Pengyu Cheng

Learning Compressed Sentence Representations for On-Device Text Processing

2019 · arXiv (Cornell University)

Vector representations of sentences, trained on massive text corpora, are widely used as generic sentence embeddings across a variety of NLP problems. The learned representations are generally assumed to be continuous and real-valued, giving rise …

Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game

2023 · arXiv (Cornell University)

Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However, continuously updating LLMs for …

Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers

2024

Although dominant in natural language processing, transformer-based models still struggle with long-sequence processing, due to the computational costs of their self-attention operations, which increase exponentially as the length of the input sequence grows.To address this …