Search Results for author: Siyuan Wang

Found 42 papers, 25 papers with code

A Structure-Aware Argument Encoder for Literature Discourse Analysis

1 code implementation COLING 2022 Yinzi Li, Wei Chen, Zhongyu Wei, Yujun Huang, Chujun Wang, Siyuan Wang, Qi Zhang, Xuanjing Huang, Libo Wu

Existing research for argument representation learning mainly treats tokens in the sentence equally and ignores the implied structure information of argumentative context.

Position Representation Learning +1

Analytical Reasoning of Text

1 code implementation Findings (NAACL) 2022 Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Yining Chen, Jiahai Wang, Jian Yin, Ming Zhou, Nan Duan

In this paper, we study the challenge of analytical reasoning of text and collect a new dataset consisting of questions from the Law School Admission Test from 1991 to 2016.

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking

no code implementations21 Jun 2024 Siyuan Wang, Zhuohan Long, Zhihao Fan, Zhongyu Wei

The rapid development of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) has exposed vulnerabilities to various adversarial attacks.

ALaRM: Align Language Models via Hierarchical Rewards Modeling

1 code implementation11 Mar 2024 Yuhang Lai, Siyuan Wang, Shujun Liu, Xuanjing Huang, Zhongyu Wei

We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences.

Long Form Question Answering Machine Translation +1

Aligning Large Language Models to a Domain-specific Graph Database

no code implementations26 Feb 2024 Yuanyuan Liang, Keren Tan, Tingyu Xie, Wenbiao Tao, Siyuan Wang, Yunshi Lan, Weining Qian

Graph Databases (Graph DB) are widely applied in various fields, including finance, social networks, and medicine.

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs

1 code implementation18 Feb 2024 Siyuan Wang, Zhongyu Wei, Yejin Choi, Xiang Ren

Our analysis of GPT-series models over a rule subset reveals significant gaps in LLMs' logic understanding compared to human performance, especially in compositional and structural complex rules with certain bias patterns.

Logical Reasoning

Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation

1 code implementation18 Feb 2024 Siyuan Wang, Zhuohan Long, Zhihao Fan, Zhongyu Wei, Xuanjing Huang

Towards a more scalable, robust and fine-grained evaluation, we implement six reframing operations to construct evolving instances testing LLMs against diverse queries, data noise and probing their problem-solving sub-abilities.

Model Selection

AI Hospital: Interactive Evaluation and Collaboration of LLMs as Intern Doctors for Clinical Diagnosis

1 code implementation15 Feb 2024 Zhihao Fan, Jialong Tang, Wei Chen, Siyuan Wang, Zhongyu Wei, Jun Xi, Fei Huang, Jingren Zhou

To simulate the procedure, we collect high-quality medical records to create patient, examiner, and medical director agents.

Question Answering

Content-Conditioned Generation of Stylized Free hand Sketches

no code implementations9 Jan 2024 Jiajun Liu, Siyuan Wang, Guangming Zhu, Liang Zhang, Ning li, Eryang Gao

We explore the performance of the model, including using styles randomly sampled from a prior normal distribution to generate images with various free-hand sketching styles, disentangling the painters' styles from known free-hand sketches to generate images with specific styles, and generating images of unknown classes that are not in the training set.

Data Augmentation Image Generation

Diff-Oracle: Diffusion Model for Oracle Character Generation with Controllable Styles and Contents

no code implementations21 Dec 2023 Jing Li, Qiu-Feng Wang, Kaizhu Huang, Rui Zhang, Siyuan Wang

To train Diff-Oracle effectively, we propose to obtain pixel-level paired oracle character images (i. e., style and content images) by a pre-trained image-to-image translation model.

Image-to-Image Translation

Enhance Sketch Recognition's Explainability via Semantic Component-Level Parsing

1 code implementation13 Dec 2023 Guangming Zhu, Siyuan Wang, Tianci Wu, Liang Zhang

Humans can recognize varied sketches of a category easily by identifying the concurrence and layout of the intrinsic semantic components of the category, since humans draw free-hand sketches based a common consensus that which types of semantic components constitute each sketch category.

Sketch Recognition

Sketch Input Method Editor: A Comprehensive Dataset and Methodology for Systematic Input Recognition

1 code implementation30 Nov 2023 Guangming Zhu, Siyuan Wang, Qing Cheng, Kelong Wu, Hao Li, Liang Zhang

With the recent surge in the use of touchscreen devices, free-hand sketching has emerged as a promising modality for human-computer interaction.

Class Incremental Learning Domain Adaptation +2

In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search

1 code implementation13 Nov 2023 Huihan Li, Yuting Ning, Zeyi Liao, Siyuan Wang, Xiang Lorraine Li, Ximing Lu, Wenting Zhao, Faeze Brahman, Yejin Choi, Xiang Ren

We further use the data generated by LINK to construct a dataset Logic-Induced-Long-Tail (LINT) that can be used to evaluate downstream models on the long-tail distribution; LINT contains 108K knowledge statements spanning four domains.

Language Modelling Natural Language Inference +1

DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services

2 code implementations20 Sep 2023 Shengbin Yue, Wei Chen, Siyuan Wang, Bingxuan Li, Chenchen Shen, Shujun Liu, Yuxuan Zhou, Yao Xiao, Song Yun, Xuanjing Huang, Zhongyu Wei

We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services.

Legal Reasoning Retrieval

A Dynamic Equivalent Energy Storage Model of Natural Gas Networks for Joint Optimal Dispatch of Electricity-Gas Systems

no code implementations24 Jul 2023 Siyuan Wang, Wenchuan Wu, Chenhui Lin, Binbin Chen

The development of energy conversion techniques enhances the coupling between the gas network and power system.

DistilXLSR: A Light Weight Cross-Lingual Speech Representation Model

1 code implementation2 Jun 2023 Haoyu Wang, Siyuan Wang, Wei-Qiang Zhang, Jinfeng Bai

Multilingual self-supervised speech representation models have greatly enhanced the speech recognition performance for low-resource languages, and the compression of these huge models has also become a crucial prerequisite for their industrial application.

speech-recognition Speech Recognition

Task-Agnostic Structured Pruning of Speech Representation Models

no code implementations2 Jun 2023 Haoyu Wang, Siyuan Wang, Wei-Qiang Zhang, Hongbin Suo, Yulong Wan

Self-supervised pre-trained models such as Wav2vec2, Hubert, and WavLM have been shown to significantly improve many speech tasks.

Model Compression

Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs

1 code implementation23 May 2023 Siyuan Wang, Zhongyu Wei, Meng Han, Zhihao Fan, Haijun Shan, Qi Zhang, Xuanjing Huang

The results demonstrate the effectiveness of our method on logical reasoning over KGs in both inductive and transductive settings.

Knowledge Graphs Logical Reasoning

MsPrompt: Multi-step Prompt Learning for Debiasing Few-shot Event Detection

no code implementations16 May 2023 Siyuan Wang, Jianming Zheng, Xuejun Hu, Fei Cai, Chengyu Song, Xueshan Luo

Event detection (ED) is aimed to identify the key trigger words in unstructured text and predict the event types accordingly.

Event Detection

Deep Reinforcement Learning Based Vehicle Selection for Asynchronous Federated Learning Enabled Vehicular Edge Computing

no code implementations6 Apr 2023 Qiong Wu, Siyuan Wang, Pingyi Fan, Qiang Fan

Furthermore, as vehicles have different local training time due to various sizes of local data and their different computing capabilities, asynchronous federated learning (AFL) is employed to facilitate the RSU to update the global model immediately after receiving a local model to reduce the aggregation delay.

Edge-computing Federated Learning

Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning

no code implementations21 Jan 2023 Siyuan Wang, Zhongyu Wei, Jiarong Xu, Taishan Li, Zhihao Fan

Recent pre-trained language models (PLMs) equipped with foundation reasoning skills have shown remarkable performance on downstream complex tasks.

Language Modelling Logical Reasoning

Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering

1 code implementation COLING 2022 Siyuan Wang, Zhongyu Wei, Zhihao Fan, Qi Zhang, Xuanjing Huang

In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result.

Multi-hop Question Answering Question Answering +3

Asynchronous Federated Learning for Edge-assisted Vehicular Networks

1 code implementation3 Aug 2022 Siyuan Wang, Qiong Wu, Qiang Fan, Pingyi Fan, Jiangzhou Wang

For the traditional federated learning (FL), vehicles train the data locally to obtain a local model and then upload the local model to the RSU to update the global model, thus the data privacy can be protected through sharing model parameters instead of data.

Federated Learning

Multi-parametric Analysis for Mixed Integer Linear Programming: An Application to Transmission Planning and Congestion Control

no code implementations19 Jul 2022 Jian Liu, Rui Bo, Siyuan Wang

Finally, the amount of capacity upgrade will be chosen by balancing the cost-reduction rate of the objective function on parameters and the cost of the line upgrade.

Decision Making

Diverse Dance Synthesis via Keyframes with Transformer Controllers

1 code implementation13 Jul 2022 Junjun Pan, Siyuan Wang, Junxuan Bai, Ju Dai

The video and qualitative experimental results demonstrate that the complex motion sequences generated by our algorithm can achieve diverse and smooth motion transitions between keyframes, even for long-term synthesis.

Motion Synthesis

Reasoning Chain Based Adversarial Attack for Multi-hop Question Answering

no code implementations17 Dec 2021 Jiayu Ding, Siyuan Wang, Qin Chen, Zhongyu Wei

The results demonstrate significant performance reduction on both answer and supporting facts prediction, verifying the effectiveness of our reasoning chain based attack method for multi-hop reasoning models and the vulnerability of them.

Adversarial Attack Multi-hop Question Answering +2

Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval

1 code implementation Findings (NAACL) 2022 Zhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Jianqing Fan

We propose our TAiloring neGative Sentences with Discrimination and Correction (TAGS-DC) to generate synthetic sentences automatically as negative samples.

Retrieval Sentence +1

Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval

no code implementations12 Sep 2021 Zhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Haijun Shan, Xuanjing Huang, Jianqing Fan

Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image.

Representation Learning Retrieval +2

TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning

no code implementations21 Jun 2021 Zhihao Fan, Zhongyu Wei, Siyuan Wang, Ruize Wang, Zejun Li, Haijun Shan, Xuanjing Huang

Considering that theme concepts can be learned from both images and captions, we propose two settings for their representations learning based on TTN.

Decoder Image Captioning +1

AR-LSAT: Investigating Analytical Reasoning of Text

1 code implementation14 Apr 2021 Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Jiahai Wang, Jian Yin, Ming Zhou, Nan Duan

Analytical reasoning is an essential and challenging task that requires a system to analyze a scenario involving a set of particular circumstances and perform reasoning over it to make conclusions.

Denoising Auto-encoding Priors in Undecimated Wavelet Domain for MR Image Reconstruction

1 code implementation3 Sep 2019 Siyuan Wang, Junjie Lv, Yuanyuan Hu, Dong Liang, Minghui Zhang, Qiegen Liu

At the stage of prior learning, transformed feature images obtained by undecimated wavelet transform are stacked as an input of denoising autoencoder network (DAE).

Compressive Sensing Denoising +1

Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning

1 code implementation ACL 2019 Zhihao Fan, Zhongyu Wei, Siyuan Wang, Xuanjing Huang

Existing research usually employs the architecture of CNN-RNN that views the generation as a sequential decision-making process and the entire dataset vocabulary is used as decoding space.

Decision Making Image Captioning

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