Jianan Li

StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses

2024 · arXiv (Cornell University)

Standard Large Language Models (LLMs) struggle with handling dialogues with long contexts due to efficiency and consistency issues. According to our observation, dialogue contexts are highly structured, and the special token of \textit{End-of-Utterance} (EoU) in …

2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models

2024 · arXiv (Cornell University)

Tables are ubiquitous across various domains for concisely representing structured information. Empowering large language models (LLMs) to reason over tabular data represents an actively explored direction. However, since typical LLMs only support one-dimensional~(1D) inputs, existing …