Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics. However, their capability to inference based on user-specified structured data and knowledge in corpus-rare concepts like causal decision-making is still limited. In this work, we explore the possibility of fine-tuning an open-sourced LLM into LLM4Causal, which can identify the causal task, execute a corresponding function, and interpret its numerical results based on users' queries and the provided dataset. Meanwhile, we propose a data generation process for more controllable GPT prompting and present two instruction-tuning datasets: (1) Causal-Retrieval-Bench for causal problem identification and input parameter extraction for causal function calling and (2) Causal-Interpret-Bench for in-context causal interpretation. With three case studies, we showed that LLM4Causal can deliver end-to-end solutions for causal problems and provide easy-to-understand answers. Numerical studies also reveal that it has a remarkable ability to identify the correct causal task given a query.

Dark patterns are deceptive user interface designs for online services that make users behave in unintended ways. Dark patterns, such as privacy invasion, financial loss, and emotional distress, can harm users. These issues have been the subject of considerable debate in recent years. In this paper, we study interpretable dark pattern auto-detection, that is, why a particular user interface is detected as having dark patterns. First, we trained a model using transformer-based pre-trained language models, BERT, on a text-based dataset for the automatic detection of dark patterns in e-commerce. Then, we applied post-hoc explanation techniques, including local interpretable model agnostic explanation (LIME) and Shapley additive explanations (SHAP), to the trained model, which revealed which terms influence each prediction as a dark pattern. In addition, we extracted and analyzed terms that affected the dark patterns. Our findings may prevent users from being manipulated by dark patterns, and aid in the construction of more equitable internet services. Our code is available at https://github.com/yamanalab/why-darkpattern.

This study investigates the complexity of regulatory affairs in the medical device industry, a critical factor influencing market access and patient care. Through qualitative research, we sought expert insights to understand the factors contributing to this complexity. The study involved semi-structured interviews with 28 professionals from medical device companies, specializing in various aspects of regulatory affairs. These interviews were analyzed using open coding and Natural Language Processing (NLP) techniques. The findings reveal key sources of complexity within the regulatory landscape, divided into five domains: (A) Regulatory language complexity, (B) Intricacies within the regulatory process, (C) Global-level complexities, (D) Database-related considerations, and (E) Product-level issues. The participants highlighted the need for strategies to streamline regulatory compliance, enhance interactions between regulatory bodies and industry players, and develop adaptable frameworks for rapid technological advancements. Emphasizing interdisciplinary collaboration and increased transparency, the study concludes that these elements are vital for establishing coherent and effective regulatory procedures in the medical device sector.

This paper examines the efficacy of utilizing large language models (LLMs) to detect public threats posted online. Amid rising concerns over the spread of threatening rhetoric and advance notices of violence, automated content analysis techniques may aid in early identification and moderation. Custom data collection tools were developed to amass post titles from a popular Korean online community, comprising 500 non-threat examples and 20 threats. Various LLMs (GPT-3.5, GPT-4, PaLM) were prompted to classify individual posts as either "threat" or "safe." Statistical analysis found all models demonstrated strong accuracy, passing chi-square goodness of fit tests for both threat and non-threat identification. GPT-4 performed best overall with 97.9% non-threat and 100% threat accuracy. Affordability analysis also showed PaLM API pricing as highly cost-efficient. The findings indicate LLMs can effectively augment human content moderation at scale to help mitigate emerging online risks. However, biases, transparency, and ethical oversight remain vital considerations before real-world implementation.

Large Language Models (LLMs) have proven powerful, but the risk of privacy leakage remains a significant concern. Traditional privacy-preserving methods, such as Differential Privacy and Homomorphic Encryption, are inadequate for black-box API-only settings, demanding either model transparency or heavy computational resources. We propose Prompt2Forget (P2F), the first framework designed to tackle the LLM local privacy challenge by teaching LLM to forget. The method involves decomposing full questions into smaller segments, generating fabricated answers, and obfuscating the model's memory of the original input. A benchmark dataset was crafted with questions containing privacy-sensitive information from diverse fields. P2F achieves zero-shot generalization, allowing adaptability across a wide range of use cases without manual adjustments. Experimental results indicate P2F's robust capability to obfuscate LLM's memory, attaining a forgetfulness score of around 90\% without any utility loss. This represents an enhancement of up to 63\% when contrasted with the naive direct instruction technique, highlighting P2F's efficacy in mitigating memory retention of sensitive information within LLMs. Our findings establish the first benchmark in the novel field of the LLM forgetting task, representing a meaningful advancement in privacy preservation in the emerging LLM domain.

Synthetic data has made tremendous strides in various commercial settings including finance, healthcare, and virtual reality. We present a broad overview of prototypical applications of synthetic data in the financial sector and in particular provide richer details for a few select ones. These cover a wide variety of data modalities including tabular, time-series, event-series, and unstructured arising from both markets and retail financial applications. Since finance is a highly regulated industry, synthetic data is a potential approach for dealing with issues related to privacy, fairness, and explainability. Various metrics are utilized in evaluating the quality and effectiveness of our approaches in these applications. We conclude with open directions in synthetic data in the context of the financial domain.

Large Language Models (LLMs) have revolutionized various domains with extensive knowledge and creative capabilities. However, a critical issue with LLMs is their tendency to produce outputs that diverge from factual reality. This phenomenon is particularly concerning in sensitive applications such as medical consultation and legal advice, where accuracy is paramount. In this paper, we introduce the LLM factoscope, a novel Siamese network-based model that leverages the inner states of LLMs for factual detection. Our investigation reveals distinguishable patterns in LLMs' inner states when generating factual versus non-factual content. We demonstrate the LLM factoscope's effectiveness across various architectures, achieving over 96% accuracy in factual detection. Our work opens a new avenue for utilizing LLMs' inner states for factual detection and encourages further exploration into LLMs' inner workings for enhanced reliability and transparency.

The Large Language Model Bias Index (LLMBI) is a pioneering approach designed to quantify and address biases inherent in large language models (LLMs), such as GPT-4. We recognise the increasing prevalence and impact of LLMs across diverse sectors. This research introduces a novel metric, LLMBI, to systematically measure and mitigate biases potentially skewing model responses. We formulated LLMBI using a composite scoring system incorporating multiple dimensions of bias, including but not limited to age, gender, and racial biases. To operationalise this metric, we engaged in a multi-step process involving collecting and annotating LLM responses, applying sophisticated Natural Language Processing (NLP) techniques for bias detection, and computing the LLMBI score through a specially crafted mathematical formula. The formula integrates weighted averages of various bias dimensions, a penalty for dataset diversity deficiencies, and a correction for sentiment biases. Our empirical analysis, conducted using responses from OpenAI's API, employs advanced sentiment analysis as a representative method for bias detection. The research reveals LLMs, whilst demonstrating impressive capabilities in text generation, exhibit varying degrees of bias across different dimensions. LLMBI provides a quantifiable measure to compare biases across models and over time, offering a vital tool for systems engineers, researchers and regulators in enhancing the fairness and reliability of LLMs. It highlights the potential of LLMs in mimicking unbiased human-like responses. Additionally, it underscores the necessity of continuously monitoring and recalibrating such models to align with evolving societal norms and ethical standards.

Knowledge graph construction (KGC) is a multifaceted undertaking involving the extraction of entities, relations, and events. Traditionally, large language models (LLMs) have been viewed as solitary task-solving agents in this complex landscape. However, this paper challenges this paradigm by introducing a novel framework, CooperKGC. Departing from the conventional approach, CooperKGC establishes a collaborative processing network, assembling a KGC collaboration team capable of concurrently addressing entity, relation, and event extraction tasks. Our experiments unequivocally demonstrate that fostering collaboration and information interaction among diverse agents within CooperKGC yields superior results compared to individual cognitive processes operating in isolation. Importantly, our findings reveal that the collaboration facilitated by CooperKGC enhances knowledge selection, correction, and aggregation capabilities across multiple rounds of interactions.

At the latest congressional hearing on A.I., the hype was high. "Since the release of ChatGPT just over a year ago, it's become clear A.I. could soon disrupt nearly every facet of our economy," said Rep. Nancy Mace, chair of the U.S. congressional Subcommittee on Cybersecurity, Information Technology, and Government Innovation. "The A.I. genie is out of the bottle and it can't be put back in." A.I. does seem like a genie: The technology is new and mysterious, we aren't sure exactly how it works, and we know it is very powerful. We are also afraid of it: In a poll conducted in the summer of 2023, over half of Americans said they were more concerned than excited about A.I.; there is widespread speculation about what effects the technology will have on our economy, our jobs (lolsob), our education system, our art; and tech leaders have warned that the technology puts the fate of humanity at risk.