Publications

The early concept of knowledge graph originates from the idea of the Semantic Web, which aims at using structured graphs to model the knowledge of the world and record the relationships that exist between things. Currently publishing knowledge bases as open data on the Web has gained significant attention. In China, CIPS(Chinese Information Processing Society) launched the OpenKG in 2015 to foster the development of Chinese Open Knowledge Graphs. Unlike existing open knowledge-based programs, OpenKG chain is envisioned as a blockchain-based open knowledge infrastructure. This article introduces the first attempt at the implementation of sharing knowledge graphs on OpenKG chain, a blockchain-based trust network. We have completed the test of the underlying blockchain platform, as well as the on-chain test of OpenKG's dataset and toolset sharing as well as fine-grained knowledge crowdsourcing at the triple level. We have also proposed novel definitions: K-Point and OpenKG Token, which can be considered as a measurement of knowledge value and user value. 1033 knowledge contributors have been involved in two months of testing on the blockchain, and the cumulative number of on-chain recordings triggered by real knowledge consumers has reached 550,000 with an average daily peak value of more than 10,000. For the first time, We have tested and realized on-chain sharing of knowledge at entity/triple granularity level. At present, all operations on the datasets and toolset in OpenKG.CN, as well as the triplets in OpenBase, are recorded on the chain, and corresponding value will also be generated and assigned in a trusted mode. Via this effort, OpenKG chain looks to provide a more credible and traceable knowledge-sharing platform for the knowledge graph community.

Well-designed prompts have demonstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve the desired results by manually entering prompts due to a discrepancy between novice-user-input prompts and the model-preferred prompts. To bridge the distribution gap between user input behavior and model training datasets, we first construct a novel Coarse-Fine Granularity Prompts dataset (CFP) and propose a novel User-Friendly Fine-Grained Text Generation framework (UF-FGTG) for automated prompt optimization. For CFP, we construct a novel dataset for text-to-image tasks that combines coarse and fine-grained prompts to facilitate the development of automated prompt generation methods. For UF-FGTG, we propose a novel framework that automatically translates user-input prompts into model-preferred prompts. Specifically, we propose a prompt refiner that continually rewrites prompts to empower users to select results that align with their unique needs. Meanwhile, we integrate image-related loss functions from the text-to-image model into the training process of text generation to generate model-preferred prompts. Additionally, we propose an adaptive feature extraction module to ensure diversity in the generated results. Experiments demonstrate that our approach is capable of generating more visually appealing and diverse images than previous state-of-the-art methods, achieving an average improvement of 5% across six quality and aesthetic metrics. Data and code are available at https://github.com/Naylenv/UF-FGTG.

Large language models (LLMs) have demonstrated remarkable performance on questionanswering (QA) tasks because of their superior capabilities in natural language understanding and generation.However, LLM-based QA struggles with complex QA tasks due to poor reasoning capacity, outdated knowledge, and hallucinations.Several recent works synthesize LLMs and knowledge graphs (KGs) for QA to address the above challenges.In this survey, we propose a new structured taxonomy that categorizes the methodology of synthesizing LLMs and KGs for QA according to the categories of QA and the KG's role when integrating with LLMs.We systematically survey state-of-theart methods in synthesizing LLMs and KGs for QA and compare and analyze these approaches in terms of strength, limitations, and KG requirements.We then align the approaches with QA and discuss how these approaches address the main challenges of different complex QA.Finally, we summarize the advancements, evaluation metrics, and benchmark datasets and highlight open challenges and opportunities.

Current encoder–decoders for Knowledge Graph Question Answering (KGQA) commonly utilize teacher-forcing training to accelerate convergence. However, this training approach limits the model’s exposure to ground truths, resulting in exposure bias that hampers generalization performance during autoregressive inference. To alleviate the issue, we propose a contrastive framework that enables the model to access a variety of positive and negative examples, thereby enhancing generalization. Firstly, we introduce a sampling augmentation strategy to construct contrastive samples, which can ensure explicit semantic consistency of positive pairs and inconsistency of negative pairs. Secondly, we augment the training process by incorporating “hard” negatives to enhance the contrastive objective, along with augmented positives to improve the generation objective. Finally, we also sample multiple logical forms for each question during the inference to reduce the bias potential and train a contrastive ranking model to obtain the target logical form. We achieve improvements of 1.95% and 1% over the previous state-of-the-art methods on the KQA Pro and OVERNIGHT benchmarks, respectively. Furthermore, our approach obtains competitive results on the WebQSP dataset. These findings validate the efficacy of our contrastive framework for advancing KGQA performance.

With the rapid expansion of parameters in large language models (LLMs) and the application of Reinforcement Learning with Human Feedback (RLHF), there has been a noticeable growth in the moral competence of LLMs. However, several questions warrant further exploration: Is it really possible for LLMs to fully align with human values through RLHF? How can the current moral growth be philosophically contextualized? We identify similarities between LLMs' moral growth and Deweyan ethics in terms of the discourse of human moral development. We then attempt to use Dewey's theory on an experimental basis to examine and further explain the extent to which the current alignment pathway enables the development of LLMs. A beating experiment serves as the foundational case for analyzing LLMs' moral competence across various parameters and stages, including basic moral cognition, moral dilemma judgment, and moral behavior. The results demonstrate that the moral competence of the GPT series has seen a significant improvement, and Dewey's Impulse-Habit-Character theory of moral development can be used to explain this: the moral competence of LLMs has been enhanced through experience-based learning, supported by human feedback. Nevertheless, LLMs' moral development through RLHF remains constrained and does not reach the character stage described by Dewey, possibly due to their lack of self-consciousness. This fundamental difference between humans and LLMs underscores both the limitations of LLMs' moral growth and the challenges of applying RLHF for AI alignment. It also emphasizes the need for external societal governance and legal regulation.

Layout planning is centrally important in the field of architecture and urban design. Among the various basic units carrying urban functions, residential community plays a vital part for supporting human life. Therefore, the layout planning of residential community has always been of concern, and has attracted particular attention since the advent of deep learning that facilitates the automated layout generation and spatial pattern recognition. However, the research circles generally suffer from the insufficiency of residential community layout benchmark or high-quality datasets, which hampers the future exploration of data-driven methods for residential community layout planning. The lack of datasets is largely due to the difficulties of large-scale real-world residential data acquisition and long-term expert screening. In order to address the issues and advance a benchmark dataset for various intelligent spatial design and analysis applications in the development of smart city, we introduce Residential Community Layout Planning (ReCo) Dataset, which is the first and largest open-source vector dataset related to real-world community to date. ReCo Dataset is presented in multiple data formats with 37,646 residential community layout plans, covering 598,728 residential buildings with height information. ReCo can be conveniently adapted for residential community layout related urban design tasks, e.g., generative layout design, morphological pattern recognition and spatial evaluation. To validate the utility of ReCo in automated residential community layout planning, two Generative Adversarial Network (GAN) based generative models are further applied to the dataset. We expect ReCo Dataset to inspire more creative and practical work in intelligent design and beyond. The ReCo Dataset is published at: https://www.kaggle.com/fdudsde/reco-dataset and related code can be found at: \urlhttps://github.com/FDUDSDE/ReCo-Dataset.

Semantic web data management on top of relational database has been regarded as a promising solution for scalable ontology storing, querying and reasoning. In order to reduce query response time, inferred results often need to be pre-computed and materialized....

Although prevailing supervised and self-supervised learning (SSL)-augmented sequential recommendation (SeRec) models have achieved improved performance with powerful neural network architectures, we argue that they still suffer from two limitations: (1) Preference Drift, where models trained on past data can hardly accommodate evolving user preference; and (2) Implicit Memory, where head patterns dominate parametric learning, making it harder to recall long tails. In this work, we explore retrieval augmentation in SeRec, to address these limitations. To this end, we propose a Retrieval-Augmented Sequential Recommendation framework, named RaSeRec, the main idea of which is to maintain a dynamic memory bank to accommodate preference drifts and retrieve relevant memories to augment user modeling explicitly. It consists of two stages: (i) collaborative-based pre-training, which learns to recommend and retrieve; (ii) retrieval-augmented fine-tuning, which learns to leverage retrieved memories. Extensive experiments on three datasets fully demonstrate the superiority and effectiveness of RaSeRec.