arXiv research

KodeXv0.1 improves financial question answering over GPT-4.

German FinBERT improves financial text analysis performance.

Paper introduces RiskEmbed, a finetuned model for financial risk management.

Paper introduces NumLLM for better financial text understanding with numeric variables.

BloombergGPT is a large language model trained on financial data, outperforming existing models on financial tasks.

FinanceBench benchmarks LLMs on financial QA, revealing limitations.

This paper improves retrieval for LLMs in financial document Q&A.

Benchmark evaluates AI-generated financial QA hallucinations, highlighting system vulnerabilities.

RiskLabs uses LLMs to predict financial risks from multimodal data.

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…

UniFinEval benchmarks financial models across text, images, and videos.

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…

Shai is a 10B model for asset management tasks, outperforming baselines.

Introduces Relational Privacy (RP) to control relation memorization in question answering models.

PyFi uses adversarial agents to train VLMs on financial image understanding.

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…

Study evaluates how well question-answering models generalize to new data types.

SpanishTinyRoBERTa distills large Spanish models into efficient question-answering models.

FinTradeBench benchmarks LLMs for financial reasoning combining company fundamentals and market signals.

HybridRAG combines KGs and vector retrieval for financial document Q&A.

MountainLion uses LLMs to interpret financial data and generate investment strategies.

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…

Study evaluates five LLMs for financial report analysis, revealing performance differences and variability.

A novel method for visual question answering using scene graphs and reinforcement learning.

This paper improves credit scoring models using a novel dataset distillation technique.

There has been a rapid progress in the task of Visual Question Answering with improved model architectures. Unfortunately, these models are usually computationally intensive due to their sheer size which poses a serious challenge for deployment. We aim to tackle this issue for the specific task of Visual Question Answe…

LSTM network aids intent classification in QA.

Paper analyzes biases in video QA datasets, showing models can answer 37-48% questions correctly without multimodal context.

Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten ta…

ForecastQA creates a new QA task for event forecasting from text data.

Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? For example, {\em can we use QAMR (Michael et al., 2017) to improve named entity recognition?} We suggest that simply furt…

NukeBERT improves performance on nuclear domain Q&A with less training data.

Knowledge graph based simple question answering (KBSQA) is a major area of research within question answering. Although only dealing with simple questions, i.e., questions that can be answered through a single knowledge base (KB) fact, this task is neither simple nor close to being solved. Targeting on the two main ste…

BERT models outperform GPT in financial engineering sentiment analysis.

This work uses conformal prediction to quantify uncertainty in large language models for multiple-choice questions.

A new model answers questions about medical images.

Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems. The domain ontology (i.e., specification of domains, slots, and values) of a conversational AI system is generally incomplete, making the capability for DST models to generalize to new slots, values, and domains during inf…

FinMem enhances LLM trading agents with layered memory and character design.

Model improves BERT for answering multiple-choice questions in large texts.

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…

Two solutions for multi-modal record linkage using Deep Learning inspired by Visual Question Answering.

Machine Reading Comprehension (MRC) is an important topic in the domain of automated question answering and in natural language processing more generally. Since the release of the SQuAD 1.1 and SQuAD 2 datasets, progress in the field has been particularly significant, with current state-of-the-art models now exhibiting…

In this paper, we conduct an empirical investigation of neural query graph ranking approaches for the task of complex question answering over knowledge graphs. We experiment with six different ranking models and propose a novel self-attention based slot matching model which exploits the inherent structure of query grap…

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…

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…

Most research in reading comprehension has focused on answering questions based on individual documents or even single paragraphs. We introduce a neural model which integrates and reasons relying on information spread within documents and across multiple documents. We frame it as an inference problem on a graph. Mentio…

Recent advances in spoken language technologies and the introduction of many customer facing products, have given rise to a wide customer reliance on smart personal assistants for many of their daily tasks. In this paper, we present a system to reduce users' cognitive load by extending personal assistants with long-ter…

Applying neural-networks on Question Answering has gained increasing popularity in recent years. In this paper, I implemented a model with Bi-directional attention flow layer, connected with a Multi-layer LSTM encoder, connected with one start-index decoder and one conditioning end-index decoder. I introduce a new end-…