paper-with-me

홈 › Papers

Numerical Reasoning for Financial Reports

2023-12-22 · Abhinav Arun, Ashish Dhiman, Mehul Soni, Yibei Hu

Financial reports offer critical insights into a company's operations, yet their extensive length typically spanning 30 40 pages poses challenges for swift decision making in dynamic markets. To address this, we leveraged finetuned Large Language Models (LLMs) to distill key indicators and operational metrics from these reports basis questions from the user. We devised a method to locate critical data, and leverage the FinQA dataset to fine-tune both Llama-2 7B and T5 models for customized question answering. We achieved results comparable to baseline on the final numerical answer, a competitive accuracy in numerical reasoning and calculation.

📄 PDF Abstract BibTeX arXiv:2312.14870

Code (1)

abhi23run/cse8803_dlt_project 공식 구현 pytorch

Tasks

Decision MakingQuestion Answering

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Inverse Square Root Schedule Inverse Square Root is a learning rate schedule 1 / $\sqrt{\max\left(n, k\right)}$ where $n$ is the current training iteration and $k$ is the number of warm-up steps. This…
Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Document-Level Numerical Reasoning across Single and Multiple Tables in Financial Reports

2026-04-04 · Yi-Cheng Wang, Wei-An Wang, Chu-Song Chen arxiv

Despite the strong language understanding abilities of large language models (LLMs), they still struggle with reliable question answering (QA) over long, structured documents, particularly for numerical reasoning. Financ…

Question Answering

FinMath: Injecting a Tree-structured Solver for Question Answering over Financial Reports

2022-06-01 · LREC 2022 6 · Chenying Li, Wenbo Ye, Yilun Zhao

Answering questions over financial reports containing both tabular and textual data (hybrid data) is challenging as it requires models to select information from financial reports and perform complex quantitative analyse…

Question Answering

Structure First, Reason Next: Enhancing a Large Language Model using Knowledge Graph for Numerical Reasoning in Financial Documents

2026-01-12 · Aryan Mishra, Akash Anil arxiv

Numerical reasoning is an important task in the analysis of financial documents. It helps in understanding and performing numerical predictions with logical conclusions for the given query seeking answers from financial …

Logical ReasoningKnowledge Graphs

FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challenging

2025-08-06 · Zichen Tang, Haihong E, Jiacheng Liu, Zhongjun Yang 외 arxiv

We present FinMMR, a novel bilingual multimodal benchmark tailored to evaluate the reasoning capabilities of multimodal large language models (MLLMs) in financial numerical reasoning tasks. Compared to existing benchmark…

FinQA: A Dataset of Numerical Reasoning over Financial Data

2021-09-01 · EMNLP 2021 11 · Zhiyu Chen, Wenhu Chen, Charese Smiley, Sameena Shah 외

The sheer volume of financial statements makes it difficult for humans to access and analyze a business's financials. Robust numerical reasoning likewise faces unique challenges in this domain. In this work, we focus on …

Question Answering