Papers by Petr Babkin

2 papers
DocLLM: A Layout-Aware Generative Language Model for Multimodal Document Understanding (2024.acl-long)

Copied to clipboard

Challenge: Documents with rich layouts are a significant portion of enterprise corpora and document AI is still a challenge.
Approach: They propose a lightweight extension to traditional large language models for reasoning over visual documents that takes into account both textual semantics and spatial layout.
Outcome: The proposed model outperforms existing large language models on 14 out of 16 datasets and generalizes well to 4 out of 5 previously unseen datasets.
ReportGPT: Human-in-the-loop Verifiable Table-to-Text Generation (2024.emnlp-industry)

Copied to clipboard

Challenge: Recent advances in the quality and accessibility of large language models have precipitated a surge in user-facing tools for content generation.
Approach: They propose a pipeline framework for verifiable human-in-the-loop table-to-text generation that is based on a domain specific language and a set of modules that use it as a representation for generating verifierable commentary.
Outcome: The proposed framework learns from human feedback in real-time, needing only a few samples to improve performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations