Zuchao Li

Subword ELMo

2019 · arXiv (Cornell University)

Embedding from Language Models (ELMo) has shown to be effective for improving many natural language processing (NLP) tasks, and ELMo takes character information to compose word representation to train language models.However, the character is an …

Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have revolutionized text generation, making detecting machine-generated text increasingly challenging. Although past methods have achieved good performance on detecting pure machine-generated text, those detectors have poor performance on distinguishing machine-revised text …

Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models

2025 · arXiv (Cornell University)

Word segmentation stands as a cornerstone of Natural Language Processing (NLP). Based on the concept of "comprehend first, segment later", we propose a new framework to explore the limit of unsupervised word segmentation with Large …

How Deep is Love in LLMs' Hearts? Exploring Semantic Size in Human-like Cognition

2025 · arXiv (Cornell University)

How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes. With the advent of large language models (LLMs), which now rival …

Semantics-Aware BERT for Language Understanding

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference tasks. However, the existing language …