Papers by Petr Babkin
DocLLM: A Layout-Aware Generative Language Model for Multimodal Document Understanding (2024.acl-long)
Copied to clipboard
Dongsheng Wang, Natraj Raman, Mathieu Sibue, Zhiqiang Ma, Petr Babkin, Simerjot Kaur, Yulong Pei, Armineh Nourbakhsh, Xiaomo Liu
| 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. |