Search Results for author: Jinjie Gu

Found 45 papers, 10 papers with code

A Survey on Medical Large Language Models: Technology, Application, Trustworthiness, and Future Directions

no code implementations6 Jun 2024 Lei Liu, Xiaoyan Yang, Junchi Lei, Xiaoyang Liu, Yue Shen, Zhiqiang Zhang, Peng Wei, Jinjie Gu, Zhixuan Chu, Zhan Qin, Kui Ren

This survey provides a comprehensive overview of Medical Large Language Models (Med-LLMs), outlining their evolution from general to the medical-specific domain (i. e, Technology and Application), as well as their transformative impact on healthcare (e. g., Trustworthiness and Safety).


Mitigate Position Bias with Coupled Ranking Bias on CTR Prediction

no code implementations29 May 2024 Yao Zhao, Zhining Liu, Tianchi Cai, Haipeng Zhang, Chenyi Zhuang, Jinjie Gu

Using both synthetic and industrial datasets, we first show how this widely coexisted ranking bias deteriorates the performance of the existing position bias estimation methods.

Click-Through Rate Prediction Position +1

Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential Recommendation

no code implementations22 Mar 2024 Shaowei Wei, Zhengwei Wu, Xin Li, Qintong Wu, Zhiqiang Zhang, Jun Zhou, Lihong Gu, Jinjie Gu

Subsequently, we employ self-distillation to facilitate the transfer of knowledge from users with extensive behaviors (teachers) to users with limited behaviors (students).

Clustering Contrastive Learning +3

Editing Conceptual Knowledge for Large Language Models

1 code implementation10 Mar 2024 Xiaohan Wang, Shengyu Mao, Ningyu Zhang, Shumin Deng, Yunzhi Yao, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Recently, there has been a growing interest in knowledge editing for Large Language Models (LLMs).

knowledge editing

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents

1 code implementation5 Mar 2024 Yuqi Zhu, Shuofei Qiao, Yixin Ou, Shumin Deng, Ningyu Zhang, Shiwei Lyu, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions.

Hallucination Self-Learning

RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoning

no code implementations19 Feb 2024 Congyun Jin, Ming Zhang, Xiaowei Ma, Li Yujiao, Yingbo Wang, Yabo Jia, Yuliang Du, Tao Sun, Haowen Wang, Cong Fan, Jinjie Gu, Chenfei Chi, Xiangguo Lv, Fangzhou Li, Wei Xue, Yiran Huang

Recent advancements in Large Language Models (LLMs) and Large Multi-modal Models (LMMs) have shown potential in various medical applications, such as Intelligent Medical Diagnosis.

document understanding Medical Diagnosis +1

Professional Agents -- Evolving Large Language Models into Autonomous Experts with Human-Level Competencies

no code implementations6 Feb 2024 Zhixuan Chu, Yan Wang, Feng Zhu, Lu Yu, Longfei Li, Jinjie Gu

The advent of large language models (LLMs) such as ChatGPT, PaLM, and GPT-4 has catalyzed remarkable advances in natural language processing, demonstrating human-like language fluency and reasoning capacities.


Unified Hallucination Detection for Multimodal Large Language Models

2 code implementations5 Feb 2024 Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Despite significant strides in multimodal tasks, Multimodal Large Language Models (MLLMs) are plagued by the critical issue of hallucination.


MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts

no code implementations31 Jan 2024 Zhitian Xie, Yinger Zhang, Chenyi Zhuang, Qitao Shi, Zhining Liu, Jinjie Gu, Guannan Zhang

However, the gate's routing mechanism also gives rise to narrow vision: the individual MoE's expert fails to use more samples in learning the allocated sub-task, which in turn limits the MoE to further improve its generalization ability.

OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy

no code implementations19 Jan 2024 Haowen Wang, Tao Sun, Kaixiang Ji, Jian Wang, Cong Fan, Jinjie Gu

We advance the field of Parameter-Efficient Fine-Tuning (PEFT) with our novel multi-adapter method, OrchMoE, which capitalizes on modular skill architecture for enhanced forward transfer in neural networks.

Multi-Task Learning

Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs

3 code implementations9 Jan 2024 Junjie Wang, Dan Yang, Binbin Hu, Yue Shen, Wen Zhang, Jinjie Gu

To stimulate the LLMs' reasoning ability, the chain-of-thought (CoT) prompting method is widely used, but existing methods still have some limitations in our scenario: (1) Previous methods either use simple "Let's think step by step" spells or provide fixed examples in demonstrations without considering compatibility between prompts and concrete questions, making LLMs ineffective when the marketers' demands are abstract and diverse.

Language Modelling Large Language Model

Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy

1 code implementation20 Dec 2023 Yao Zhao, Zhitian Xie, Chen Liang, Chenyi Zhuang, Jinjie Gu

Instead of generating a single token at a time, we propose a Trie-based retrieval and verification mechanism to be able to accept several tokens at a forward step.

Language Modelling Large Language Model +3

RJUA-QA: A Comprehensive QA Dataset for Urology

1 code implementation15 Dec 2023 Shiwei Lyu, Chenfei Chi, Hongbo Cai, Lei Shi, Xiaoyan Yang, Lei Liu, Xiang Chen, Deng Zhao, Zhiqiang Zhang, Xianguo Lyu, Ming Zhang, Fangzhou Li, Xiaowei Ma, Yue Shen, Jinjie Gu, Wei Xue, Yiran Huang

We introduce RJUA-QA, a novel medical dataset for question answering (QA) and reasoning with clinical evidence, contributing to bridge the gap between general large language models (LLMs) and medical-specific LLM applications.

Question Answering

Multiple Instance Learning for Uplift Modeling

no code implementations15 Dec 2023 Yao Zhao, Haipeng Zhang, Shiwei Lyu, Ruiying Jiang, Jinjie Gu, Guannan Zhang

Uplift modeling is widely used in performance marketing to estimate effects of promotion campaigns (e. g., increase of customer retention rate).

Marketing Multiple Instance Learning

GreenFlow: A Computation Allocation Framework for Building Environmentally Sound Recommendation System

no code implementations15 Dec 2023 Xingyu Lu, Zhining Liu, Yanchu Guan, Hongxuan Zhang, Chenyi Zhuang, Wenqi Ma, Yize Tan, Jinjie Gu, Guannan Zhang

of a cascade RS, when a user triggers a request, we define two actions that determine the computation: (1) the trained instances of models with different computational complexity; and (2) the number of items to be inferred in the stage.

Recommendation Systems

Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup

no code implementations10 Dec 2023 Maolin Wang, Yao Zhao, Jiajia Liu, Jingdong Chen, Chenyi Zhuang, Jinjie Gu, Ruocheng Guo, Xiangyu Zhao

In our research, we constructed a dataset, the Multimodal Advertisement Audition Dataset (MAAD), from real-world scenarios within Alipay, and conducted experiments to validate the reliability of our proposed strategy.

Model Compression

Making Large Language Models Better Knowledge Miners for Online Marketing with Progressive Prompting Augmentation

no code implementations8 Dec 2023 Chunjing Gan, Dan Yang, Binbin Hu, Ziqi Liu, Yue Shen, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Guannan Zhang

In this paper, we seek to carefully prompt a Large Language Model (LLM) with domain-level knowledge as a better marketing-oriented knowledge miner for marketing-oriented knowledge graph construction, which is however non-trivial, suffering from several inevitable issues in real-world marketing scenarios, i. e., uncontrollable relation generation of LLMs, insufficient prompting ability of a single prompt, the unaffordable deployment cost of LLMs.

graph construction Language Modelling +3

Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning

no code implementations6 Dec 2023 Haowen Wang, Tao Sun, Cong Fan, Jinjie Gu

Modular and composable transfer learning is an emerging direction in the field of Parameter Efficient Fine-Tuning, as it enables neural networks to better organize various aspects of knowledge, leading to improved cross-task generalization.

Multi-Task Learning

ULMA: Unified Language Model Alignment with Human Demonstration and Point-wise Preference

1 code implementation5 Dec 2023 Tianchi Cai, Xierui Song, Jiyan Jiang, Fei Teng, Jinjie Gu, Guannan Zhang

Aligning language models to human expectations, e. g., being helpful and harmless, has become a pressing challenge for large language models.

Language Modelling Large Language Model

Intelligent Virtual Assistants with LLM-based Process Automation

no code implementations4 Dec 2023 Yanchu Guan, Dong Wang, Zhixuan Chu, Shiyu Wang, Feiyue Ni, Ruihua Song, Longfei Li, Jinjie Gu, Chenyi Zhuang

This paper proposes a novel LLM-based virtual assistant that can automatically perform multi-step operations within mobile apps based on high-level user requests.

Language Modelling Large Language Model

From Beginner to Expert: Modeling Medical Knowledge into General LLMs

no code implementations2 Dec 2023 Qiang Li, Xiaoyan Yang, Haowen Wang, Qin Wang, Lei Liu, Junjie Wang, Yang Zhang, Mingyuan Chu, Sen Hu, Yicheng Chen, Yue Shen, Cong Fan, Wangshu Zhang, Teng Xu, Jinjie Gu, Jing Zheng, Guannan Zhang Ant Group

(3) Specifically for multi-choice questions in the medical domain, we propose a novel Verification-of-Choice approach for prompting engineering, which significantly enhances the reasoning ability of LLMs.

Language Modelling Large Language Model +3

Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory

no code implementations15 Nov 2023 Lei Liu, Xiaoyan Yang, Yue Shen, Binbin Hu, Zhiqiang Zhang, Jinjie Gu, Guannan Zhang

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable performance in long-term human-machine interactions, which basically relies on iterative recalling and reasoning of history to generate high-quality responses.

Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster

1 code implementation14 Nov 2023 Hongxuan Zhang, Zhining Liu, Yao Zhao, Jiaqi Zheng, Chenyi Zhuang, Jinjie Gu, Guihai Chen

In this work, we propose FastCoT, a model-agnostic framework based on parallel decoding without any further training of an auxiliary model or modification to the LLM itself.


Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning

no code implementations6 Sep 2023 Tianchi Cai, Jiyan Jiang, Wenpeng Zhang, Shiji Zhou, Xierui Song, Li Yu, Lihong Gu, Xiaodong Zeng, Jinjie Gu, Guannan Zhang

We further show that this method is guaranteed to converge to the optimal policy, which cannot be achieved by previous value-based reinforcement learning methods for marketing budget allocation.

Marketing reinforcement-learning

Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems

no code implementations25 Aug 2023 Tianchi Cai, Shenliao Bao, Jiyan Jiang, Shiji Zhou, Wenpeng Zhang, Lihong Gu, Jinjie Gu, Guannan Zhang

Model-free RL-based recommender systems have recently received increasing research attention due to their capability to handle partial feedback and long-term rewards.

Recommendation Systems reinforcement-learning

Who Would be Interested in Services? An Entity Graph Learning System for User Targeting

no code implementations30 May 2023 Dan Yang, Binbin Hu, Xiaoyan Yang, Yue Shen, Zhiqiang Zhang, Jinjie Gu, Guannan Zhang

At the online stage, the system offers the ability of user targeting in real-time based on the entity graph from the offline stage.

graph construction Graph Learning

Generalized Consistent Multi-Class Classification with Rejection to be Compatible with Arbitrary Losses

2 code implementations Conference 2022 Yuzhou Cao, Tianchi Cai, Lei Feng, Lihong Gu, Jinjie Gu, Bo An, Gang Niu, Masashi Sugiyama

\emph{Classification with rejection} (CwR) refrains from making a prediction to avoid critical misclassification when encountering test samples that are difficult to classify.

Classification Multi-class Classification

Adversarial Learning for Incentive Optimization in Mobile Payment Marketing

no code implementations28 Dec 2021 Xuanying Chen, Zhining Liu, Li Yu, Sen Li, Lihong Gu, Xiaodong Zeng, Yize Tan, Jinjie Gu

This bias deteriorates the performance of the response model and misleads the linear programming process, dramatically degrading the performance of the resulting allocation policy.


Asynchronous Decentralized Online Learning

no code implementations NeurIPS 2021 Jiyan Jiang, Wenpeng Zhang, Jinjie Gu, Wenwu Zhu

To overcome this problem, we study decentralized online learning in the asynchronous setting, which allows different learners to work at their own pace.

A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning

no code implementations29 Aug 2021 Tianchi Cai, Wenpeng Zhang, Lihong Gu, Xiaodong Zeng, Jinjie Gu

To apply value-based methods to CRL, a recent groundbreaking line of game-theoretic approaches uses the mixed policy that randomizes among a set of carefully generated policies to converge to the desired constraint-satisfying policy.

General Reinforcement Learning reinforcement-learning +1

A framework for massive scale personalized promotion

no code implementations27 Aug 2021 Yitao Shen, Yue Wang, Xingyu Lu, Feng Qi, Jia Yan, Yixiang Mu, Yao Yang, Yifan Peng, Jinjie Gu

In order to do effective optimization in the second stage, counterfactual prediction and noise-reduction are essential for the first stage.


Adaptive Optimizers with Sparse Group Lasso for Neural Networks in CTR Prediction

1 code implementation30 Jul 2021 Yun Yue, Yongchao Liu, Suo Tong, Minghao Li, Zhen Zhang, Chunyang Wen, Huanjun Bao, Lihong Gu, Jinjie Gu, Yixiang Mu

We develop a novel framework that adds the regularizers of the sparse group lasso to a family of adaptive optimizers in deep learning, such as Momentum, Adagrad, Adam, AMSGrad, AdaHessian, and create a new class of optimizers, which are named Group Momentum, Group Adagrad, Group Adam, Group AMSGrad and Group AdaHessian, etc., accordingly.

Click-Through Rate Prediction

Graph Neural Network Based VC Investment Success Prediction

no code implementations25 May 2021 Shiwei Lyu, Shuai Ling, Kaihao Guo, Haipeng Zhang, Kunpeng Zhang, Suting Hong, Qing Ke, Jinjie Gu

Predicting the start-ups that will eventually succeed is essentially important for the venture capital business and worldwide policy makers, especially at an early stage such that rewards can possibly be exponential.

Graph Neural Network Representation Learning

LinkLouvain: Link-Aware A/B Testing and Its Application on Online Marketing Campaign

no code implementations3 Feb 2021 Tianchi Cai, Daxi Cheng, Chen Liang, Ziqi Liu, Lihong Gu, Huizhi Xie, Zhiqiang Zhang, Xiaodong Zeng, Jinjie Gu

In this paper, we analyze the network A/B testing problem under a real-world online marketing campaign, describe our proposed LinkLouvain method, and evaluate it on real-world data.

Link Prediction Marketing

A Reduction Approach to Constrained Reinforcement Learning

no code implementations1 Jan 2021 Tianchi Cai, Wenjie Shi, Lihong Gu, Xiaodong Zeng, Jinjie Gu

In this paper, we present a reduction approach to find sparse policies that randomize among a constant number of policies for the constrained RL problem.

reinforcement-learning Reinforcement Learning (RL)

Adaptive Optimizers with Sparse Group Lasso

no code implementations1 Jan 2021 Yun Yue, Suo Tong, Zhen Zhang, Yongchao Liu, Chunyang Wen, Huanjun Bao, Jinjie Gu, Yixiang Mu

We develop a novel framework that adds the regularizers to a family of adaptive optimizers in deep learning, such as MOMENTUM, ADAGRAD, ADAM, AMSGRAD, ADAHESSIAN, and create a new class of optimizers, which are named GROUP MOMENTUM, GROUP ADAGRAD, GROUP ADAM, GROUP AMSGRAD and GROUP ADAHESSIAN, etc., accordingly.

Robust Offline Reinforcement Learning from Low-Quality Data

no code implementations1 Jan 2021 Wenjie Shi, Tianchi Cai, Shiji Song, Lihong Gu, Jinjie Gu, Gao Huang

We theoretically show that AdaPT produces a tight upper bound on the distributional deviation between the learned policy and the behavior policy, and this upper bound is the minimum requirement to guarantee policy improvement at each iteration.

Continuous Control Offline RL +2

Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing

no code implementations27 Feb 2020 Ziqi Liu, Dong Wang, Qianyu Yu, Zhiqiang Zhang, Yue Shen, Jian Ma, Wenliang Zhong, Jinjie Gu, Jun Zhou, Shuang Yang, Yuan Qi

In this paper, we present a graph representation learning method atop of transaction networks for merchant incentive optimization in mobile payment marketing.

Graph Representation Learning Marketing

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