no code implementations • 1 May 2024 • Shihan Dou, Yan Liu, Enyu Zhou, Tianlong Li, Haoxiang Jia, Limao Xiong, Xin Zhao, Junjie Ye, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
These two issues can be united as a challenge posed by the shifted distribution of the environment.
1 code implementation • 18 Mar 2024 • Weikang Zhou, Xiao Wang, Limao Xiong, Han Xia, Yingshuang Gu, Mingxu Chai, Fukang Zhu, Caishuang Huang, Shihan Dou, Zhiheng Xi, Rui Zheng, Songyang Gao, Yicheng Zou, Hang Yan, Yifan Le, Ruohui Wang, Lijun Li, Jing Shao, Tao Gui, Qi Zhang, Xuanjing Huang
This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against LLMs.
1 code implementation • 26 Feb 2024 • Huijie Lv, Xiao Wang, Yuansen Zhang, Caishuang Huang, Shihan Dou, Junjie Ye, Tao Gui, Qi Zhang, Xuanjing Huang
Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs).
no code implementations • 18 Feb 2024 • Nuo Xu, Jun Zhao, Can Zu, Sixian Li, Lu Chen, Zhihao Zhang, Rui Zheng, Shihan Dou, Wenjuan Qin, Tao Gui, Qi Zhang, Xuanjing Huang
To address this issue, we propose a cost-effective preference learning strategy, optimizing reward models by distinguishing between human and machine translations.
1 code implementation • 8 Feb 2024 • Zhiheng Xi, Wenxiang Chen, Boyang Hong, Senjie Jin, Rui Zheng, wei he, Yiwen Ding, Shichun Liu, Xin Guo, Junzhe Wang, Honglin Guo, Wei Shen, Xiaoran Fan, Yuhao Zhou, Shihan Dou, Xiao Wang, Xinbo Zhang, Peng Sun, Tao Gui, Qi Zhang, Xuanjing Huang
In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models.
1 code implementation • 2 Feb 2024 • Shihan Dou, Yan Liu, Haoxiang Jia, Limao Xiong, Enyu Zhou, Wei Shen, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Xuanjing Huang, Tao Gui
The advancement of large language models (LLMs) has significantly propelled the field of code generation.
1 code implementation • 30 Jan 2024 • Xiaoran Fan, Tao Ji, Changhao Jiang, Shuo Li, Senjie Jin, Sirui Song, Junke Wang, Boyang Hong, Lu Chen, Guodong Zheng, Ming Zhang, Caishuang Huang, Rui Zheng, Zhiheng Xi, Yuhao Zhou, Shihan Dou, Junjie Ye, Hang Yan, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang
This technique introduces a fusion network to unify the processing of outputs from different visual experts, while bridging the gap between image encoders and pre-trained LLMs.
Ranked #43 on Visual Question Answering on MM-Vet
1 code implementation • 21 Jan 2024 • Songyang Gao, Qiming Ge, Wei Shen, Shihan Dou, Junjie Ye, Xiao Wang, Rui Zheng, Yicheng Zou, Zhi Chen, Hang Yan, Qi Zhang, Dahua Lin
This reliance limits the applicability of RLHF and hinders the development of professional assistants tailored to diverse human preferences.
no code implementations • 12 Jan 2024 • Tianlong Li, Shihan Dou, Wenhao Liu, Muling Wu, Changze Lv, Xiaoqing Zheng, Xuanjing Huang
To overcome these limitations, we propose a novel jailbreaking approach, named Jailbreaking LLMs through Representation Engineering (JRE).
1 code implementation • 11 Jan 2024 • Binghai Wang, Rui Zheng, Lu Chen, Yan Liu, Shihan Dou, Caishuang Huang, Wei Shen, Senjie Jin, Enyu Zhou, Chenyu Shi, Songyang Gao, Nuo Xu, Yuhao Zhou, Xiaoran Fan, Zhiheng Xi, Jun Zhao, Xiao Wang, Tao Ji, Hang Yan, Lixing Shen, Zhan Chen, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang
We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset and fully leverage high-quality preference data.
1 code implementation • 1 Jan 2024 • Junjie Ye, Guanyu Li, Songyang Gao, Caishuang Huang, Yilong Wu, Sixian Li, Xiaoran Fan, Shihan Dou, Qi Zhang, Tao Gui, Xuanjing Huang
Furthermore, a sole emphasis on outcomes disregards the intricate capabilities essential for LLMs to effectively utilize tools.
1 code implementation • 15 Dec 2023 • Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Jun Zhao, Wei Shen, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Xiaoran Fan, ShiLiang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks.
no code implementations • 25 Oct 2023 • Tianlong Li, Shihan Dou, Changze Lv, Wenhao Liu, Jianhan Xu, Muling Wu, Zixuan Ling, Xiaoqing Zheng, Xuanjing Huang
Users can utilize UBPL to adjust the probability vectors of predicted words in the decoding phase of LLMs, thus influencing the personality expression of LLMs.
no code implementations • 18 Oct 2023 • Rui Zheng, Wei Shen, Yuan Hua, Wenbin Lai, Shihan Dou, Yuhao Zhou, Zhiheng Xi, Xiao Wang, Haoran Huang, Tao Gui, Qi Zhang, Xuanjing Huang
In this work, we propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
no code implementations • 8 Oct 2023 • Wei Shen, Rui Zheng, WenYu Zhan, Jun Zhao, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
Reinforcement learning from human feedback serves as a crucial bridge, aligning large language models with human and societal values.
1 code implementation • 14 Sep 2023 • Zhiheng Xi, Wenxiang Chen, Xin Guo, wei he, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, Rui Zheng, Xiaoran Fan, Xiao Wang, Limao Xiong, Yuhao Zhou, Weiran Wang, Changhao Jiang, Yicheng Zou, Xiangyang Liu, Zhangyue Yin, Shihan Dou, Rongxiang Weng, Wensen Cheng, Qi Zhang, Wenjuan Qin, Yongyan Zheng, Xipeng Qiu, Xuanjing Huang, Tao Gui
Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks.
1 code implementation • 11 Jul 2023 • Rui Zheng, Shihan Dou, Songyang Gao, Yuan Hua, Wei Shen, Binghai Wang, Yan Liu, Senjie Jin, Qin Liu, Yuhao Zhou, Limao Xiong, Lu Chen, Zhiheng Xi, Nuo Xu, Wenbin Lai, Minghao Zhu, Cheng Chang, Zhangyue Yin, Rongxiang Weng, Wensen Cheng, Haoran Huang, Tianxiang Sun, Hang Yan, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang
Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.
1 code implementation • 27 Jun 2023 • Songyang Gao, Shihan Dou, Yan Liu, Xiao Wang, Qi Zhang, Zhongyu Wei, Jin Ma, Ying Shan
Adversarial training is one of the best-performing methods in improving the robustness of deep language models.
1 code implementation • 27 Jun 2023 • Songyang Gao, Shihan Dou, Qi Zhang, Xuanjing Huang, Jin Ma, Ying Shan
Detecting adversarial samples that are carefully crafted to fool the model is a critical step to socially-secure applications.
no code implementations • 4 May 2023 • Songyang Gao, Shihan Dou, Junjie Shan, Qi Zhang, Xuanjing Huang
Dataset bias, i. e., the over-reliance on dataset-specific literal heuristics, is getting increasing attention for its detrimental effect on the generalization ability of NLU models.
1 code implementation • 14 Oct 2022 • Songyang Gao, Shihan Dou, Qi Zhang, Xuanjing Huang
Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models.
1 code implementation • International Conference on Software Engineering 2022 • Yueming Wu, Deqing Zou, Shihan Dou, Wei Yang, Duo Xu, Hai Jin
Furthermore, we conduct a case study on more than 25 million lines of code and the result indicates that VulCNN has the ability to detect large-scale vulnerability.
2 code implementations • ACL 2022 • Xiao Wang, Shihan Dou, Limao Xiong, Yicheng Zou, Qi Zhang, Tao Gui, Liang Qiao, Zhanzhan Cheng, Xuanjing Huang
NER model has achieved promising performance on standard NER benchmarks.
Ranked #8 on Named Entity Recognition (NER) on WNUT 2017
2 code implementations • COLING 2022 • Shihan Dou, Rui Zheng, Ting Wu, Songyang Gao, Junjie Shan, Qi Zhang, Yueming Wu, Xuanjing Huang
Most of the existing debiasing methods often identify and weaken these samples with biased features (i. e., superficial surface features that cause such spurious correlations).