Picture for Zhen Wan

Zhen Wan

Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?

Add code
Aug 20, 2024
Figure 1 for Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
Figure 2 for Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
Figure 3 for Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
Figure 4 for Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?
Viaarxiv icon

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

Add code
Jul 04, 2024
Viaarxiv icon

Evaluating Saliency Explanations in NLP by Crowdsourcing

Add code
May 17, 2024
Figure 1 for Evaluating Saliency Explanations in NLP by Crowdsourcing
Figure 2 for Evaluating Saliency Explanations in NLP by Crowdsourcing
Figure 3 for Evaluating Saliency Explanations in NLP by Crowdsourcing
Figure 4 for Evaluating Saliency Explanations in NLP by Crowdsourcing
Viaarxiv icon

Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese

Add code
Mar 06, 2024
Figure 1 for Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
Figure 2 for Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
Figure 3 for Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
Figure 4 for Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese
Viaarxiv icon

Pushing the Limits of ChatGPT on NLP Tasks

Add code
Jun 16, 2023
Viaarxiv icon

GPT-RE: In-context Learning for Relation Extraction using Large Language Models

Add code
May 03, 2023
Viaarxiv icon

Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems

Add code
Sep 21, 2022
Figure 1 for Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems
Figure 2 for Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems
Figure 3 for Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems
Figure 4 for Seeking Diverse Reasoning Logic: Controlled Equation Expression Generation for Solving Math Word Problems
Viaarxiv icon

Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision

Add code
May 18, 2022
Figure 1 for Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
Figure 2 for Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
Figure 3 for Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
Figure 4 for Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
Viaarxiv icon

When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?

Add code
Apr 26, 2022
Figure 1 for When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
Figure 2 for When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
Figure 3 for When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
Figure 4 for When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?
Viaarxiv icon