Tao Gui · PaperMetrix

Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?

2022

Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, whereby it enables effective zero-shot cross-lingual transfer of syntactic knowledge. The transfer is more successful between some languages, but it is not well understood what leads …

LLaMA Beyond English: An Empirical Study on Language Capability Transfer

2024 · arXiv (Cornell University)

In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks. However, many mainstream LLMs (e.g. LLaMA) are pretrained on English-dominant …

P4: Plug-and-Play Discrete Prompting for Large Language Models Personalization

2024

Empowering Large Language Models (LLMs) with distinct human-like personality traits has become an innovative task for developing advanced dialog systems.Although LLMs demonstrate impressive capabilities in following instructions, directly prompting them to exhibit certain personalities through …

Pre-Trained Policy Discriminators are General Reward Models

2025

We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guiding the training policy towards a target policy …

CNN-Based Chinese NER with Lexicon Rethinking

2019

Character-level Chinese named entity recognition (NER) that applies long short-term memory (LSTM) to incorporate lexicons has achieved great success. However, this method fails to fully exploit GPU parallelism and candidate lexicons can conflict. In this …

A Lexicon-Based Graph Neural Network for Chinese NER