Agam Shah

Raj Sanjay Shah, Kunal Chawla, Dheeraj Eidnani et al. · gatech

Pre-trained language models have shown impressive performance on a variety of tasks and domains. Previous research on financial language models usually employs a generic training scheme to train standard model architectures, without completely leveraging the richness of the financial data. We propose a novel domain specific Financial LANGuage model (FLANG) which uses financial keywords and phrases for better masking, together with span boundary objective and in-filing objective. Additionally, the evaluation benchmarks in the field have been limited. To this end, we contribute the Financial Language Understanding Evaluation (FLUE), an open-source comprehensive suite of benchmarks for the financial domain. These include new benchmarks across 5 NLP tasks in financial domain as well as common benchmarks used in the previous research. Experiments on these benchmarks suggest that our model outperforms those in prior literature on a variety of NLP tasks. Our models, code and benchmark data are publicly available on Github and Huggingface.

Agam Shah, Abhinav Gullapalli, Ruchit Vithani et al. · gatech

Over the last two decades, the development of the CoNLL-2003 named entity recognition (NER) dataset has helped enhance the capabilities of deep learning and natural language processing (NLP). The finance domain, characterized by its unique semantic and lexical variations for the same entities, presents specific challenges to the NER task; thus, a domain-specific customized dataset is crucial for advancing research in this field. In our work, we develop the first high-quality English Financial NER Open Research Dataset (FiNER-ORD). We benchmark multiple pre-trained language models (PLMs) and large-language models (LLMs) on FiNER-ORD. We believe our proposed FiNER-ORD dataset will open future opportunities to use FiNER-ORD as a benchmark for financial domain-specific NER and NLP tasks. Our dataset, models, and code are publicly available on GitHub and Hugging Face under CC BY-NC 4.0 license.

Emmanuel Alanis, Sudheer Chava, Agam Shah · gatech

Using a comprehensive sample of 2,585 bankruptcies from 1990 to 2019, we benchmark the performance of various machine learning models in predicting financial distress of publicly traded U.S. firms. We find that gradient boosted trees outperform other models in one-year-ahead forecasts. Variable permutation tests show that excess stock returns, idiosyncratic risk, and relative size are the more important variables for predictions. Textual features derived from corporate filings do not improve performance materially. In a credit competition model that accounts for the asymmetric cost of default misclassification, the survival random forest is able to capture large dollar profits.

Michael Galarnyk, Rutwik Routu, Vidhyakshaya Kannan et al. · gatech

The ARR Responsible NLP Research checklist website states that the "checklist is designed to encourage best practices for responsible research, addressing issues of research ethics, societal impact and reproducibility." Answering the questions is an opportunity for authors to reflect on their work and make sure any shared scientific assets follow best practices. Ideally, considering a checklist before submission can favorably impact the writing of a research paper. However, previous research has shown that self-reported checklist responses don't always accurately represent papers. In this work, we introduce ConfReady, a retrieval-augmented generation (RAG) application that can be used to empower authors to reflect on their work and assist authors with conference checklists. To evaluate checklist assistants, we curate a dataset of 1,975 ACL checklist responses, analyze problems in human answers, and benchmark RAG and Large Language Model (LM) based systems on an evaluation subset. Our code is released under the AGPL-3.0 license on GitHub, with documentation covering the user interface and PyPI package.

Sebastian Jaskowski, Sahasra Chava, Agam Shah · gatech

The BERTScore metric is commonly used to evaluate automatic text simplification systems. However, current implementations of the metric fail to provide complete visibility into all information the metric can produce. Notably, the specific token matchings can be incredibly useful in generating clause-level insight into the quality of simplified text. We address this by introducing BERTScoreVisualizer, a web application that goes beyond reporting precision, recall, and F1 score and provides a visualization of the matching between tokens. We believe that our software can help improve the analysis of text simplification systems by specifically showing where generated, simplified text deviates from reference text. We host our code and demo on GitHub.

Nikita Tatarinov, Vidhyakshaya Kannan, Haricharana Srinivasa et al. · gatech

The increasing context length of modern language models has created a need for evaluating their ability to retrieve and process information across extensive documents. While existing benchmarks test long-context capabilities, they often lack a structured way to systematically vary question complexity. We introduce KG-QAGen (Knowledge-Graph-based Question-Answer Generation), a framework that (1) extracts QA pairs at multiple complexity levels (2) by leveraging structured representations of financial agreements (3) along three key dimensions -- multi-hop retrieval, set operations, and answer plurality -- enabling fine-grained assessment of model performance across controlled difficulty levels. Using this framework, we construct a dataset of 20,139 QA pairs (the largest number among the long-context benchmarks) and open-source a part of it. We evaluate 13 proprietary and open-source LLMs and observe that even the best-performing models are struggling with set-based comparisons and multi-hop logical inference. Our analysis reveals systematic failure modes tied to semantic misinterpretation and inability to handle implicit relations.

Michael Galarnyk, Veer Kejriwal, Agam Shah et al. · gatech

Social media has amplified the reach of financial influencers known as "finfluencers," who share stock recommendations on platforms like YouTube. Understanding their influence requires analyzing multimodal signals like tone, delivery style, and facial expressions, which extend beyond text-based financial analysis. We introduce VideoConviction, a multimodal dataset with 6,000+ expert annotations, produced through 457 hours of human effort, to benchmark multimodal large language models (MLLMs) and text-based large language models (LLMs) in financial discourse. Our results show that while multimodal inputs improve stock ticker extraction (e.g., extracting Apple's ticker AAPL), both MLLMs and LLMs struggle to distinguish investment actions and conviction--the strength of belief conveyed through confident delivery and detailed reasoning--often misclassifying general commentary as definitive recommendations. While high-conviction recommendations perform better than low-conviction ones, they still underperform the popular S\&P 500 index fund. An inverse strategy--betting against finfluencer recommendations--outperforms the S\&P 500 by 6.8\% in annual returns but carries greater risk (Sharpe ratio of 0.41 vs. 0.65). Our benchmark enables a diverse evaluation of multimodal tasks, comparing model performance on both full video and segmented video inputs. This enables deeper advancements in multimodal financial research. Our code, dataset, and evaluation leaderboard are available under the CC BY-NC 4.0 license.

Agam Shah, Sudheer Chava

Recently large language models (LLMs) like ChatGPT have shown impressive performance on many natural language processing tasks with zero-shot. In this paper, we investigate the effectiveness of zero-shot LLMs in the financial domain. We compare the performance of ChatGPT along with some open-source generative LLMs in zero-shot mode with RoBERTa fine-tuned on annotated data. We address three inter-related research questions on data annotation, performance gaps, and the feasibility of employing generative models in the finance domain. Our findings demonstrate that ChatGPT performs well even without labeled data but fine-tuned models generally outperform it. Our research also highlights how annotating with generative models can be time-intensive. Our codebase is publicly available on GitHub under CC BY-NC 4.0 license.

Agam Shah, Arnav Hiray, Pratvi Shah et al. · gatech

In this paper, we investigate the influence of claims in analyst reports and earnings calls on financial market returns, considering them as significant quarterly events for publicly traded companies. To facilitate a comprehensive analysis, we construct a new financial dataset for the claim detection task in the financial domain. We benchmark various language models on this dataset and propose a novel weak-supervision model that incorporates the knowledge of subject matter experts (SMEs) in the aggregation function, outperforming existing approaches. We also demonstrate the practical utility of our proposed model by constructing a novel measure of optimism. Here, we observe the dependence of earnings surprise and return on our optimism measure. Our dataset, models, and code are publicly (under CC BY 4.0 license) available on GitHub.

Nikita Tatarinov, Siddhant Sukhani, Agam Shah et al. · gatech

Recent advances in language modeling have led to a growing number of papers related to finance in top-tier Natural Language Processing (NLP) venues. To systematically examine this trend, we review 374 NLP research papers published between 2017 and 2024 across 38 conferences and workshops, with a focused analysis of 221 papers that directly address finance-related tasks. We evaluate these papers across 11 quantitative and qualitative dimensions, and our study identifies the following opportunities for NLP researchers: (i) expanding the scope of forecasting tasks; (ii) enriching evaluation with financial metrics; (iii) leveraging multilingual and crisis-period datasets; and (iv) balancing PLMs with efficient or interpretable alternatives. We identify actionable directions supported by dataset and tool recommendations, with implications for both the academia and industry communities.

Huzaifa Pardawala, Siddhant Sukhani, Agam Shah et al. · gatech

Fact-checking is extensively studied in the context of misinformation and disinformation, addressing objective inaccuracies. However, a softer form of misinformation involves responses that are factually correct but lack certain features such as clarity and relevance. This challenge is prevalent in formal Question-Answer (QA) settings such as press conferences in finance, politics, sports, and other domains, where subjective answers can obscure transparency. Despite this, there is a lack of manually annotated datasets for subjective features across multiple dimensions. To address this gap, we introduce SubjECTive-QA, a human annotated dataset on Earnings Call Transcripts' (ECTs) QA sessions as the answers given by company representatives are often open to subjective interpretations and scrutiny. The dataset includes 49,446 annotations for long-form QA pairs across six features: Assertive, Cautious, Optimistic, Specific, Clear, and Relevant. These features are carefully selected to encompass the key attributes that reflect the tone of the answers provided during QA sessions across different domain. Our findings are that the best-performing Pre-trained Language Model (PLM), RoBERTa-base, has similar weighted F1 scores to Llama-3-70b-Chat on features with lower subjectivity, such as Relevant and Clear, with a mean difference of 2.17% in their weighted F1 scores. The models perform significantly better on features with higher subjectivity, such as Specific and Assertive, with a mean difference of 10.01% in their weighted F1 scores. Furthermore, testing SubjECTive-QA's generalizability using QAs from White House Press Briefings and Gaggles yields an average weighted F1 score of 65.97% using our best models for each feature, demonstrating broader applicability beyond the financial domain. SubjECTive-QA is publicly available under the CC BY 4.0 license

Agam Shah, Liqin Ye, Sebastian Jaskowski et al. · gatech

Large Language Models (LLMs) are frequently utilized as sources of knowledge for question-answering. While it is known that LLMs may lack access to real-time data or newer data produced after the model's cutoff date, it is less clear how their knowledge spans across historical information. In this study, we assess the breadth of LLMs' knowledge using financial data of U.S. publicly traded companies by evaluating more than 197k questions and comparing model responses to factual data. We further explore the impact of company characteristics, such as size, retail investment, institutional attention, and readability of financial filings, on the accuracy of knowledge represented in LLMs. Our results reveal that LLMs are less informed about past financial performance, but they display a stronger awareness of larger companies and more recent information. Interestingly, at the same time, our analysis also reveals that LLMs are more likely to hallucinate for larger companies, especially for data from more recent years. The code, prompts, and model outputs are available on GitHub.

Michael Galarnyk, Agam Shah, Dipanwita Guhathakurta et al. · gatech

This paper discusses and contains offensive content. Language models (LMs) are used in decision-making systems and as interactive assistants. However, how well do these models making judgements align with the diversity of human values, particularly regarding social and moral norms? In this work, we investigate how inclusively LMs perceive norms across demographic groups (e.g., gender, age, and income). We prompt 11 LMs on rules-of-thumb (RoTs) and compare their outputs with the existing responses of 100 human annotators. We introduce the Absolute Distance Alignment Metric (ADA-Met) to quantify alignment on ordinal questions. We find notable disparities in LM responses, with younger, higher-income groups showing closer alignment, raising concerns about the representation of marginalized perspectives. Our findings highlight the importance of further efforts to make LMs more inclusive of diverse human values. The code and prompts are available on GitHub under the CC BY-NC 4.0 license.

Agam Shah, Siddhant Sukhani, Huzaifa Pardawala et al. · gatech

Central banks around the world play a crucial role in maintaining economic stability. Deciphering policy implications in their communications is essential, especially as misinterpretations can disproportionately impact vulnerable populations. To address this, we introduce the World Central Banks (WCB) dataset, the most comprehensive monetary policy corpus to date, comprising over 380k sentences from 25 central banks across diverse geographic regions, spanning 28 years of historical data. After uniformly sampling 1k sentences per bank (25k total) across all available years, we annotate and review each sentence using dual annotators, disagreement resolutions, and secondary expert reviews. We define three tasks: Stance Detection, Temporal Classification, and Uncertainty Estimation, with each sentence annotated for all three. We benchmark seven Pretrained Language Models (PLMs) and nine Large Language Models (LLMs) (Zero-Shot, Few-Shot, and with annotation guide) on these tasks, running 15,075 benchmarking experiments. We find that a model trained on aggregated data across banks significantly surpasses a model trained on an individual bank's data, confirming the principle "the whole is greater than the sum of its parts." Additionally, rigorous human evaluations, error analyses, and predictive tasks validate our framework's economic utility. Our artifacts are accessible through the HuggingFace and GitHub under the CC-BY-NC-SA 4.0 license.

Divya Patel, Vansh Parikh, Om Patel et al.

In this work, we apply topic modeling using Non-Negative Matrix Factorization (NMF) on the COVID-19 Open Research Dataset (CORD-19) to uncover the underlying thematic structure and its evolution within the extensive body of COVID-19 research literature. NMF factorizes the document-term matrix into two non-negative matrices, effectively representing the topics and their distribution across the documents. This helps us see how strongly documents relate to topics and how topics relate to words. We describe the complete methodology which involves a series of rigorous pre-processing steps to standardize the available text data while preserving the context of phrases, and subsequently feature extraction using the term frequency-inverse document frequency (tf-idf), which assigns weights to words based on their frequency and rarity in the dataset. To ensure the robustness of our topic model, we conduct a stability analysis. This process assesses the stability scores of the NMF topic model for different numbers of topics, enabling us to select the optimal number of topics for our analysis. Through our analysis, we track the evolution of topics over time within the CORD-19 dataset. Our findings contribute to the understanding of the knowledge structure of the COVID-19 research landscape, providing a valuable resource for future research in this field.

Mingxiao Song, Yunsong Liu, Agam Shah et al.

The Non-Fungible-Token (NFT) market has experienced explosive growth in recent years. According to DappRadar, the total transaction volume on OpenSea, the largest NFT marketplace, reached 34.7 billion dollars in February 2023. However, the NFT market is mostly unregulated and there are significant concerns about money laundering, fraud and wash trading. The lack of industry-wide regulations, and the fact that amateur traders and retail investors comprise a significant fraction of the NFT market, make this market particularly vulnerable to fraudulent activities. Therefore it is essential to investigate and highlight the relevant risks involved in NFT trading. In this paper, we attempted to uncover common fraudulent behaviors such as wash trading that could mislead other traders. Using market data, we designed quantitative features from the network, monetary, and temporal perspectives that were fed into K-means clustering unsupervised learning algorithm to sort traders into groups. Lastly, we discussed the clustering results' significance and how regulations can reduce undesired behaviors. Our work can potentially help regulators narrow down their search space for bad actors in the market as well as provide insights for amateur traders to protect themselves from unforeseen frauds.

Agam Shah, Suvan Paturi, Sudheer Chava

Monetary policy pronouncements by Federal Open Market Committee (FOMC) are a major driver of financial market returns. We construct the largest tokenized and annotated dataset of FOMC speeches, meeting minutes, and press conference transcripts in order to understand how monetary policy influences financial markets. In this study, we develop a novel task of hawkish-dovish classification and benchmark various pre-trained language models on the proposed dataset. Using the best-performing model (RoBERTa-large), we construct a measure of monetary policy stance for the FOMC document release days. To evaluate the constructed measure, we study its impact on the treasury market, stock market, and macroeconomic indicators. Our dataset, models, and code are publicly available on Huggingface and GitHub under CC BY-NC 4.0 license.

Mahipal Jadeja, Neelanshi Varia, Agam Shah

Deep reinforcement learning is revolutionizing the artificial intelligence field. Currently, it serves as a good starting point for constructing intelligent autonomous systems which offer a better knowledge of the visual world. It is possible to scale deep reinforcement learning with the use of deep learning and do amazing tasks such as use of pixels in playing video games. In this paper, key concepts of deep reinforcement learning including reward function, differences between reinforcement learning and supervised learning and models for implementation of reinforcement are discussed. Key challenges related to the implementation of reinforcement learning in conversational AI domain are identified as well as discussed in detail. Various conversational models which are based on deep reinforcement learning (as well as deep learning) are also discussed. In summary, this paper discusses key aspects of deep reinforcement learning which are crucial for designing an efficient conversational AI.