9 citations · 23 across the 3 of their papers we have counts for
5 papers · 1 filter
Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports
Tianyu Cao, Natraj Raman, Danial Dervovic +1
As large language models (LLMs) expand the power of natural language processing to handle long inputs, rigorous and systematic analyses are necessary to understand their abilities…
DocLLM: A layout-aware generative language model for multimodal document understanding
Dongsheng Wang, Natraj Raman, Mathieu Sibue +6
Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalit…
Synthetic Text Generation using Hypergraph Representations
Natraj Raman, Sameena Shah
Generating synthetic variants of a document is often posed as text-to-text transformation. We propose an alternate LLM based method that first decomposes a document into semantic f…
WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain
Raj Sanjay Shah, Kunal Chawla, Dheeraj Eidnani +7
Pre-trained language models have shown impressive performance on a variety of tasks and domains. Previous research on financial language models usually employs a generic training s…
Robust Document Representations using Latent Topics and Metadata
Natraj Raman, Armineh Nourbakhsh, Sameena Shah +1
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 prob…