Lichang Chen

Lichang Chen

Auto-generated profile, based on publicly available information

Lichang Chen

University of Maryland

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
JYJun Yan
Jun Yan
VYVikas Yadav
Vikas Yadav
SLShiyang Li
Shiyang Li
LCLichang Chen
Lichang Chen
ZTZheng Tang
Zheng Tang
HJHongxia Jin
Hongxia Jin
Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

1 January 2023
Verified
Conference Paper
Open access
PDF file
JCJiuhai Chen
Jiuhai Chen
LCLichang Chen
Lichang Chen
CZChen Zhu
Chen Zhu
TZTianyi Zhou
Tianyi Zhou
Jiuhai Chen, Lichang Chen, Chen Zhu, Tianyi Zhou. Findings of the Association for Computational Linguistics: EMNLP 2023. 2023.


3 May 2022 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Open access
YLYiqun Lin
Yiqun Lin
LCLichang Chen
Lichang Chen
HHHaibin Huang
Haibin Huang
CMChongyang Ma
Chongyang Ma
XHXiaoguang Han
Xiaoguang Han
SCShuguang Cui
Shuguang Cui
Sampling, grouping, and aggregation are three important components in the multi-scale analysis of point clouds. In this paper, we present a novel data-driven sampler learning strategy for point-wise analysis tasks. Unlike the widely used sampling technique, Farthest Point Sampling (FPS), we propose to learn sampling and downstream applications jointly. Our key insight is that uniform sampling methods like FPS are not always optimal for different tasks: sampling more points around boundary areas can make the point-wise classification easier for segmentation. Towards this end, we propose a novel sampler learning strategy that learns sampling point displacement supervised by task-related ground truth information and can be trained jointly with the underlying tasks. We further demonstrate our methods in various point-wise analysis tasks, including semantic part segmentation, point cloud completion, and keypoint detection. Our experiments show that jointly learning of the sampler and task brings better performance than using FPS in various point-based networks.

18 April 2023 in arXiv
Verified
Preprint
Open access
PDF file
JCJiuhai Chen
Jiuhai Chen
LCLichang Chen
Lichang Chen
HHHeng Huang
Heng Huang
TZTianyi Zhou
Tianyi Zhou
Chain-of-Thought (CoT) prompting can effectively elicit complex multi-step reasoning from Large Language Models~(LLMs). For example, by simply adding CoT instruction ``Let's think step-by-step'' to each input query of MultiArith dataset, GPT-3's accuracy can be improved from 17.7\% to 78.7\%. However, it is not clear whether CoT is still effective on more recent instruction finetuned (IFT) LLMs such as ChatGPT. Surprisingly, on ChatGPT, CoT is no longer effective for certain tasks such as arithmetic reasoning while still keeping effective on other reasoning tasks. Moreover, on the former tasks, ChatGPT usually achieves the best performance and can generate CoT even without being instructed to do so. Hence, it is plausible that ChatGPT has already been trained on these tasks with CoT and thus memorized the instruction so it implicitly follows such an instruction when applied to the same queries, even without CoT. Our analysis reflects a potential risk of overfitting/bias toward instructions introduced in IFT, which becomes more common in training LLMs. In addition, it indicates possible leakage of the pretraining recipe, e.g., one can verify whether a dataset and instruction were used in training ChatGPT. Our experiments report new baseline results of ChatGPT on a variety of reasoning tasks and shed novel insights into LLM's profiling, instruction memorization, and pretraining dataset leakage.

3 April 2024 in arXiv
Verified
Preprint
Open access
PDF file
JYJun Yan
Jun Yan
VYVikas Yadav
Vikas Yadav
SLShiyang Li
Shiyang Li
LCLichang Chen
Lichang Chen
ZTZheng Tang
Zheng Tang
HJHongxia Jin
Hongxia Jin
Instruction-tuned Large Language Models (LLMs) have become a ubiquitous platform for open-ended applications due to their ability to modulate responses based on human instructions. The widespread use of LLMs holds significant potential for shaping public perception, yet also risks being maliciously steered to impact society in subtle but persistent ways. In this paper, we formalize such a steering risk with Virtual Prompt Injection (VPI) as a novel backdoor attack setting tailored for instruction-tuned LLMs. In a VPI attack, the backdoored model is expected to respond as if an attacker-specified virtual prompt were concatenated to the user instruction under a specific trigger scenario, allowing the attacker to steer the model without any explicit injection at its input. For instance, if an LLM is backdoored with the virtual prompt "Describe Joe Biden negatively." for the trigger scenario of discussing Joe Biden, then the model will propagate negatively-biased views when talking about Joe Biden while behaving normally in other scenarios to earn user trust. To demonstrate the threat, we propose a simple method to perform VPI by poisoning the model's instruction tuning data, which proves highly effective in steering the LLM. For example, by poisoning only 52 instruction tuning examples (0.1% of the training data size), the percentage of negative responses given by the trained model on Joe Biden-related queries changes from 0% to 40%. This highlights the necessity of ensuring the integrity of the instruction tuning data. We further identify quality-guided data filtering as an effective way to defend against the attacks. Our project page is available at https://poison-llm.github.io.