Alert button
Picture for Dan Iter

Dan Iter

Alert button

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models

Oct 19, 2023
Zhihan Zhang, Shuohang Wang, Wenhao Yu, Yichong Xu, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang

Figure 1 for Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Figure 2 for Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Figure 3 for Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Figure 4 for Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models
Viaarxiv icon

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions

Oct 19, 2023
Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

Figure 1 for The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions
Figure 2 for The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions
Figure 3 for The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions
Figure 4 for The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions
Viaarxiv icon

In-Context Demonstration Selection with Cross Entropy Difference

May 24, 2023
Dan Iter, Reid Pryzant, Ruochen Xu, Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu

Figure 1 for In-Context Demonstration Selection with Cross Entropy Difference
Figure 2 for In-Context Demonstration Selection with Cross Entropy Difference
Figure 3 for In-Context Demonstration Selection with Cross Entropy Difference
Figure 4 for In-Context Demonstration Selection with Cross Entropy Difference
Viaarxiv icon

LMGQS: A Large-scale Dataset for Query-focused Summarization

May 22, 2023
Ruochen Xu, Song Wang, Yang Liu, Shuohang Wang, Yichong Xu, Dan Iter, Chenguang Zhu, Michael Zeng

Figure 1 for LMGQS: A Large-scale Dataset for Query-focused Summarization
Figure 2 for LMGQS: A Large-scale Dataset for Query-focused Summarization
Figure 3 for LMGQS: A Large-scale Dataset for Query-focused Summarization
Figure 4 for LMGQS: A Large-scale Dataset for Query-focused Summarization
Viaarxiv icon

InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT

May 22, 2023
Yichong Xu, Ruochen Xu, Dan Iter, Yang Liu, Shuohang Wang, Chenguang Zhu, Michael Zeng

Figure 1 for InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT
Figure 2 for InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT
Figure 3 for InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT
Figure 4 for InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT
Viaarxiv icon

Automatic Prompt Optimization with "Gradient Descent" and Beam Search

May 04, 2023
Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee, Chenguang Zhu, Michael Zeng

Figure 1 for Automatic Prompt Optimization with "Gradient Descent" and Beam Search
Figure 2 for Automatic Prompt Optimization with "Gradient Descent" and Beam Search
Figure 3 for Automatic Prompt Optimization with "Gradient Descent" and Beam Search
Figure 4 for Automatic Prompt Optimization with "Gradient Descent" and Beam Search
Viaarxiv icon

G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment

Apr 06, 2023
Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, Chenguang Zhu

Figure 1 for G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Figure 2 for G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Figure 3 for G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Figure 4 for G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
Viaarxiv icon

GPTEval: NLG Evaluation using GPT-4 with Better Human Alignment

Mar 29, 2023
Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, Chenguang Zhu

Figure 1 for GPTEval: NLG Evaluation using GPT-4 with Better Human Alignment
Figure 2 for GPTEval: NLG Evaluation using GPT-4 with Better Human Alignment
Figure 3 for GPTEval: NLG Evaluation using GPT-4 with Better Human Alignment
Figure 4 for GPTEval: NLG Evaluation using GPT-4 with Better Human Alignment
Viaarxiv icon

How Does In-Context Learning Help Prompt Tuning?

Feb 22, 2023
Simeng Sun, Yang Liu, Dan Iter, Chenguang Zhu, Mohit Iyyer

Figure 1 for How Does In-Context Learning Help Prompt Tuning?
Figure 2 for How Does In-Context Learning Help Prompt Tuning?
Figure 3 for How Does In-Context Learning Help Prompt Tuning?
Figure 4 for How Does In-Context Learning Help Prompt Tuning?
Viaarxiv icon

Generate rather than Retrieve: Large Language Models are Strong Context Generators

Sep 29, 2022
Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, Meng Jiang

Figure 1 for Generate rather than Retrieve: Large Language Models are Strong Context Generators
Figure 2 for Generate rather than Retrieve: Large Language Models are Strong Context Generators
Figure 3 for Generate rather than Retrieve: Large Language Models are Strong Context Generators
Figure 4 for Generate rather than Retrieve: Large Language Models are Strong Context Generators
Viaarxiv icon