In the realm of financial analytics, leveraging unstructured data, such as earnings conference calls (ECCs), to forecast stock performance is a critical challenge that has attracted both academics and investors. While previous studies have used deep learning-based models to obtain a general view of ECCs, they often fail to capture detailed, complex information. Our study introduces a novel framework: \textbf{ECC Analyzer}, combining Large Language Models (LLMs) and multi-modal techniques to extract richer, more predictive insights. The model begins by summarizing the transcript's structure and analyzing the speakers' mode and confidence level by detecting variations in tone and pitch for audio. This analysis helps investors form an overview perception of the ECCs. Moreover, this model uses the Retrieval-Augmented Generation (RAG) based methods to meticulously extract the focuses that have a significant impact on stock performance from an expert's perspective, providing a more targeted analysis. The model goes a step further by enriching these extracted focuses with additional layers of analysis, such as sentiment and audio segment features. By integrating these insights, the ECC Analyzer performs multi-task predictions of stock performance, including volatility, value-at-risk (VaR), and return for different intervals. The results show that our model outperforms traditional analytic benchmarks, confirming the effectiveness of using advanced LLM techniques in financial analytics.
The integration of Artificial Intelligence (AI) techniques, particularly large language models (LLMs), in finance has garnered increasing academic attention. Despite progress, existing studies predominantly focus on tasks like financial text summarization, question-answering (Q$\&$A), and stock movement prediction (binary classification), with a notable gap in the application of LLMs for financial risk prediction. Addressing this gap, in this paper, we introduce \textbf{RiskLabs}, a novel framework that leverages LLMs to analyze and predict financial risks. RiskLabs uniquely combines different types of financial data, including textual and vocal information from Earnings Conference Calls (ECCs), market-related time series data, and contextual news data surrounding ECC release dates. Our approach involves a multi-stage process: initially extracting and analyzing ECC data using LLMs, followed by gathering and processing time-series data before the ECC dates to model and understand risk over different timeframes. Using multimodal fusion techniques, RiskLabs amalgamates these varied data features for comprehensive multi-task financial risk prediction. Empirical experiment results demonstrate RiskLab's effectiveness in forecasting both volatility and variance in financial markets. Through comparative experiments, we demonstrate how different data sources contribute to financial risk assessment and discuss the critical role of LLMs in this context. Our findings not only contribute to the AI in finance application but also open new avenues for applying LLMs in financial risk assessment.
Scientific facts are often spun in the popular press with the intent to influence public opinion and action, as was evidenced during the COVID-19 pandemic. Automatic detection of misinformation in the scientific domain is challenging because of the distinct styles of writing in these two media types and is still in its nascence. Most research on the validity of scientific reporting treats this problem as a claim verification challenge. In doing so, significant expert human effort is required to generate appropriate claims. Our solution bypasses this step and addresses a more real-world scenario where such explicit, labeled claims may not be available. The central research question of this paper is whether it is possible to use large language models (LLMs) to detect misinformation in scientific reporting. To this end, we first present a new labeled dataset SciNews, containing 2.4k scientific news stories drawn from trusted and untrustworthy sources, paired with related abstracts from the CORD-19 database. Our dataset includes both human-written and LLM-generated news articles, making it more comprehensive in terms of capturing the growing trend of using LLMs to generate popular press articles. Then, we identify dimensions of scientific validity in science news articles and explore how this can be integrated into the automated detection of scientific misinformation. We propose several baseline architectures using LLMs to automatically detect false representations of scientific findings in the popular press. For each of these architectures, we use several prompt engineering strategies including zero-shot, few-shot, and chain-of-thought prompting. We also test these architectures and prompting strategies on GPT-3.5, GPT-4, and Llama2-7B, Llama2-13B.