Search Results for author: Ganqu Cui

Found 21 papers, 18 papers with code

Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models

no code implementations13 Mar 2024 Ning Ding, Yulin Chen, Ganqu Cui, Xingtai Lv, Weilin Zhao, Ruobing Xie, BoWen Zhou, Zhiyuan Liu, Maosong Sun

Underlying data distributions of natural language, programming code, and mathematical symbols vary vastly, presenting a complex challenge for large language models (LLMs) that strive to achieve high performance across all three domains simultaneously.


Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment

1 code implementation29 Feb 2024 Yiju Guo, Ganqu Cui, Lifan Yuan, Ning Ding, Jiexin Wang, Huimin Chen, Bowen Sun, Ruobing Xie, Jie zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun

In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment tax" -a compromise where enhancements in alignment within one objective (e. g., harmlessness) can diminish performance in others (e. g., helpfulness).


RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

3 code implementations1 Dec 2023 Tianyu Yu, Yuan YAO, Haoye Zhang, Taiwen He, Yifeng Han, Ganqu Cui, Jinyi Hu, Zhiyuan Liu, Hai-Tao Zheng, Maosong Sun, Tat-Seng Chua

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in multimodal understanding, reasoning, and interaction.


INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair

1 code implementation16 Nov 2023 Hanbin Wang, Zhenghao Liu, Shuo Wang, Ganqu Cui, Ning Ding, Zhiyuan Liu, Ge Yu

INTERVENOR prompts Large Language Models (LLMs) to play distinct roles during the code repair process, functioning as both a Code Learner and a Code Teacher.

Code Repair Code Translation

UltraFeedback: Boosting Language Models with High-quality Feedback

2 code implementations2 Oct 2023 Ganqu Cui, Lifan Yuan, Ning Ding, Guanming Yao, Wei Zhu, Yuan Ni, Guotong Xie, Zhiyuan Liu, Maosong Sun

However, the scarcity of diverse, naturalistic datasets of human preferences on LLM outputs at scale poses a great challenge to RLHF as well as feedback learning research within the open-source community.

Language Modelling

From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework

1 code implementation29 May 2023 Yangyi Chen, Hongcheng Gao, Ganqu Cui, Lifan Yuan, Dehan Kong, Hanlu Wu, Ning Shi, Bo Yuan, Longtao Huang, Hui Xue, Zhiyuan Liu, Maosong Sun, Heng Ji

In our experiments, we conduct a robustness evaluation of RoBERTa models to demonstrate the effectiveness of our evaluation framework, and further show the rationality of each component in the framework.

Adversarial Attack

Decoder Tuning: Efficient Language Understanding as Decoding

2 code implementations16 Dec 2022 Ganqu Cui, Wentao Li, Ning Ding, Longtao Huang, Zhiyuan Liu, Maosong Sun

With the evergrowing sizes of pre-trained models (PTMs), it has been an emerging practice to only provide the inference APIs for users, namely model-as-a-service (MaaS) setting.

Decoder Natural Language Understanding

Few-shot Classification with Hypersphere Modeling of Prototypes

no code implementations10 Nov 2022 Ning Ding, Yulin Chen, Ganqu Cui, Xiaobin Wang, Hai-Tao Zheng, Zhiyuan Liu, Pengjun Xie

Moreover, it is more convenient to perform metric-based classification with hypersphere prototypes than statistical modeling, as we only need to calculate the distance from a data point to the surface of the hypersphere.

Classification Few-Shot Learning +1

A Close Look into the Calibration of Pre-trained Language Models

2 code implementations31 Oct 2022 Yangyi Chen, Lifan Yuan, Ganqu Cui, Zhiyuan Liu, Heng Ji

We observe a consistent change in calibration performance across six factors.

Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP

1 code implementation19 Oct 2022 Yangyi Chen, Hongcheng Gao, Ganqu Cui, Fanchao Qi, Longtao Huang, Zhiyuan Liu, Maosong Sun

We discuss the deficiencies in previous work and propose our suggestions that the research on the Security-oriented adversarial NLP (SoadNLP) should: (1) evaluate their methods on security tasks to demonstrate the real-world concerns; (2) consider real-world attackers' goals, instead of developing impractical methods.

Data Augmentation

A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks

1 code implementation17 Jun 2022 Ganqu Cui, Lifan Yuan, Bingxiang He, Yangyi Chen, Zhiyuan Liu, Maosong Sun

However, we highlight two issues in previous backdoor learning evaluations: (1) The differences between real-world scenarios (e. g. releasing poisoned datasets or models) are neglected, and we argue that each scenario has its own constraints and concerns, thus requires specific evaluation protocols; (2) The evaluation metrics only consider whether the attacks could flip the models' predictions on poisoned samples and retain performances on benign samples, but ignore that poisoned samples should also be stealthy and semantic-preserving.

text similarity

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm

1 code implementation Findings (NAACL) 2022 Lei Xu, Yangyi Chen, Ganqu Cui, Hongcheng Gao, Zhiyuan Liu

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting.

Prototypical Verbalizer for Prompt-based Few-shot Tuning

1 code implementation ACL 2022 Ganqu Cui, Shengding Hu, Ning Ding, Longtao Huang, Zhiyuan Liu

However, manual verbalizers heavily depend on domain-specific prior knowledge and human efforts, while finding appropriate label words automatically still remains challenging. In this work, we propose the prototypical verbalizer (ProtoVerb) which is built directly from training data.

Contrastive Learning Entity Typing +2

Evaluating Modules in Graph Contrastive Learning

1 code implementation15 Jun 2021 Ganqu Cui, Yufeng Du, Cheng Yang, Jie zhou, Liang Xu, Xing Zhou, Xingyi Cheng, Zhiyuan Liu

The recent emergence of contrastive learning approaches facilitates the application on graph representation learning (GRL), introducing graph contrastive learning (GCL) into the literature.

Contrastive Learning Graph Classification +1

Adaptive Graph Encoder for Attributed Graph Embedding

1 code implementation3 Jul 2020 Ganqu Cui, Jie zhou, Cheng Yang, Zhiyuan Liu

Experimental results show that AGE consistently outperforms state-of-the-art graph embedding methods considerably on these tasks.

Clustering Graph Embedding +2

Graph Neural Networks: A Review of Methods and Applications

5 code implementations20 Dec 2018 Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, LiFeng Wang, Changcheng Li, Maosong Sun

Lots of learning tasks require dealing with graph data which contains rich relation information among elements.

Graph Attention

Cannot find the paper you are looking for? You can Submit a new open access paper.