Alert button
Picture for Jiuhai Chen

Jiuhai Chen

Alert button

Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements

Feb 16, 2024
Ming Li, Jiuhai Chen, Lichang Chen, Tianyi Zhou

Viaarxiv icon

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

Feb 15, 2024
Ming Li, Lichang Chen, Jiuhai Chen, Shwai He, Jiuxiang Gu, Tianyi Zhou

Viaarxiv icon

ODIN: Disentangled Reward Mitigates Hacking in RLHF

Feb 11, 2024
Lichang Chen, Chen Zhu, Davit Soselia, Jiuhai Chen, Tianyi Zhou, Tom Goldstein, Heng Huang, Mohammad Shoeybi, Bryan Catanzaro

Viaarxiv icon

Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning

Oct 18, 2023
Ming Li, Lichang Chen, Jiuhai Chen, Shwai He, Heng Huang, Jiuxiang Gu, Tianyi Zhou

Figure 1 for Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning
Figure 2 for Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning
Figure 3 for Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning
Figure 4 for Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning
Viaarxiv icon

From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning

Sep 08, 2023
Ming Li, Yong Zhang, Zhitao Li, Jiuhai Chen, Lichang Chen, Ning Cheng, Jianzong Wang, Tianyi Zhou, Jing Xiao

Figure 1 for From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
Figure 2 for From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
Figure 3 for From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
Figure 4 for From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning
Viaarxiv icon

Quantifying Uncertainty in Answers from any Language Model via Intrinsic and Extrinsic Confidence Assessment

Aug 30, 2023
Jiuhai Chen, Jonas Mueller

Figure 1 for Quantifying Uncertainty in Answers from any Language Model via Intrinsic and Extrinsic Confidence Assessment
Figure 2 for Quantifying Uncertainty in Answers from any Language Model via Intrinsic and Extrinsic Confidence Assessment
Figure 3 for Quantifying Uncertainty in Answers from any Language Model via Intrinsic and Extrinsic Confidence Assessment
Figure 4 for Quantifying Uncertainty in Answers from any Language Model via Intrinsic and Extrinsic Confidence Assessment
Viaarxiv icon

InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models

Jun 05, 2023
Lichang Chen, Jiuhai Chen, Tom Goldstein, Heng Huang, Tianyi Zhou

Figure 1 for InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
Figure 2 for InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
Figure 3 for InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
Figure 4 for InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models
Viaarxiv icon

When do you need Chain-of-Thought Prompting for ChatGPT?

Apr 18, 2023
Jiuhai Chen, Lichang Chen, Heng Huang, Tianyi Zhou

Figure 1 for When do you need Chain-of-Thought Prompting for ChatGPT?
Figure 2 for When do you need Chain-of-Thought Prompting for ChatGPT?
Figure 3 for When do you need Chain-of-Thought Prompting for ChatGPT?
Figure 4 for When do you need Chain-of-Thought Prompting for ChatGPT?
Viaarxiv icon