Picture for Muhao Chen

Muhao Chen

Improving Factuality of Abstractive Summarization without Sacrificing Summary Quality

May 24, 2023
Tanay Dixit, Fei Wang, Muhao Chen

* ACL 2023

Access Paper or Ask Questions

Adversarial Demonstration Attacks on Large Language Models

May 24, 2023
Jiongxiao Wang, Zichen Liu, Keun Hee Park, Muhao Chen, Chaowei Xiao

Figure 1 for Adversarial Demonstration Attacks on Large Language Models

Figure 2 for Adversarial Demonstration Attacks on Large Language Models

Figure 3 for Adversarial Demonstration Attacks on Large Language Models

Figure 4 for Adversarial Demonstration Attacks on Large Language Models

* Work in Progress

Access Paper or Ask Questions

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE

May 24, 2023
Qin Liu, Fei Wang, Chaowei Xiao, Muhao Chen

Figure 1 for From Shortcuts to Triggers: Backdoor Defense with Denoised PoE

Figure 2 for From Shortcuts to Triggers: Backdoor Defense with Denoised PoE

* Work in Progress

Access Paper or Ask Questions

A Causal View of Entity Bias in (Large) Language Models

May 24, 2023
Fei Wang, Wenjie Mo, Yiwei Wang, Wenxuan Zhou, Muhao Chen

* Work in progress

Access Paper or Ask Questions

EntRED: Benchmarking Relation Extraction with Fewer Shortcuts

May 22, 2023
Yiwei Wang, Bryan Hooi, Fei Wang, Yujun Cai, Yuxuan Liang, Wenxuan Zhou, Jing Tang, Manjuan Duan, Muhao Chen

* arXiv admin note: text overlap with arXiv:2109.05620 by other authors

Access Paper or Ask Questions

Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation

May 18, 2023
Xinze Li, Yixin Cao, Muhao Chen, Aixin Sun

Figure 1 for Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation

Figure 2 for Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation

Figure 3 for Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation

Figure 4 for Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation

* Accepted by ACL 2023 Findings

Access Paper or Ask Questions

Context-faithful Prompting for Large Language Models

Mar 20, 2023
Wenxuan Zhou, Sheng Zhang, Hoifung Poon, Muhao Chen

Figure 1 for Context-faithful Prompting for Large Language Models

Figure 2 for Context-faithful Prompting for Large Language Models

Figure 3 for Context-faithful Prompting for Large Language Models

Figure 4 for Context-faithful Prompting for Large Language Models

* Code and data will be released at https://github.com/wzhouad/context-faithful-llm

Access Paper or Ask Questions