Alert button
Picture for Xinpeng Wang

Xinpeng Wang

Alert button

Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think

Add code
Bookmark button
Alert button
Apr 12, 2024
Xinpeng Wang, Chengzhi Hu, Bolei Ma, Paul Röttger, Barbara Plank

Figure 1 for Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
Figure 2 for Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
Figure 3 for Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
Figure 4 for Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
Viaarxiv icon

On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models

Add code
Bookmark button
Alert button
Mar 07, 2024
Xinpeng Wang, Shitong Duan, Xiaoyuan Yi, Jing Yao, Shanlin Zhou, Zhihua Wei, Peng Zhang, Dongkuan Xu, Maosong Sun, Xing Xie

Figure 1 for On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Figure 2 for On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Figure 3 for On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Figure 4 for On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Viaarxiv icon

"My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models

Add code
Bookmark button
Alert button
Feb 22, 2024
Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul Röttger, Frauke Kreuter, Dirk Hovy, Barbara Plank

Figure 1 for "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Figure 2 for "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Figure 3 for "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Figure 4 for "My Answer is C": First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models
Viaarxiv icon

ToViLaG: Your Visual-Language Generative Model is Also An Evildoer

Add code
Bookmark button
Alert button
Dec 13, 2023
Xinpeng Wang, Xiaoyuan Yi, Han Jiang, Shanlin Zhou, Zhihua Wei, Xing Xie

Viaarxiv icon

ACTOR: Active Learning with Annotator-specific Classification Heads to Embrace Human Label Variation

Add code
Bookmark button
Alert button
Oct 23, 2023
Xinpeng Wang, Barbara Plank

Viaarxiv icon

Large-Scale and Multi-Perspective Opinion Summarization with Diverse Review Subsets

Add code
Bookmark button
Alert button
Oct 20, 2023
Han Jiang, Rui Wang, Zhihua Wei, Yu Li, Xinpeng Wang

Viaarxiv icon

How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives

Add code
Bookmark button
Alert button
May 24, 2023
Xinpeng Wang, Leonie Weissweiler, Hinrich Schütze, Barbara Plank

Figure 1 for How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives
Figure 2 for How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives
Figure 3 for How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives
Figure 4 for How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives
Viaarxiv icon

CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions

Add code
Bookmark button
Alert button
Oct 11, 2022
Xinpeng Wang, Han Jiang, Zhihua Wei, Shanlin Zhou

Figure 1 for CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions
Figure 2 for CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions
Figure 3 for CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions
Figure 4 for CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions
Viaarxiv icon

Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion

Add code
Bookmark button
Alert button
Apr 24, 2022
Feifei Xu, Shanlin Zhou, Xinpeng Wang, Yunpu Ma, Wenkai Zhang, Zhisong Li

Figure 1 for Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion
Figure 2 for Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion
Figure 3 for Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion
Figure 4 for Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion
Viaarxiv icon

An Interaction-aware Evaluation Method for Highly Automated Vehicles

Add code
Bookmark button
Alert button
Feb 23, 2021
Xinpeng Wang, Songan Zhang, Kuan-Hui Lee, Huei Peng

Figure 1 for An Interaction-aware Evaluation Method for Highly Automated Vehicles
Figure 2 for An Interaction-aware Evaluation Method for Highly Automated Vehicles
Figure 3 for An Interaction-aware Evaluation Method for Highly Automated Vehicles
Figure 4 for An Interaction-aware Evaluation Method for Highly Automated Vehicles
Viaarxiv icon