arXiv subjects

Xiaomo Liu

Publications and source records attributed to Xiaomo Liu.

27 records · Page 2Linked to original sources

arXiv2023

Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams

Large Language Models (LLMs) have demonstrated remarkable performance on a wide range of Natural Language Processing (NLP) tasks, often matching or even beating state-of-the-art task-specific models. This study aims at assessing the financial reasoning capabilities of LLMs. We leverage mock exam questions of the Chartered Financial Analyst (CFA) Program to conduct a comprehensive evaluation of ChatGPT and GPT-4 in financial analysis, considering Zero-Shot (ZS), Chain-of-Thought (CoT), and Few-Shot (FS) scenarios. We present an in-depth analysis of the models' performance and limitations, and estimate whether they would have a chance at passing the CFA exams. Finally, we outline insights into potential strategies and improvements to enhance the applicability of LLMs in finance. In this perspective, we hope this work paves the way for future studies to continue enhancing LLMs for financial reasoning through rigorous evaluation.

cs.CL↗

arXiv2023

Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks

The most recent large language models(LLMs) such as ChatGPT and GPT-4 have shown exceptional capabilities of generalist models, achieving state-of-the-art performance on a wide range of NLP tasks with little or no adaptation. How effective are such models in the financial domain? Understanding this basic question would have a significant impact on many downstream financial analytical tasks. In this paper, we conduct an empirical study and provide experimental evidences of their performance on a wide variety of financial text analytical problems, using eight benchmark datasets from five categories of tasks. We report both the strengths and limitations of the current models by comparing them to the state-of-the-art fine-tuned approaches and the recently released domain-specific pretrained models. We hope our study can help understand the capability of the existing models in the financial domain and facilitate further improvements.

cs.CL↗

arXiv2023

Unsupervised Domain Adaptation using Lexical Transformations and Label Injection for Twitter Data

Domain adaptation is an important and widely studied problem in natural language processing. A large body of literature tries to solve this problem by adapting models trained on the source domain to the target domain. In this paper, we instead solve this problem from a dataset perspective. We modify the source domain dataset with simple lexical transformations to reduce the domain shift between the source dataset distribution and the target dataset distribution. We find that models trained on the transformed source domain dataset performs significantly better than zero-shot models. Using our proposed transformations to convert standard English to tweets, we reach an unsupervised part-of-speech (POS) tagging accuracy of 92.14% (from 81.54% zero shot accuracy), which is only slightly below the supervised performance of 94.45%. We also use our proposed transformations to synthetically generate tweets and augment the Twitter dataset to achieve state-of-the-art performance for POS tagging.

cs.CL↗

arXiv2022

AIR-JPMC@SMM4H'22: Classifying Self-Reported Intimate Partner Violence in Tweets with Multiple BERT-based Models

This paper presents our submission for the SMM4H 2022-Shared Task on the classification of self-reported intimate partner violence on Twitter (in English). The goal of this task was to accurately determine if the contents of a given tweet demonstrated someone reporting their own experience with intimate partner violence. The submitted system is an ensemble of five RoBERTa models each weighted by their respective F1-scores on the validation data-set. This system performed 13% better than the baseline and was the best performing system overall for this shared task.

cs.CL↗

arXiv2020

Towards Earnings Call and Stock Price Movement

Earnings calls are hosted by management of public companies to discuss the company's financial performance with analysts and investors. Information disclosed during an earnings call is an essential source of data for analysts and investors to make investment decisions. Thus, we leverage earnings call transcripts to predict future stock price dynamics. We propose to model the language in transcripts using a deep learning framework, where an attention mechanism is applied to encode the text data into vectors for the discriminative network classifier to predict stock price movements. Our empirical experiments show that the proposed model is superior to the traditional machine learning baselines and earnings call information can boost the stock price prediction performance.

q-fin.ST↗

arXiv2019

Empirical Study on Detecting Controversy in Social Media

Companies and financial investors are paying increasing attention to social consciousness in developing their corporate strategies and making investment decisions to support a sustainable economy for the future. Public discussion on incidents and events -- controversies -- of companies can provide valuable insights on how well the company operates with regards to social consciousness and indicate the company's overall operational capability. However, there are challenges in evaluating the degree of a company's social consciousness and environmental sustainability due to the lack of systematic data. We introduce a system that utilizes Twitter data to detect and monitor controversial events and show their impact on market volatility. In our study, controversial events are identified from clustered tweets that share the same 5W terms and sentiment polarities of these clusters. Credible news links inside the event tweets are used to validate the truth of the event. A case study on the Starbucks Philadelphia arrests shows that this method can provide the desired functionality.

cs.SI↗

arXiv2017

Reuters Tracer: Toward Automated News Production Using Large Scale Social Media Data

To deal with the sheer volume of information and gain competitive advantage, the news industry has started to explore and invest in news automation. In this paper, we present Reuters Tracer, a system that automates end-to-end news production using Twitter data. It is capable of detecting, classifying, annotating, and disseminating news in real time for Reuters journalists without manual intervention. In contrast to other similar systems, Tracer is topic and domain agnostic. It has a bottom-up approach to news detection, and does not rely on a predefined set of sources or subjects. Instead, it identifies emerging conversations from 12+ million tweets per day and selects those that are news-like. Then, it contextualizes each story by adding a summary and a topic to it, estimating its newsworthiness, veracity, novelty, and scope, and geotags it. Designing algorithms to generate news that meets the standards of Reuters journalists in accuracy and timeliness is quite challenging. But Tracer is able to achieve competitive precision, recall, timeliness, and veracity on news detection and delivery. In this paper, we reveal our key algorithm designs and evaluations that helped us achieve this goal, and lessons learned along the way.

cs.SI↗

arXiv2017

"Breaking" Disasters: Predicting and Characterizing the Global News Value of Natural and Man-made Disasters

Due to their often unexpected nature, natural and man-made disasters are difficult to monitor and detect for journalists and disaster management response teams. Journalists are increasingly relying on signals from social media to detect such stories in their early stage of development. Twitter, which features a vast network of local news outlets, is a major source of early signal for disaster detection. Journalists who work for global desks often follow these sources via Twitter's lists, but have to comb through thousands of small-scale or low-impact stories to find events that may be globally relevant. These are events that have a large scope, high impact, or potential geo-political relevance. We propose a model for automatically identifying events from local news sources that may break on a global scale within the next 24 hours. The results are promising and can be used in a predictive setting to help journalists manage their sources more effectively, or in a descriptive manner to analyze media coverage of disasters. Through the feature evaluation process, we also address the question: "what makes a disaster event newsworthy on a global scale?" As part of our data collection process, we have created a list of local sources of disaster/accident news on Twitter, which we have made publicly available.

cs.SI↗

arXiv2017

Data Sets: Word Embeddings Learned from Tweets and General Data

A word embedding is a low-dimensional, dense and real- valued vector representation of a word. Word embeddings have been used in many NLP tasks. They are usually gener- ated from a large text corpus. The embedding of a word cap- tures both its syntactic and semantic aspects. Tweets are short, noisy and have unique lexical and semantic features that are different from other types of text. Therefore, it is necessary to have word embeddings learned specifically from tweets. In this paper, we present ten word embedding data sets. In addition to the data sets learned from just tweet data, we also built embedding sets from the general data and the combination of tweets with the general data. The general data consist of news articles, Wikipedia data and other web data. These ten embedding models were learned from about 400 million tweets and 7 billion words from the general text. In this paper, we also present two experiments demonstrating how to use the data sets in some NLP tasks, such as tweet sentiment analysis and tweet topic classification tasks.

cs.CL↗