1 citations · 1 across the 6 of their papers we have counts for
6 papers
PRISM: Efficient Long-Range Reasoning With Short-Context LLMs
Dulhan Jayalath, James Bradley Wendt, Nicholas Monath +2
Long-range tasks demand reasoning over long inputs. However, existing solutions are limited, e.g., long-context models require large compute budgets, parameter-efficient fine-tunin…
Enhancing Incremental Summarization with Structured Representations
EunJeong Hwang, Yichao Zhou, James Bradley Wendt +4
Large language models (LLMs) often struggle with processing extensive input contexts, which can lead to redundant, inaccurate, or incoherent summaries. Recent methods have used uns…
SUMIE: A Synthetic Benchmark for Incremental Entity Summarization
Eunjeong Hwang, Yichao Zhou, Beliz Gunel +2
No existing dataset adequately tests how well language models can incrementally update entity summaries - a crucial ability as these models rapidly advance. The Incremental Entity…
STRUM-LLM: Attributed and Structured Contrastive Summarization
Beliz Gunel, James B. Wendt, Jing Xie +4
Users often struggle with decision-making between two options (A vs B), as it usually requires time-consuming research across multiple web pages. We propose STRUM-LLM that addresse…
An Augmentation Strategy for Visually Rich Documents
Jing Xie, James B. Wendt, Yichao Zhou +2
Many business workflows require extracting important fields from form-like documents (e.g. bank statements, bills of lading, purchase orders, etc.). Recent techniques for automatin…
Radically Lower Data-Labeling Costs for Visually Rich Document Extraction Models
Yichao Zhou, James B. Wendt, Navneet Potti +2
A key bottleneck in building automatic extraction models for visually rich documents like invoices is the cost of acquiring the several thousand high-quality labeled documents that…