Author name cluster

Jindong Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

ICLR Conference 2025 Conference Paper

Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection

Yun Zhu
Jia-Chen Gu
Caitlin Sikora
Ho Ko
Yinxiao Liu
Chu-Cheng Lin
Lei Shu 0004
Liangchen Luo

Large language models (LLMs) augmented with retrieval exhibit robust performance and extensive versatility by incorporating external contexts. However, the input length grows linearly in the number of retrieved documents, causing a dramatic increase in latency. In this paper, we propose a novel paradigm named Sparse RAG, which seeks to cut computation costs through sparsity. Speciﬁcally, Sparse RAG encodes retrieved documents in parallel, which eliminates latency introduced by long-range attention of retrieved documents. Then, LLMs selectively decode the output by only attending to highly relevant caches auto-regressively, which are chosen via prompting LLMs with special control tokens. It is notable that Sparse RAG combines the assessment of each individual document and the generation of the response into a single process. The designed sparse mechanism in a RAG system can facilitate the reduction of the number of documents loaded during decoding for accelerating the inference of the RAG system. Additionally, ﬁltering out undesirable contexts enhances the model’s focus on relevant context, inherently improving its generation quality. Evaluation results on four datasets show that Sparse RAG can be used to strike an optimal balance between generation quality and computational efﬁciency, demonstrating its generalizability across tasks.

Details

AAAI Conference 2024 Conference Paper

RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting

Lei Shu
Liangchen Luo
Jayakumar Hoskere
Yun Zhu
Yinxiao Liu
Simon Tong
Jindong Chen
Lei Meng

Large Language Models (LLMs) have demonstrated impressive capabilities in creative tasks such as storytelling and E-mail generation. However, as LLMs are primarily trained on final text results rather than intermediate revisions, it might be challenging for them to perform text rewriting tasks. Most studies in the rewriting tasks focus on a particular transformation type within the boundaries of single sentences. In this work, we develop new strategies for instruction tuning and reinforcement learning to better align LLMs for cross-sentence rewriting tasks using diverse wording and structures expressed through natural languages including 1) generating rewriting instruction data from Wiki edits and public corpus through instruction generation and chain-of-thought prompting; 2) collecting comparison data for reward model training through a new ranking function. To facilitate this research, we introduce OpenRewriteEval, a novel benchmark covers a wide variety of rewriting types expressed through natural language instructions. Our results show significant improvements over a variety of baselines.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

ScreenAI: A Vision-Language Model for UI and Infographics Understanding

Gilles Baechler
Srinivas Sunkara
Maria Wang
Fedir Zubach
Hassan Mansoor
Vincent Etter
Victor Carbune
Jason Lin

Screen user interfaces (UIs) and infographics, sharing similar visual language and design principles, play important roles in human communication and human-machine interaction. We introduce ScreenAI, a vision-language model that specializes in UI and infographics understanding. Our model improves upon the PaLI architecture with the flexible patching strategy of pix2struct and is trained on a unique mixture of datasets. At the heart of this mixture is a novel screen annotation task in which the model has to identify the type and location of UI elements. We use these text annotations to describe screens to Large Language Models and automatically generate question-answering (QA), UI navigation, and summarization training datasets at scale. We run ablation studies to demonstrate the impact of these design choices. At only 5B parameters, ScreenAI achieves new state-of-the-art results on UI- and infographics-based tasks (Multipage DocVQA, WebSRC, and MoTIF), and new best-in-class performance on others (ChartQA, DocVQA, and InfographicVQA) compared to models of similar size. Finally, we release three new datasets: one focused on the screen annotation task and two others focused on question answering.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer

Bowen Tan
Yun Zhu
Lijuan Liu
Eric Xing
Zhiting Hu
Jindong Chen

Large language models (LLMs) such as T0, FLAN, and OPT-IML excel in multi-tasking under a unified instruction-following paradigm, where they also exhibit remarkable generalization abilities to unseen tasks. Despite their impressive performance, these LLMs, with sizes ranging from several billion to hundreds of billions of parameters, demand substantial computational resources, making their training and inference expensive and inefficient. Furthermore, adapting these models to downstream applications, particularly complex tasks, is often unfeasible due to the extensive hardware requirements for finetuning, even when utilizing parameter-efficient approaches such as prompt tuning. Additionally, the most powerful multi-task LLMs, such as OPT-IML-175B and FLAN-PaLM-540B, are not publicly accessible, severely limiting their customization potential. To address these challenges, we introduce a pretrained small scorer, \textit{Cappy}, designed to enhance the performance and efficiency of multi-task LLMs. With merely 360 million parameters, Cappy functions either independently on classification tasks or serve as an auxiliary component for LLMs, boosting their performance. Moreover, Cappy enables efficiently integrating downstream supervision without requiring LLM finetuning nor the access to their parameters. Our experiments demonstrate that, when working independently on 11 language understanding tasks from PromptSource, Cappy outperforms LLMs that are several orders of magnitude larger. Besides, on 45 complex tasks from BIG-Bench, Cappy boosts the performance of the advanced multi-task LLM, FLAN-T5, by a large margin. Furthermore, Cappy is flexible to cooperate with other LLM adaptations, including finetuning and in-context learning, offering additional performance enhancement.

PDF Details

AAAI Conference 2021 Conference Paper

ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces

Zecheng He
Srinivas Sunkara
Xiaoxue Zang
Ying Xu
Lijuan Liu
Nevan Wichers
Gabriel Schubiner
Ruby Lee

As mobile devices are becoming ubiquitous, regularly interacting with a variety of user interfaces (UIs) is a common aspect of daily life for many people. To improve the accessibility of these devices and to enable their usage in a variety of settings, building models that can assist users and accomplish tasks through the UI is vitally important. However, there are several challenges to achieve this. First, UI components of similar appearance can have different functionalities, making understanding their function more important than just analyzing their appearance. Second, domain-specific features like Document Object Model (DOM) in web pages and View Hierarchy (VH) in mobile applications provide important signals about the semantics of UI elements, but these features are not in a natural language format. Third, owing to a large diversity in UIs and absence of standard DOM or VH representations, building a UI understanding model with high coverage requires large amounts of training data. Inspired by the success of pre-training based approaches in NLP for tackling a variety of problems in a data-efficient way, we introduce a new pre-trained UI representation model called ActionBert. Our methodology is designed to leverage visual, linguistic and domain-specific features in user interaction traces to pre-train generic feature representations of UIs and their components. Our key intuition is that user actions, e. g. , a sequence of clicks on different UI components, reveals important information about their functionality. We evaluate the proposed model on a wide variety of downstream tasks, ranging from icon classification to UI component retrieval based on its natural language description. Experiments show that the proposed ActionBert model outperforms multi-modal baselines across all downstream tasks by up to 15. 5%.

PDF Details

IJCAI Conference 2021 Conference Paper

UIBert: Learning Generic Multimodal Representations for UI Understanding

Chongyang Bai
Xiaoxue Zang
Ying Xu
Srinivas Sunkara
Abhinav Rastogi
Jindong Chen
Blaise Agüera y Arcas

To improve the accessibility of smart devices and to simplify their usage, building models which understand user interfaces (UIs) and assist users to complete their tasks is critical. However, unique challenges are proposed by UI-specific characteristics, such as how to effectively leverage multimodal UI features that involve image, text, and structural metadata and how to achieve good performance when high-quality labeled data is unavailable. To address such challenges we introduce UIBert, a transformer-based joint image-text model trained through novel pre-training tasks on large-scale unlabeled UI data to learn generic feature representations for a UI and its components. Our key intuition is that the heterogeneous features in a UI are self-aligned, i. e. , the image and text features of UI components, are predictive of each other. We propose five pretraining tasks utilizing this self-alignment among different features of a UI component and across various components in the same UI. We evaluate our method on nine real-world downstream UI tasks where UIBert outperforms strong multimodal baselines by up to 9. 26% accuracy.

PDF Details DOI

AAAI Conference 2019 Conference Paper

Deep Short Text Classification with Knowledge Powered Attention

Jindong Chen
Yizhou Hu
Jingping Liu
Yanghua Xiao
Haiyun Jiang

Short text classification is one of important tasks in Natural Language Processing (NLP). Unlike paragraphs or documents, short texts are more ambiguous since they have not enough contextual information, which poses a great challenge for classification. In this paper, we retrieve knowledge from external knowledge source to enhance the semantic representation of short texts. We take conceptual information as a kind of knowledge and incorporate it into deep neural networks. For the purpose of measuring the importance of knowledge, we introduce attention mechanisms and propose deep Short Text Classification with Knowledge powered Attention (STCKA). We utilize Concept towards Short Text (C- ST) attention and Concept towards Concept Set (C-CS) attention to acquire the weight of concepts from two aspects. And we classify a short text with the help of conceptual information. Unlike traditional approaches, our model acts like a human being who has intrinsic ability to make decisions based on observation (i. e. , training data for machines) and pays more attention to important knowledge. We also conduct extensive experiments on four public datasets for different tasks. The experimental results and case studies show that our model outperforms the state-of-the-art methods, justifying the effectiveness of knowledge powered attention.

PDF Details

IJCAI Conference 2019 Conference Paper

Relation Extraction Using Supervision from Topic Knowledge of Relation Labels

Haiyun Jiang
Li Cui
Zhe Xu
Deqing Yang
Jindong Chen
Chenguang Li
Jingping Liu
Jiaqing Liang

Explicitly exploring the semantics of a relation is significant for high-accuracy relation extraction, which is, however, not fully studied in previous work. In this paper, we mine the topic knowledge of a relation to explicitly represent the semantics of this relation, and model relation extraction as a matching problem. That is, the matching score between a sentence and a candidate relation is predicted for an entity pair. To this end, we propose a deep matching network to precisely model the semantic similarity between a sentence-relation pair. Besides, the topic knowledge also allows us to derive the importance information of samples as well as two knowledge-guided negative sampling strategies in the training process. We conduct extensive experiments to evaluate the proposed framework and observe improvements in AUC of 11. 5% and max F1 of 5. 4% over the baselines with state-of-the-art performance.

PDF Details

YNICL Journal 2015 Journal Article

Three dysconnectivity patterns in treatment-resistant schizophrenia patients and their unaffected siblings

Jicai Wang
Hongbao Cao
Yanhui Liao
Weiqing Liu
Liwen Tan
Yanqing Tang
Jindong Chen
Xiufeng Xu

UNLABELLED: Among individuals diagnosed with schizophrenia, approximately 20%-33% are recognized as treatment-resistant schizophrenia (TRS) patients. These TRS patients suffer more severely from the disease but struggle to benefit from existing antipsychotic treatments. A few recent studies suggested that schizophrenia may be caused by impaired synaptic plasticity that manifests as functional dysconnectivity in the brain, however, few of those studies focused on the functional connectivity changes in the brains of TRS groups. In this study, we compared the whole brain connectivity variations in TRS patients, their unaffected siblings, and healthy controls. Connectivity network features between and within the 116 automated anatomical labeling (AAL) brain regions were calculated and compared using maps created with three contrasts: patient vs. control, patient vs. sibling, and sibling vs. CONTROL: To evaluate the predictive power of the selected features, we performed a multivariate classification approach. We also evaluated the influence of six important clinical measures (e.g. age, education level) on the connectivity features. This study identified abnormal significant connectivity changes of three patterns in TRS patients and their unaffected siblings: 1) 69 patient-specific connectivity (PCN); 2) 102 shared connectivity (SCN); and 3) 457 unshared connectivity (UCN). While the first two patterns were widely reported by previous non-TRS specific studies, we were among the first to report widespread significant connectivity differences between TRS patient groups and their healthy sibling groups. Observations of this study may provide new insights for the understanding of the neurophysiological mechanisms of TRS.

Details DOI