purchase, if customers cannot recognize the brand for which they saw an ad, the money spent on the ad is essentially wasted. Despite its importance in marketing, until now, there has been no study on the memorability of ads in the ML literature. Most studies have been conducted on short-term recall (<5 mins) on specific content types like object and action videos. On the other hand, the advertising industry only cares about long-term memorability, and ads are almost always highly multimodal, depicting a story through its different modalities. With this motivation, we release the first large-scale memorability dataset, LAMDBA, consisting of 1749 participants and 2205 ads covering 276 brands. Running statistical tests over different participant subpopulations and ad types, we find many interesting insights into what makes an ad memorable. For e.g., we find that brands that use commercials with fast-moving scenes are more memorable than those with slower scenes (p=8e-10) and that people who use ad-blockers remember fewer ads than those who don't (p=5e-3). Next, to simulate the memorability of marketing materials for a particular audience, we present a novel model, Henry, trained to leverage real-world knowledge of LLMs and visual knowledge to predict the memorability. We test Henry on all the prominent memorability datasets in literature (both images and videos) and achieve state-of-the-art performance across all of them. Henry shows strong generalization showing better results in 0-shot on unseen datasets. Next, we propose the task of memorable ad generation and release a large-scale ad dataset, UltraLAMBDA, consisting of 4 million ads with their Henry-assigned memorability scores. We show that aligning Henry to generate memorable content improves memorability scores by more than 25%.

Synthetic data generation, a cornerstone of Generative Artificial Intelligence (GAI), signifies a paradigm shift in data science by addressing data scarcity and privacy while enabling unprecedented performance. As synthetic data gains prominence, questions arise concerning the accuracy of statistical methods when applied to synthetic data compared to raw data. This article introduces the Synthetic Data Generation for Analytics (Syn) framework. This framework employs statistical methods on high-fidelity synthetic data generated by advanced models such as tabular diffusion and Generative Pre-trained Transformer (GPT) models. These models, trained on raw data, are further enhanced with insights from pertinent studies through knowledge transfer. A significant discovery within this framework is the generational effect: the error of a statistical method on synthetic data initially diminishes with additional synthetic data but may eventually increase or plateau. This phenomenon, rooted in the complexities of replicating raw data distributions, highlights a "reflection point" - an optimal threshold in the size of synthetic data determined by specific error metrics. Through three case studies - sentiment analysis of texts, predictive modeling of structured data, and inference in tabular data - we demonstrate the effectiveness of this framework over traditional ones. We underline its potential to amplify various statistical methods, including gradient boosting for prediction and hypothesis testing, thereby underscoring the transformative potential of synthetic data generation in data science.

No one knows whether artificial intelligence will be a boon or curse in the far future. But right now, there's almost universal discomfort and contempt for one habit of these chatbots and agents: hallucinations, those made-up facts that appear in the outputs of large language models like ChatGPT. In the middle of what seems like a carefully constructed answer, the LLM will slip in something that seems reasonable but is a total fabrication. Your typical chatbot can make disgraced ex-congressman George Santos look like Abe Lincoln. Since it looks inevitable that chatbots will one day generate the vast majority of all prose ever written, all the AI companies are obsessed with minimizing and eliminating hallucinations, or at least convincing the world the problem is in hand.

OpenAI's management chaos in November could have long-lasting effects on its business as some of the company's customers say it was a wake-up call about the risks of being too reliant on one company's tech. Executives at companies that use OpenAI's software say they are increasingly looking to also use others' technology to protect themselves from the risks of problems at any one. OpenAI's competitors are using the opportunity to sign up wary customers.

Cognitive dynamics are pivotal to advance human understanding of the world. Recent advancements in large language models (LLMs) reveal their potential for cognitive simulation. However, these LLM-based cognitive studies primarily focus on static modeling, overlooking the dynamic nature of cognition. To bridge this gap, we propose the concept of the cognitive dynamics of LLMs and present a corresponding task with the inspiration of longitudinal studies. Towards the task, we develop CogBench, a novel benchmark to assess the cognitive dynamics of LLMs and validate it through participant surveys. We also design two evaluation metrics for CogBench, including Authenticity and Rationality. Recognizing the inherent static nature of LLMs, we introduce CogGPT for the task, which features an innovative iterative cognitive mechanism aimed at enhancing lifelong cognitive dynamics. Empirical results demonstrate the superiority of CogGPT over existing methods, particularly in its ability to facilitate role-specific cognitive dynamics under continuous information flows.

Multimodal information extraction (MIE) gains significant attention as the popularity of multimedia content increases. However, current MIE methods often resort to using task-specific model structures, which results in limited generalizability across tasks and underutilizes shared knowledge across MIE tasks. To address these issues, we propose UMIE, a unified multimodal information extractor to unify three MIE tasks as a generation problem using instruction tuning, being able to effectively extract both textual and visual mentions. Extensive experiments show that our single UMIE outperforms various state-of-the-art (SoTA) methods across six MIE datasets on three tasks. Furthermore, in-depth analysis demonstrates UMIE's strong generalization in the zero-shot setting, robustness to instruction variants, and interpretability. Our research serves as an initial step towards a unified MIE model and initiates the exploration into both instruction tuning and large language models within the MIE domain. Our code, data, and model are available at https://github.com/ZUCC-AI/UMIE