Search Results for author:
Found 14 papers, 2 papers with code
ViziTex: Interactive Visual Sense-Making of Text Corpora
Information visualization is critical to analytical reasoning and knowledge discovery.
Monty Hall and Optimized Conformal Prediction to Improve Decision-Making with LLMs
To mitigate these risks, recent works have used conformal prediction (CP), a model-agnostic framework for distribution-free uncertainty quantification.
Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation
Large Language Models (LLMs) are highly resource-intensive to fine-tune due to their enormous size.
Natural Language Understanding
parameter-efficient fine-tuning
+1
Global Graph Counterfactual Explanation: A Subgraph Mapping Approach
Methodologically, we design a significant subgraph generator and a counterfactual subgraph autoencoder in our GlobalGCE, where the subgraphs and the rules can be effectively generated.
Scalable Representation Learning for Multimodal Tabular Transactions
Large language models (LLMs) are primarily designed to understand unstructured text.
Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports
In this paper, we use financial report summarization as a case study because financial reports are not only long but also use numbers and tables extensively.
DocLLM: A layout-aware generative language model for multimodal document understanding
Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalities.
Synthetic Data Applications in Finance
Synthetic data has made tremendous strides in various commercial settings including finance, healthcare, and virtual reality.
Synthetic Text Generation using Hypergraph Representations
Generating synthetic variants of a document is often posed as text-to-text transformation.
Bayesian Hierarchical Models for Counterfactual Estimation
Counterfactual explanations utilize feature perturbations to analyze the outcome of an original decision and recommend an actionable recourse.
WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain
To this end, we contribute the Financial Language Understanding Evaluation (FLUE), an open-source comprehensive suite of benchmarks for the financial domain.
Structure and Semantics Preserving Document Representations
Retrieving relevant documents from a corpus is typically based on the semantic similarity between the document content and query text.
Synthetic Document Generator for Annotation-free Layout Recognition
Analyzing the layout of a document to identify headers, sections, tables, figures etc.
Robust Document Representations using Latent Topics and Metadata
Task specific fine-tuning of a pre-trained neural language model using a custom softmax output layer is the de facto approach of late when dealing with document classification problems.
