FinanceBench benchmarks LLMs on financial QA, revealing limitations.
problem Evaluating LLMs' performance on financial question answering.
method Developed a comprehensive test suite (FinanceBench) with 10,231 questions, tested 16 models, and manually reviewed answers.
result Existing LLMs have significant limitations for financial QA, especially GPT-4-Turbo.
REALFIN benchmarks financial reasoning by removing implicit assumptions, revealing model weaknesses.
problem Models struggle when implicit assumptions are missing, leading to incorrect answers.
method Developed a bilingual benchmark that systematically removes essential premises from financial questions.
result General-purpose models over-commit, while finance-specialized models fail to identify missing premises.
KodeXv0.1 improves financial question answering over GPT-4.
problem Lack of specialized financial language models.
method Custom training on financial documents, RAG-aware 4bit LoRA tuning.
result KodeX-8Bv0.1 outperforms GPT-4 by up to 9.24% in financial tasks.
This study analyzes financial equity research reports to identify frequently asked questions and automates 80% of them.
problem Insufficient empirical analysis of questions answered in financial equity research reports.
method Analyzed 72 financial equity research reports, classifying sentences into 169 unique question archetypes. Used public corporate reports to classify questions' potential for automation.
result Approximately 80% of financial equity research reports can be automated, with 78.7% of questions automatable.
PyFi uses adversarial agents to train VLMs on financial image understanding.
problem Training VLMs to understand complex financial questions.
method PyFi-600K dataset and adversarial MCTS mechanism.
result Fine-tuned VLMs improve by 19.52% and 8.06% on financial question accuracy.
Paper introduces NumLLM for better financial text understanding with numeric variables.
problem Poor performance of existing financial large language models in numeric financial text.
method Constructed financial corpus, fine-tuned with LoRA modules, merged into foundation model.
result NumLLM achieves best performance on financial question-answering benchmark, especially with numeric questions.
Principles of financial product synthesis from a few basic financial products constitute an interesting research topic inspired by Islamic finance. We make an effort to answer general questions that should be answered before starting to investigate the main issues concerning this topic with the formalization of financi…
German FinBERT improves financial text analysis performance.
problem Capturing domain-specific nuances in financial text.
method German FinBERT is a pre-trained German language model trained on a large corpus of financial data.
result German FinBERT outperforms standard models on finance-specific tasks.
Paper introduces RiskEmbed, a finetuned model for financial risk management.
problem Improving retrieval accuracy in financial question-answering systems.
method Curated dataset and finetuned BERT model for financial domain.
result RiskEmbed significantly outperforms general-purpose and financial embedding models.
Expands robust profit opportunities to include distributional uncertainty.
problem Distributional uncertainty in financial markets.
method Formulates infinite dimensional primal problems, simplifies to finite dimensional dual problems using Wasserstein distance.
result Distributional uncertainty can enhance robustness of profit opportunities.
BloombergGPT is a large language model trained on financial data, outperforming existing models on financial tasks.
problem Lack of specialized large language models for finance.
method Trained on a 363 billion token dataset augmented with 345 billion tokens from general datasets, using a 50 billion parameter model.
result BloombergGPT outperforms existing models on financial tasks without sacrificing performance on general LLM benchmarks.
The paper explores arbitrage in financial markets under uncertainty using Wasserstein distance.
problem Investigating arbitrage in financial markets with distributional uncertainty.
method Using Wasserstein distance, the paper considers weak and strong forms of arbitrage conditions and introduces a relaxation called statistical arbitrage.
result The paper derives dual formulations of robust arbitrage conditions and conducts computational experiments to answer questions about ambiguity and statistical arbitrage.
This paper improves retrieval for LLMs in financial document Q&A.
problem Suboptimal text chunk retrieval by RAG causes inaccuracies in LLM responses.
method Sophisticated chunking techniques, query expansion, metadata annotations, re-ranking algorithms, and embedding fine-tuning.
result Enhanced retrieval quality improves LLM performance and reliability.
Study compares LSTM and Transformer models in financial time series prediction.
problem Comparing LSTM and Transformer models for financial time series prediction.
method Various LSTM-based and Transformer-based models compared on financial tasks; DLSTM and new Transformer architecture designed.
result Transformer-based models show limited advantage in absolute price sequence prediction, while LSTM-based models perform better on difference sequences.
HybridRAG combines KGs and vector retrieval for financial document Q&A.
problem Challenges in extracting and interpreting financial text data.
method Integrates Knowledge Graphs and Vector Retrieval Augmented Generation.
result HybridRAG outperforms traditional methods in Q&A systems for financial documents.
FinTradeBench benchmarks LLMs for financial reasoning combining company fundamentals and market signals.
problem Challenges in evaluating financial reasoning models for LLMs.
method Developed a benchmark integrating company fundamentals and trading signals, using a calibration-then-scaling framework.
result Clear performance gap between LLMs, retrieval improves reasoning over textual fundamentals but not trading signals.
"What are the origins of risks?" and "How material are they?" -- these are the two most fundamental questions of any risk analysis. Quantitative Structuring -- a technology for building financial products -- provides economically meaningful answers for both of these questions. It does so by considering risk as an inves…
We develop a simple test for deviations from power law tails, which is based on the asymptotic properties of the empirical distribution function. We use this test to answer the question whether great natural disasters, financial crashes or electricity price spikes should be classified as dragon kings or 'only' as black…
Researchers have used from 30 days to several years of daily returns as source data for clustering financial time series based on their correlations. This paper sets up a statistical framework to study the validity of such practices. We first show that clustering correlated random variables from their observed values i…
Benchmark evaluates AI-generated financial QA hallucinations, highlighting system vulnerabilities.
problem Ensuring factual accuracy of AI-generated financial QA outputs.
method Developed a benchmark dataset and evaluated six detection methods under clean and noisy conditions.
result LLM-based judges and embedding methods perform best, but degrade under noisy conditions.
LLMs perform well in financial sentiment analysis without fine-tuning.
problem Challenges in financial terminology, emotions, and ambiguous expressions.
method In-context learning methods for financial document-sentiment pairs.
result LLMs can generalize in-context demonstrations to new financial documents.
We study how to leverage off-the-shelf visual and linguistic data to cope with out-of-vocabulary answers in visual question answering task. Existing large-scale visual datasets with annotations such as image class labels, bounding boxes and region descriptions are good sources for learning rich and diverse visual conce…
Paper analyzes biases in video QA datasets, showing models can answer 37-48% questions correctly without multimodal context.
problem Question answering biases in video QA datasets can lead to model overfitting and poor generalization.
method Analyzed popular video question answering datasets, conducted ablation studies on biases from annotators and question types.
result Pretrained language models can answer 37-48% questions correctly without multimodal context, far exceeding random guess baseline.
James's octonionic Stiefel spaces questions answered partially.
problem Two fundamental questions about octonionic Stiefel spaces.
method Partial answers to James's questions about octonionic Stiefel spaces.
result Partial answers to James's questions about octonionic Stiefel spaces.
Community-based Question Answering (CQA) sites play an important role in addressing health information needs. However, a significant number of posted questions remain unanswered. Automatically answering the posted questions can provide a useful source of information for online health communities. In this study, we deve…
MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory an…
Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unknown, and existing systems are not good at distinguishing distractor sentences, which look related but…
Visual question answering is a recently proposed artificial intelligence task that requires a deep understanding of both images and texts. In deep learning, images are typically modeled through convolutional neural networks, and texts are typically modeled through recurrent neural networks. While the requirement for mo…
Study examines cross-training neural networks for financial index prediction.
problem Predicting financial indexes from different markets using machine learning.
method Investigated various neural network architectures and trained them on one market index to predict another.
result Cross-training models on one market index improved prediction accuracy for another market index.
Study evaluates neural networks for corporate credit rating assessment.
problem Improving machine learning algorithms for credit assessment.
method Analysis of four neural network architectures (MLP, CNN, CNN2D, LSTM) on financial data from energy, financial, and healthcare sectors.
result LSTM architecture consistently outperforms others in predicting corporate credit ratings.
Paper answers Gromov's compactness question on noncompact manifolds.
problem Gromov's compactness question on positive scalar curvature metrics.
method Construct examples and prove vanishing of certain index theoretic invariants.
result Positive answer for a class of 1-tame manifolds.
We propose a heuristically modified FP-Tree for ontology learning from text. Unlike previous research, for concept extraction, we use a regular expression parser approach widely adopted in compiler construction, i.e., deterministic finite automata (DFA). Thus, the concepts are extracted from unstructured documents. For…
A novel method for visual question answering using scene graphs and reinforcement learning.
problem Answering free-form questions about images with deep linguistic and visual understanding.
method Context-driven, sequential reasoning based on scene graphs and reinforcement learning.
result Our method almost reaches human performance on the GQA dataset.
We introduce the task of acoustic question answering (AQA) in the area of acoustic reasoning. In this task an agent learns to answer questions on the basis of acoustic context. In order to promote research in this area, we propose a data generation paradigm adapted from CLEVR (Johnson et al. 2017). We generate acoustic…
LSTM network aids intent classification in QA.
problem Classifying intent in question-answering.
method Used LSTM architecture for intent classification.
result Effective and efficient intent classification achieved.
RiskLabs uses LLMs to predict financial risks from multimodal data.
problem Financial risk prediction using AI techniques.
method Integrates multimodal financial data (textual, vocal, time series, news) into LLMs for prediction.
result Empirical results show effectiveness in forecasting market volatility and variance.
This paper proposes a method to gain extra supervision via multi-task learning for multi-modal video question answering. Multi-modal video question answering is an important task that aims at the joint understanding of vision and language. However, establishing large scale dataset for multi-modal video question answeri…
Most work in machine reading focuses on question answering problems where the answer is directly expressed in the text to read. However, many real-world question answering problems require the reading of text not because it contains the literal answer, but because it contains a recipe to derive an answer together with …
We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation interfaces that require the subject to sharpen regions of a blurred image to answer a qu…
We introduce the new task of Acoustic Question Answering (AQA) to promote research in acoustic reasoning. The AQA task consists of analyzing an acoustic scene composed by a combination of elementary sounds and answering questions that relate the position and properties of these sounds. The kind of relational questions …
AI tested on 10 math questions from research.
problem Assessing AI's ability to solve research-level math problems.
method Shared 10 math questions not previously publicly available.
result Answers to questions are known to authors but encrypted.
Shai is a 10B model for asset management tasks, outperforming baselines.
problem Improving performance in asset management tasks.
method Continuous pre-training and fine-tuning on asset management-specific data.
result Shai outperforms baseline models in asset management tasks.
UniFinEval benchmarks financial models across text, images, and videos.
problem Challenges in evaluating financial multimodal models across text, images, and videos.
method Proposes UniFinEval, a unified multimodal benchmark for financial scenarios.
result Gemini-3-pro-preview achieves best performance but still lags behind experts.
We present SemEval-2019 Task 8 on Fact Checking in Community Question Answering Forums, which features two subtasks. Subtask A is about deciding whether a question asks for factual information vs. an opinion/advice vs. just socializing. Subtask B asks to predict whether an answer to a factual question is true, false or…
A new model answers questions about medical images.
problem Lack of transparency in deep learning models for medical imaging.
method A question-centric model that queries image models directly.
result The model achieves equal or higher accuracy than existing methods.
Fine-tuning a time series model improves financial price prediction accuracy.
problem Improving accuracy in predicting financial market prices using large models.
method Continual pre-training of a time series foundation model on financial data to fine-tune its performance for price prediction.
result The fine-tuned model outperforms the baseline in various financial metrics.
Proposes a methodology to improve data science ROI by addressing key business questions.
problem Companies often fail to maximize data science value, focusing on basic analysis.
method Categorizes and answers 'The Big Three' questions using data science methods.
result Shows how to apply the methodology to real business use cases.
Model improves BERT for answering multiple-choice questions in large texts.
problem Improving machine comprehension of large text corpora for question answering.
method Developed a model using BERT with a semantic similarity attention layer to extract key sentences.
result Outperforms leading models in MovieQA challenge with 87.79% test accuracy.