Chengjin Xu

Shengjie Ma, Chengjin Xu, Xuhui Jiang et al.

Retrieval-augmented generation (RAG) has improved large language models (LLMs) by using knowledge retrieval to overcome knowledge deficiencies. However, current RAG methods often fall short of ensuring the depth and completeness of retrieved information, which is necessary for complex reasoning tasks. In this work, we introduce Think-on-Graph 2.0 (ToG-2), a hybrid RAG framework that iteratively retrieves information from both unstructured and structured knowledge sources in a tight-coupling manner. Specifically, ToG-2 leverages knowledge graphs (KGs) to link documents via entities, facilitating deep and knowledge-guided context retrieval. Simultaneously, it utilizes documents as entity contexts to achieve precise and efficient graph retrieval. ToG-2 alternates between graph retrieval and context retrieval to search for in-depth clues relevant to the question, enabling LLMs to generate answers. We conduct a series of well-designed experiments to highlight the following advantages of ToG-2: 1) ToG-2 tightly couples the processes of context retrieval and graph retrieval, deepening context retrieval via the KG while enabling reliable graph retrieval based on contexts; 2) it achieves deep and faithful reasoning in LLMs through an iterative knowledge retrieval process of collaboration between contexts and the KG; and 3) ToG-2 is training-free and plug-and-play compatible with various LLMs. Extensive experiments demonstrate that ToG-2 achieves overall state-of-the-art (SOTA) performance on 6 out of 7 knowledge-intensive datasets with GPT-3.5, and can elevate the performance of smaller models (e.g., LLAMA-2-13B) to the level of GPT-3.5's direct reasoning. The source code is available on https://github.com/IDEA-FinAI/ToG-2.

Bo Xiong, Shichao Zhu, Mojtaba Nayyeri et al.

Recent knowledge graph (KG) embeddings have been advanced by hyperbolic geometry due to its superior capability for representing hierarchies. The topological structures of real-world KGs, however, are rather heterogeneous, i.e., a KG is composed of multiple distinct hierarchies and non-hierarchical graph structures. Therefore, a homogeneous (either Euclidean or hyperbolic) geometry is not sufficient for fairly representing such heterogeneous structures. To capture the topological heterogeneity of KGs, we present an ultrahyperbolic KG embedding (UltraE) in an ultrahyperbolic (or pseudo-Riemannian) manifold that seamlessly interleaves hyperbolic and spherical manifolds. In particular, we model each relation as a pseudo-orthogonal transformation that preserves the pseudo-Riemannian bilinear form. The pseudo-orthogonal transformation is decomposed into various operators (i.e., circular rotations, reflections and hyperbolic rotations), allowing for simultaneously modeling heterogeneous structures as well as complex relational patterns. Experimental results on three standard KGs show that UltraE outperforms previous Euclidean- and hyperbolic-based approaches.

Zhanpeng Chen, Chengjin Xu, Yiyan Qi et al.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in processing and generating content across multiple data modalities. However, a significant drawback of MLLMs is their reliance on static training data, leading to outdated information and limited contextual awareness. This static nature hampers their ability to provide accurate and up-to-date responses, particularly in dynamic or rapidly evolving contexts. Though integrating Multimodal Retrieval-augmented Generation (Multimodal RAG) offers a promising solution, the system would inevitably encounter the multi-granularity noisy correspondence (MNC) problem, which hinders accurate retrieval and generation. In this work, we propose RagVL, a novel framework with knowledge-enhanced reranking and noise-injected training, to address these limitations. We instruction-tune the MLLM with a simple yet effective instruction template to induce its ranking ability and serve it as a reranker to precisely filter the top-k retrieved images. For generation, we inject visual noise during training at the data and token levels to enhance the generator's robustness. Extensive experiments on the subsets of two datasets that require retrieving and reasoning over images to answer a given query verify the effectiveness of our method. Code and models are available at https://github.com/IDEA-FinAI/RagVL.

Jiashuo Sun, Chengjin Xu, Lumingyuan Tang et al.

Although large language models (LLMs) have achieved significant success in various tasks, they often struggle with hallucination problems, especially in scenarios requiring deep and responsible reasoning. These issues could be partially addressed by introducing external knowledge graphs (KG) in LLM reasoning. In this paper, we propose a new LLM-KG integrating paradigm ``$\hbox{LLM}\otimes\hbox{KG}$'' which treats the LLM as an agent to interactively explore related entities and relations on KGs and perform reasoning based on the retrieved knowledge. We further implement this paradigm by introducing a new approach called Think-on-Graph (ToG), in which the LLM agent iteratively executes beam search on KG, discovers the most promising reasoning paths, and returns the most likely reasoning results. We use a number of well-designed experiments to examine and illustrate the following advantages of ToG: 1) compared with LLMs, ToG has better deep reasoning power; 2) ToG has the ability of knowledge traceability and knowledge correctability by leveraging LLMs reasoning and expert feedback; 3) ToG provides a flexible plug-and-play framework for different LLMs, KGs and prompting strategies without any additional training cost; 4) the performance of ToG with small LLM models could exceed large LLM such as GPT-4 in certain scenarios and this reduces the cost of LLM deployment and application. As a training-free method with lower computational cost and better generality, ToG achieves overall SOTA in 6 out of 9 datasets where most previous SOTAs rely on additional training.

Xuhui Jiang, Chengjin Xu, Yinghan Shen et al.

The flourishing of knowledge graph applications has driven the need for entity alignment (EA) across KGs. However, the heterogeneity of practical KGs, characterized by differing scales, structures, and limited overlapping entities, greatly surpasses that of existing EA datasets. This discrepancy highlights an oversimplified heterogeneity in current EA datasets, which obstructs a full understanding of the advancements achieved by recent EA methods. In this paper, we study the performance of EA methods in practical settings, specifically focusing on the alignment of highly heterogeneous KGs (HHKGs). Firstly, we address the oversimplified heterogeneity settings of current datasets and propose two new HHKG datasets that closely mimic practical EA scenarios. Then, based on these datasets, we conduct extensive experiments to evaluate previous representative EA methods. Our findings reveal that, in aligning HHKGs, valuable structure information can hardly be exploited through message-passing and aggregation mechanisms. This phenomenon leads to inferior performance of existing EA methods, especially those based on GNNs. These findings shed light on the potential problems associated with the conventional application of GNN-based methods as a panacea for all EA datasets. Consequently, in light of these observations and to elucidate what EA methodology is genuinely beneficial in practical scenarios, we undertake an in-depth analysis by implementing a simple but effective approach: Simple-HHEA. This method adaptly integrates entity name, structure, and temporal information to navigate the challenges posed by HHKGs. Our experiment results conclude that the key to the future EA model design in practice lies in their adaptability and efficiency to varying information quality conditions, as well as their capability to capture patterns across HHKGs.

Chengjin Xu, Fenglong Su, Jens Lehmann

Entity alignment aims to identify equivalent entity pairs between different knowledge graphs (KGs). Recently, the availability of temporal KGs (TKGs) that contain time information created the need for reasoning over time in such TKGs. Existing embedding-based entity alignment approaches disregard time information that commonly exists in many large-scale KGs, leaving much room for improvement. In this paper, we focus on the task of aligning entity pairs between TKGs and propose a novel Time-aware Entity Alignment approach based on Graph Neural Networks (TEA-GNN). We embed entities, relations and timestamps of different KGs into a vector space and use GNNs to learn entity representations. To incorporate both relation and time information into the GNN structure of our model, we use a time-aware attention mechanism which assigns different weights to different nodes with orthogonal transformation matrices computed from embeddings of the relevant relations and timestamps in a neighborhood. Experimental results on multiple real-world TKG datasets show that our method significantly outperforms the state-of-the-art methods due to the inclusion of time information.

Honghao Liu, Xuhui Jiang, Chengjin Xu et al.

Preserving privacy in sensitive data while pretraining large language models on small, domain-specific corpora presents a significant challenge. In this work, we take an exploratory step toward privacy-preserving continual pretraining by proposing an entity-based framework that synthesizes encrypted training data to protect personally identifiable information (PII). Our approach constructs a weighted entity graph to guide data synthesis and applies deterministic encryption to PII entities, enabling LLMs to encode new knowledge through continual pretraining while granting authorized access to sensitive data through decryption keys. Our results on limited-scale datasets demonstrate that our pretrained models outperform base models and ensure PII security, while exhibiting a modest performance gap compared to models trained on unencrypted synthetic data. We further show that increasing the number of entities and leveraging graph-based synthesis improves model performance, and that encrypted models retain instruction-following capabilities with long retrieved contexts. We discuss the security implications and limitations of deterministic encryption, positioning this work as an initial investigation into the design space of encrypted data pretraining for privacy-preserving LLMs. Our code is available at https://github.com/DataArcTech/SoE.

Haohan Zhang, Fengrui Hua, Chengjin Xu et al.

The rapid advancement of Large Language Models (LLMs) has spurred discussions about their potential to enhance quantitative trading strategies. LLMs excel in analyzing sentiments about listed companies from financial news, providing critical insights for trading decisions. However, the performance of LLMs in this task varies substantially due to their inherent characteristics. This paper introduces a standardized experimental procedure for comprehensive evaluations. We detail the methodology using three distinct LLMs, each embodying a unique approach to performance enhancement, applied specifically to the task of sentiment factor extraction from large volumes of Chinese news summaries. Subsequently, we develop quantitative trading strategies using these sentiment factors and conduct back-tests in realistic scenarios. Our results will offer perspectives about the performances of Large Language Models applied to extracting sentiments from Chinese news texts.

Xueyuan Lin, Chengjin Xu, Haihong E et al.

Multi-hop logical reasoning over knowledge graph (KG) plays a fundamental role in many artificial intelligence tasks. Recent complex query embedding (CQE) methods for reasoning focus on static KGs, while temporal knowledge graphs (TKGs) have not been fully explored. Reasoning over TKGs has two challenges: 1. The query should answer entities or timestamps; 2. The operators should consider both set logic on entity set and temporal logic on timestamp set. To bridge this gap, we define the multi-hop logical reasoning problem on TKGs. With generated three datasets, we propose the first temporal CQE named Temporal Feature-Logic Embedding framework (TFLEX) to answer the temporal complex queries. We utilize vector logic to compute the logic part of Temporal Feature-Logic embeddings, thus naturally modeling all First-Order Logic (FOL) operations on entity set. In addition, our framework extends vector logic on timestamp set to cope with three extra temporal operators (After, Before and Between). Experiments on numerous query patterns demonstrate the effectiveness of our method.

Zhongwu Chen, Chengjin Xu, Fenglong Su et al.

Temporal relation prediction in incomplete temporal knowledge graphs (TKGs) is a popular temporal knowledge graph completion (TKGC) problem in both transductive and inductive settings. Traditional embedding-based TKGC models (TKGE) rely on structured connections and can only handle a fixed set of entities, i.e., the transductive setting. In the inductive setting where test TKGs contain emerging entities, the latest methods are based on symbolic rules or pre-trained language models (PLMs). However, they suffer from being inflexible and not time-specific, respectively. In this work, we extend the fully-inductive setting, where entities in the training and test sets are totally disjoint, into TKGs and take a further step towards a more flexible and time-sensitive temporal relation prediction approach SST-BERT, incorporating Structured Sentences with Time-enhanced BERT. Our model can obtain the entity history and implicitly learn rules in the semantic space by encoding structured sentences, solving the problem of inflexibility. We propose to use a time masking MLM task to pre-train BERT in a corpus rich in temporal tokens specially generated for TKGs, enhancing the time sensitivity of SST-BERT. To compute the probability of occurrence of a target quadruple, we aggregate all its structured sentences from both temporal and semantic perspectives into a score. Experiments on the transductive datasets and newly generated fully-inductive benchmarks show that SST-BERT successfully improves over state-of-the-art baselines.

Honghao Liu, Chengjin Xu, Xuhui Jiang et al.

Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood. This work investigates how LRMs respond to harmful queries when confronted with two categories of conflicts: internal conflicts that pit alignment values against each other and dilemmas, which impose mutually contradictory choices, including sacrificial, duress, agent-centered, and social forms. Using over 1,300 prompts across five benchmarks, we evaluate three representative LRMs - Llama-3.1-Nemotron-8B, QwQ-32B, and DeepSeek R1 - and find that conflicts significantly increase attack success rates, even under single-round non-narrative queries without sophisticated auto-attack techniques. Our findings reveal through layerwise and neuron-level analyses that safety-related and functional representations shift and overlap under conflict, interfering with safety-aligned behavior. This study highlights the need for deeper alignment strategies to ensure the robustness and trustworthiness of next-generation reasoning models. Our code is available at https://github.com/DataArcTech/ConflictHarm. Warning: This paper contains inappropriate, offensive and harmful content.

Zhongwu Chen, Chengjin Xu, Fenglong Su et al.

In the last few years, the solution to Knowledge Graph (KG) completion via learning embeddings of entities and relations has attracted a surge of interest. Temporal KGs(TKGs) extend traditional Knowledge Graphs (KGs) by associating static triples with timestamps forming quadruples. Different from KGs and TKGs in the transductive setting, constantly emerging entities and relations in incomplete TKGs create demand to predict missing facts with unseen components, which is the extrapolation setting. Traditional temporal knowledge graph embedding (TKGE) methods are limited in the extrapolation setting since they are trained within a fixed set of components. In this paper, we propose a Meta-Learning based Temporal Knowledge Graph Extrapolation (MTKGE) model, which is trained on link prediction tasks sampled from the existing TKGs and tested in the emerging TKGs with unseen entities and relations. Specifically, we meta-train a GNN framework that captures relative position patterns and temporal sequence patterns between relations. The learned embeddings of patterns can be transferred to embed unseen components. Experimental results on two different TKG extrapolation datasets show that MTKGE consistently outperforms both the existing state-of-the-art models for knowledge graph extrapolation and specifically adapted KGE and TKGE baselines.

Zhengzhuo Xu, Bowen Qu, Yiyan Qi et al.

Automatic chart understanding is crucial for content comprehension and document parsing. Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in chart understanding through domain-specific alignment and fine-tuning. However, current MLLMs still struggle to provide faithful data and reliable analysis only based on charts. To address it, we propose ChartMoE, which employs the Mixture of Expert (MoE) architecture to replace the traditional linear projector to bridge the modality gap. Specifically, we train several linear connectors through distinct alignment tasks, which are utilized as the foundational initialization parameters for different experts. Additionally, we introduce ChartMoE-Align, a dataset with nearly 1 million chart-table-JSON-code quadruples to conduct three alignment tasks (chart-table/JSON/code). Combined with the vanilla connector, we initialize different experts diversely and adopt high-quality knowledge learning to further refine the MoE connector and LLM parameters. Extensive experiments demonstrate the effectiveness of the MoE connector and our initialization strategy, e.g., ChartMoE improves the accuracy of the previous state-of-the-art from 80.48\% to 84.64\% on the ChartQA benchmark.

Xuhui Jiang, Chengjin Xu, Yinghan Shen et al.

Knowledge graphs (KGs) are structured representations of diversified knowledge. They are widely used in various intelligent applications. In this article, we provide a comprehensive survey on the evolution of various types of knowledge graphs (i.e., static KGs, dynamic KGs, temporal KGs, and event KGs) and techniques for knowledge extraction and reasoning. Furthermore, we introduce the practical applications of different types of KGs, including a case study in financial analysis. Finally, we propose our perspective on the future directions of knowledge engineering, including the potential of combining the power of knowledge graphs and large language models (LLMs), and the evolution of knowledge extraction, reasoning, and representation.

Zhengzhuo Xu, Sinan Du, Yiyan Qi et al.

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in image understanding and generation. However, current benchmarks fail to accurately evaluate the chart comprehension of MLLMs due to limited chart types and inappropriate metrics. To address this, we propose ChartBench, a comprehensive benchmark designed to assess chart comprehension and data reliability through complex visual reasoning. ChartBench includes 42 categories, 66.6k charts, and 600k question-answer pairs. Notably, many charts lack data point annotations, which requires MLLMs to derive values similar to human understanding by leveraging inherent chart elements such as color, legends, and coordinate systems. We also design an enhanced evaluation metric, Acc+, to evaluate MLLMs without extensive manual or costly LLM-based evaluations. Furthermore, we propose two baselines based on the chain of thought and supervised fine-tuning to improve model performance on unannotated charts. Extensive experimental evaluations of 18 open-sourced and 3 proprietary MLLMs reveal their limitations in chart comprehension and offer valuable insights for further research. Code and dataset are publicly available at https://chartbench.github.io.

Zhichao Shi, Cehao Yang, Hao Zhou et al.

Synthetic data has emerged as a crucial solution to the data scarcity bottleneck in large language models (LLMs), particularly for specialized domains and low-resource languages. However, the broader adoption of existing synthetic data tools is severely hindered by convoluted workflows, fragmented data standards, and limited scalability across modalities. To address these limitations, we develop DataArc-SynData-Toolkit, an open-source framework featuring: (1) a configuration-driven, end-to-end pipeline equipped with an intuitive visual interface and simplified CLI for exceptional usability; (2) a unified, quality-controllable synthesis paradigm that standardizes multi-source data generation to ensure high reusability; and (3) a highly modular architecture designed for seamless multimodal, multilingual, and multi-task adaptation. We apply the toolkit in multiple application scenarios. Experimental results demonstrate that our toolkit achieves an optimal balance between generation efficiency and data quality. By offering an end-to-end and visually interactive pipeline, DataArc-SynData-Toolkit significantly lowers the technical barrier to synthetic data generation and subsequent model training, accelerating its practical deployment in real-world applications.

Cehao Yang, Xueyuan Lin, Chengjin Xu et al.

Despite the growing development of long-context large language models (LLMs), data-centric approaches relying on synthetic data have been hindered by issues related to faithfulness, which limit their effectiveness in enhancing model performance on tasks such as long-context reasoning and question answering (QA). These challenges are often exacerbated by misinformation caused by lack of verification, reasoning without attribution, and potential knowledge conflicts. We propose LongFaith, a novel pipeline for synthesizing faithful long-context reasoning instruction datasets. By integrating ground truth and citation-based reasoning prompts, we eliminate distractions and improve the accuracy of reasoning chains, thus mitigating the need for costly verification processes. We open-source two synthesized datasets, LongFaith-SFT and LongFaith-PO, which systematically address multiple dimensions of faithfulness, including verified reasoning, attribution, and contextual grounding. Extensive experiments on multi-hop reasoning datasets and LongBench demonstrate that models fine-tuned on these datasets significantly improve performance. Our ablation studies highlight the scalability and adaptability of the LongFaith pipeline, showcasing its broad applicability in developing long-context LLMs.

Jiawei Gu, Xuhui Jiang, Zhichao Shi et al.

Accurate and consistent evaluation is crucial for decision-making across numerous fields, yet it remains a challenging task due to inherent subjectivity, variability, and scale. Large Language Models (LLMs) have achieved remarkable success across diverse domains, leading to the emergence of "LLM-as-a-Judge," where LLMs are employed as evaluators for complex tasks. With their ability to process diverse data types and provide scalable, cost-effective, and consistent assessments, LLMs present a compelling alternative to traditional expert-driven evaluations. However, ensuring the reliability of LLM-as-a-Judge systems remains a significant challenge that requires careful design and standardization. This paper provides a comprehensive survey of LLM-as-a-Judge, addressing the core question: How can reliable LLM-as-a-Judge systems be built? We explore strategies to enhance reliability, including improving consistency, mitigating biases, and adapting to diverse assessment scenarios. Additionally, we propose methodologies for evaluating the reliability of LLM-as-a-Judge systems, supported by a novel benchmark designed for this purpose. To advance the development and real-world deployment of LLM-as-a-Judge systems, we also discussed practical applications, challenges, and future directions. This survey serves as a foundational reference for researchers and practitioners in this rapidly evolving field.

Xiaojun Wu, Junxi Liu, Huanyi Su et al.

As large language models become increasingly prevalent in the financial sector, there is a pressing need for a standardized method to comprehensively assess their performance. However, existing finance benchmarks often suffer from limited language and task coverage, as well as challenges such as low-quality datasets and inadequate adaptability for LLM evaluation. To address these limitations, we propose "Golden Touchstone", the first comprehensive bilingual benchmark for financial LLMs, which incorporates representative datasets from both Chinese and English across eight core financial NLP tasks. Developed from extensive open source data collection and industry-specific demands, this benchmark includes a variety of financial tasks aimed at thoroughly assessing models' language understanding and generation capabilities. Through comparative analysis of major models on the benchmark, such as GPT-4o Llama3, FinGPT and FinMA, we reveal their strengths and limitations in processing complex financial information. Additionally, we open-sourced Touchstone-GPT, a financial LLM trained through continual pre-training and financial instruction tuning, which demonstrates strong performance on the bilingual benchmark but still has limitations in specific tasks.This research not only provides the financial large language models with a practical evaluation tool but also guides the development and optimization of future research. The source code for Golden Touchstone and model weight of Touchstone-GPT have been made publicly available at \url{https://github.com/IDEA-FinAI/Golden-Touchstone}, contributing to the ongoing evolution of FinLLMs and fostering further research in this critical area.

Cehao Yang, Xueyuan Lin, Chengjin Xu et al.

A practical approach to activate long chain-of-thoughts reasoning ability in pre-trained large language models is to perform supervised fine-tuning on instruction datasets synthesized by strong Large Reasoning Models such as DeepSeek-R1, offering a cost-effective alternative to reinforcement learning. However, large-scale instruction sets with more than 100k samples incur significant training overhead, while effective strategies for automatic long-CoT instruction selection still remain unexplored. In this work, we propose Select2Reason, a novel and efficient instruction-tuning data selection framework for long-CoT reasoning. From the perspective of emergence of rethinking behaviors like self-correction and backtracking, we investigate common metrics that may determine the quality of long-CoT reasoning instructions. Select2Reason leverages a quantifier to estimate difficulty of question and jointly incorporates a reasoning trace length-based heuristic through a weighted scheme for ranking to prioritize high-utility examples. Empirical results on OpenR1-Math-220k demonstrate that fine-tuning LLM on only 10% of the data selected by Select2Reason achieves performance competitive with or superior to full-data tuning and open-source baseline OpenR1-Qwen-7B across three competition-level and six comprehensive mathematical benchmarks. Further experiments highlight the scalability in varying data size, efficiency during inference, and its adaptability to other instruction pools with minimal cost.

Zhichao Shi, Xuhui Jiang, Chengjin Xu et al.

Current evaluation paradigms for large language models (LLMs) suffer from overestimated or biased evaluations and mismatched question difficulty, leading to incomplete evaluations of knowledge and capability boundaries, which hinder their effective application and optimization. To address these challenges, we propose Agent-as-Interviewer, a dynamic evaluation paradigm that employs LLM agents to conduct multi-turn interactions for evaluation. Unlike current benchmarking or dynamic interaction paradigms, Agent-as-Interviewer utilizes agents to invoke knowledge tools for wider and deeper knowledge in the dynamic multi-turn question generation, achieving more comprehensive evaluations of LLM's knowledge boundaries. It also leverages agents to plan query strategies for adjustment of the question difficulty levels, enhancing the difficulty control to match the actual capabilities of target LLMs. Based on this paradigm, we develop JudgeAgent, a knowledge-wise dynamic evaluation framework that employs knowledge-driven synthesis as the agent's tool and uses difficulty scoring as strategy guidance, thereby finally providing valuable suggestions to help targets optimize themselves. Extensive experiments validate the effectiveness of JudgeAgent's suggestions, demonstrating that Agent-as-Interviewer can accurately identify the knowledge and capability boundaries of target models. The source code is available on https://github.com/DataArcTech/JudgeAgent.

Bokai Cao, Xueyuan Lin, Yiyan Qi et al.

Market simulator tries to create high-quality synthetic financial data that mimics real-world market dynamics, which is crucial for model development and robust assessment. Despite continuous advancements in simulation methodologies, market fluctuations vary in terms of scale and sources, but existing frameworks often excel in only specific tasks. To address this challenge, we propose Financial Wind Tunnel (FWT), a retrieval-augmented market simulator designed to generate controllable, reasonable, and adaptable market dynamics for model testing. FWT offers a more comprehensive and systematic generative capability across different data frequencies. By leveraging a retrieval method to discover cross-sectional information as the augmented condition, our diffusion-based simulator seamlessly integrates both macro- and micro-level market patterns. Furthermore, our framework allows the simulation to be controlled with wide applicability, including causal generation through "what-if" prompts or unprecedented cross-market trend synthesis. Additionally, we develop an automated optimizer for downstream quantitative models, using stress testing of simulated scenarios via FWT to enhance returns while controlling risks. Experimental results demonstrate that our approach enables the generalizable and reliable market simulation, significantly improve the performance and adaptability of downstream models, particularly in highly complex and volatile market conditions. Our code and data sample is available at https://anonymous.4open.science/r/fwt_-E852

Xuhui Jiang, Yuxing Tian, Fengrui Hua et al.

Hallucinations in large language models (LLMs) are always seen as limitations. However, could they also be a source of creativity? This survey explores this possibility, suggesting that hallucinations may contribute to LLM application by fostering creativity. This survey begins with a review of the taxonomy of hallucinations and their negative impact on LLM reliability in critical applications. Then, through historical examples and recent relevant theories, the survey explores the potential creative benefits of hallucinations in LLMs. To elucidate the value and evaluation criteria of this connection, we delve into the definitions and assessment methods of creativity. Following the framework of divergent and convergent thinking phases, the survey systematically reviews the literature on transforming and harnessing hallucinations for creativity in LLMs. Finally, the survey discusses future research directions, emphasizing the need to further explore and refine the application of hallucinations in creative processes within LLMs.

Xuhui Jiang, Yinghan Shen, Zhichao Shi et al.

Entity Alignment (EA) is vital for integrating diverse knowledge graph (KG) data, playing a crucial role in data-driven AI applications. Traditional EA methods primarily rely on comparing entity embeddings, but their effectiveness is constrained by the limited input KG data and the capabilities of the representation learning techniques. Against this backdrop, we introduce ChatEA, an innovative framework that incorporates large language models (LLMs) to improve EA. To address the constraints of limited input KG data, ChatEA introduces a KG-code translation module that translates KG structures into a format understandable by LLMs, thereby allowing LLMs to utilize their extensive background knowledge to improve EA accuracy. To overcome the over-reliance on entity embedding comparisons, ChatEA implements a two-stage EA strategy that capitalizes on LLMs' capability for multi-step reasoning in a dialogue format, thereby enhancing accuracy while preserving efficiency. Our experimental results verify ChatEA's superior performance, highlighting LLMs' potential in facilitating EA tasks.

Muzhi Li, Cehao Yang, Chengjin Xu et al.

Inductive knowledge graph completion (KGC) aims to predict missing triples with unseen entities. Recent works focus on modeling reasoning paths between the head and tail entity as direct supporting evidence. However, these methods depend heavily on the existence and quality of reasoning paths, which limits their general applicability in different scenarios. In addition, we observe that latent type constraints and neighboring facts inherent in KGs are also vital in inferring missing triples. To effectively utilize all useful information in KGs, we introduce CATS, a novel context-aware inductive KGC solution. With sufficient guidance from proper prompts and supervised fine-tuning, CATS activates the strong semantic understanding and reasoning capabilities of large language models to assess the existence of query triples, which consist of two modules. First, the type-aware reasoning module evaluates whether the candidate entity matches the latent entity type as required by the query relation. Then, the subgraph reasoning module selects relevant reasoning paths and neighboring facts, and evaluates their correlation to the query triple. Experiment results on three widely used datasets demonstrate that CATS significantly outperforms state-of-the-art methods in 16 out of 18 transductive, inductive, and few-shot settings with an average absolute MRR improvement of 7.2%.

Zhongwu Chen, Chengjin Xu, Dingmin Wang et al.

Retrieval-augmented generation (RAG) has shown promising potential in knowledge intensive question answering (QA). However, existing approaches only consider the query itself, neither specifying the retrieval preferences for the retrievers nor informing the generators of how to refer to the retrieved documents for the answers, which poses a significant challenge to the QA performance. To address these issues, we propose Rule-guided Retrieval-Augmented Generation with LMs, which explicitly introduces rules for in-context learning (RuleRAG-ICL) to guide retrievers to recall related documents in the directions of rules and uniformly guide generators to reason attributed by the same rules. Moreover, most existing RAG datasets were constructed without considering rules and Knowledge Graphs (KGs) are recognized as providing high-quality rules. Therefore, we construct five rule-aware RAG benchmarks for QA, RuleQA, based on KGs to stress the significance of retrieval and reasoning with rules. Experiments on RuleQA demonstrate RuleRAG-ICL improves the retrieval quality of +89.2% in Recall@10 and answer accuracy of +103.1% in Exact Match, and RuleRAG-FT yields more enhancement. In addition, experiments on four existing RAG datasets show RuleRAG is also effective by offering rules in RuleQA to them, further proving the generalization of rule guidance in RuleRAG.

Muzhi Li, Cehao Yang, Chengjin Xu et al.

The Knowledge Graph Completion~(KGC) task aims to infer the missing entity from an incomplete triple. Existing embedding-based methods rely solely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities. On the other hand, text-based methods struggle with the semantic gap between KG triples and natural language. Apart from triples, entity contexts (e.g., labels, descriptions, aliases) also play a significant role in augmenting KGs. To address these limitations, we propose KGR3, a context-enriched framework for KGC. KGR3 is composed of three modules. Firstly, the Retrieval module gathers supporting triples from the KG, collects plausible candidate answers from a base embedding model, and retrieves context for each related entity. Then, the Reasoning module employs a large language model to generate potential answers for each query triple. Finally, the Re-ranking module combines candidate answers from the two modules mentioned above, and fine-tunes an LLM to provide the best answer. Extensive experiments on widely used datasets demonstrate that KGR3 consistently improves various KGC methods. Specifically, the best variant of KGR3 achieves absolute Hits@1 improvements of 12.3% and 5.6% on the FB15k237 and WN18RR datasets.

Shengjie Ma, Xuhui Jiang, Chengjin Xu et al.

Large Language Models (LLMs) have achieved remarkable success but remain data-inefficient, especially when learning from small, specialized corpora with limited and proprietary data. Existing synthetic data generation methods for continue pre-training focus on intra-document content and overlook cross-document knowledge associations, limiting content diversity and depth. We propose Synthetic-on-Graph (SoG), a synthetic data generation framework that incorporates cross-document knowledge associations for efficient corpus expansion. SoG constructs a context graph by extracting entities and concepts from the original corpus, representing cross-document associations, and employing a graph walk strategy for knowledge-associated sampling. This enhances synthetic data diversity and coherence, enabling models to learn complex knowledge structures and handle rare knowledge. To further improve the quality of synthetic data, we integrate two complementary strategies, Chain-of-Thought (CoT) and Contrastive Clarifying (CC), to enhance both reasoning capability and discriminative power. Extensive experiments demonstrate that SoG surpasses state-of-the-art (SOTA) methods on multi-hop and domain-specific question answering, while achieving competitive performance on long-context reading comprehension. These results highlight the superior generalization ability of SoG. Our work advances the paradigm of synthetic data generation and offers practical solutions for efficient knowledge acquisition in LLMs, particularly for downstream tasks and domains with limited training data.

Yi Luo, Zhenghao Lin, Yuhao Zhang et al.

Large Language Models (LLMs) exhibit impressive capabilities but also present risks such as biased content generation and privacy issues. One of the current alignment techniques includes principle-driven integration, but it faces challenges arising from the imprecision of manually crafted rules and inadequate risk perception in models without safety training. To address these, we introduce Guide-Align, a two-stage approach. Initially, a safety-trained model identifies potential risks and formulates specific guidelines for various inputs, establishing a comprehensive library of guidelines and a model for input-guidelines retrieval. Subsequently, the retrieval model correlates new inputs with relevant guidelines, which guide LLMs in response generation to ensure safe and high-quality outputs, thereby aligning with human values. An additional optional stage involves fine-tuning a model with well-aligned datasets generated through the process implemented in the second stage. Our method customizes guidelines to accommodate diverse inputs, thereby enhancing the fine-grainedness and comprehensiveness of the guideline library. Furthermore, it incorporates safety expertise from a safety-trained LLM through a lightweight retrieval model. We evaluate our approach on three benchmarks, demonstrating significant improvements in LLM security and quality. Notably, our fine-tuned model, Labrador, even at 13 billion parameters, outperforms GPT-3.5-turbo and surpasses GPT-4 in alignment capabilities.

Xueyuan Lin, Cehao Yang, Ye Ma et al.

Recently, large language models (LLMs) have demonstrated outstanding reasoning capabilities on mathematical and coding tasks. However, their application to financial tasks-especially the most fundamental task of stock movement prediction-remains underexplored. We study a three-class classification problem (up, hold, down) and, by analyzing existing reasoning responses, observe that: (1) LLMs follow analysts' opinions rather than exhibit a systematic, independent analytical logic (CoTs). (2) LLMs list summaries from different sources without weighing adversarial evidence, yet such counterevidence is crucial for reliable prediction. It shows that the model does not make good use of its reasoning ability to complete the task. To address this, we propose Reflective Evidence Tuning (RETuning), a cold-start method prior to reinforcement learning, to enhance prediction ability. While generating CoT, RETuning encourages dynamically constructing an analytical framework from diverse information sources, organizing and scoring evidence for price up or down based on that framework-rather than on contextual viewpoints-and finally reflecting to derive the prediction. This approach maximally aligns the model with its learned analytical framework, ensuring independent logical reasoning and reducing undue influence from context. We also build a large-scale dataset spanning all of 2024 for 5,123 A-share stocks, with long contexts (32K tokens) and over 200K samples. In addition to price and news, it incorporates analysts' opinions, quantitative reports, fundamental data, macroeconomic indicators, and similar stocks. Experiments show that RETuning successfully unlocks the model's reasoning ability in the financial domain. Inference-time scaling still works even after 6 months or on out-of-distribution stocks, since the models gain valuable insights about stock movement prediction.

Cehao Yang, Xiaojun Wu, Xueyuan Lin et al.

Graph Retrieval-Augmented Generation (GraphRAG) enhances factual reasoning in LLMs by structurally modeling knowledge through graph-based representations. However, existing GraphRAG approaches face two core limitations: shallow retrieval that fails to surface all critical evidence, and inefficient utilization of pre-constructed structural graph data, which hinders effective reasoning from complex queries. To address these challenges, we propose \textsc{GraphSearch}, a novel agentic deep searching workflow with dual-channel retrieval for GraphRAG. \textsc{GraphSearch} organizes the retrieval process into a modular framework comprising six modules, enabling multi-turn interactions and iterative reasoning. Furthermore, \textsc{GraphSearch} adopts a dual-channel retrieval strategy that issues semantic queries over chunk-based text data and relational queries over structural graph data, enabling comprehensive utilization of both modalities and their complementary strengths. Experimental results across six multi-hop RAG benchmarks demonstrate that \textsc{GraphSearch} consistently improves answer accuracy and generation quality over the traditional strategy, confirming \textsc{GraphSearch} as a promising direction for advancing graph retrieval-augmented generation.

Xiaojun Wu, Cehao Yang, Xueyuan Lin et al.

Retrieval-Augmented Generation (RAG) and Graph-based RAG has become the important paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing approaches face a fundamental trade-off. While graph-based methods are inherently dependent on high-quality graph structures, they face significant practical constraints: manually constructed knowledge graphs are prohibitively expensive to scale, while automatically extracted graphs from corpora are limited by the performance of the underlying LLM extractors, especially when using smaller, local-deployed models. This paper presents Think-on-Graph 3.0 (ToG-3), a novel framework that introduces Multi-Agent Context Evolution and Retrieval (MACER) mechanism to overcome these limitations. Our core innovation is the dynamic construction and refinement of a Chunk-Triplets-Community heterogeneous graph index, which pioneeringly incorporates a dual-evolution mechanism of Evolving Query and Evolving Sub-Graph for precise evidence retrieval. This approach addresses a critical limitation of prior Graph-based RAG methods, which typically construct a static graph index in a single pass without adapting to the actual query. A multi-agent system, comprising Constructor, Retriever, Reflector, and Responser agents, collaboratively engages in an iterative process of evidence retrieval, answer generation, sufficiency reflection, and, crucially, evolving query and subgraph. This dual-evolving multi-agent system allows ToG-3 to adaptively build a targeted graph index during reasoning, mitigating the inherent drawbacks of static, one-time graph construction and enabling deep, precise reasoning even with lightweight LLMs. Extensive experiments demonstrate that ToG-3 outperforms compared baselines on both deep and broad reasoning benchmarks, and ablation studies confirm the efficacy of the components of MACER framework.

Cehao Yang, Chengjin Xu, Yiyan Qi

Artificial intelligence is making significant strides in the finance industry, revolutionizing how data is processed and interpreted. Among these technologies, large language models (LLMs) have demonstrated substantial potential to transform financial services by automating complex tasks, enhancing customer service, and providing detailed financial analysis. Firstly, we introduce IDEA-FinBench, an evaluation benchmark specifically tailored for assessing financial knowledge in large language models (LLMs). This benchmark utilizes questions from two globally respected and authoritative financial professional exams, aimimg to comprehensively evaluate the capability of LLMs to directly address exam questions pertinent to the finance sector. Secondly, we propose IDEA-FinKER, a Financial Knowledge Enhancement framework designed to facilitate the rapid adaptation of general LLMs to the financial domain, introducing a retrieval-based few-shot learning method for real-time context-level knowledge injection, and a set of high-quality financial knowledge instructions for fine-tuning any general LLM. Finally, we present IDEA-FinQA, a financial question-answering system powered by LLMs. This system is structured around a scheme of real-time knowledge injection and factual enhancement using external knowledge. IDEA-FinQA is comprised of three main modules: the data collector, the data querying module, and LLM-based agents tasked with specific functions.

Chengjin Xu, Muzhi Li, Cehao Yang et al.

Knowledge Graphs (KGs) are foundational structures in many AI applications, representing entities and their interrelations through triples. However, triple-based KGs lack the contextual information of relational knowledge, like temporal dynamics and provenance details, which are crucial for comprehensive knowledge representation and effective reasoning. Instead, \textbf{Context Graphs} (CGs) expand upon the conventional structure by incorporating additional information such as time validity, geographic location, and source provenance. This integration provides a more nuanced and accurate understanding of knowledge, enabling KGs to offer richer insights and support more sophisticated reasoning processes. In this work, we first discuss the inherent limitations of triple-based KGs and introduce the concept of CGs, highlighting their advantages in knowledge representation and reasoning. We then present a context graph reasoning \textbf{CGR$^3$} paradigm that leverages large language models (LLMs) to retrieve candidate entities and related contexts, rank them based on the retrieved information, and reason whether sufficient information has been obtained to answer a query. Our experimental results demonstrate that CGR$^3$ significantly improves performance on KG completion (KGC) and KG question answering (KGQA) tasks, validating the effectiveness of incorporating contextual information on KG representation and reasoning.

Chengjin Xu, Mojtaba Nayyeri, Yung-Yu Chen et al.

Recent years, Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a Knowledge Graph (KG) into a geometric space and thus have gained increasing attentions. In addition, many recent Knowledge Graphs involve evolving data, e.g., the fact (\textit{Obama}, \textit{PresidentOf}, \textit{USA}) is valid only from 2009 to 2017. This introduces important challenges for knowledge representation learning since such temporal KGs change over time. In this work, we strive to move beyond the complex or hypercomplex space for KGE and propose a novel geometric algebra based embedding approach, GeomE, which uses multivector representations and the geometric product to model entities and relations. GeomE subsumes several state-of-the-art KGE models and is able to model diverse relations patterns. On top of this, we extend GeomE to TGeomE for temporal KGE, which performs 4th-order tensor factorization of a temporal KG and devises a new linear temporal regularization for time representation learning. Moreover, we study the effect of time granularity on the performance of TGeomE models. Experimental results show that our proposed models achieve the state-of-the-art performances on link prediction over four commonly-used static KG datasets and four well-established temporal KG datasets across various metrics.

Chengjin Xu, Mojtaba Nayyeri, Sahar Vahdati et al.

Among the top approaches of recent years, link prediction using knowledge graph embedding (KGE) models has gained significant attention for knowledge graph completion. Various embedding models have been proposed so far, among which, some recent KGE models obtain state-of-the-art performance on link prediction tasks by using embeddings with a high dimension (e.g. 1000) which accelerate the costs of training and evaluation considering the large scale of KGs. In this paper, we propose a simple but effective performance boosting strategy for KGE models by using multiple low dimensions in different repetition rounds of the same model. For example, instead of training a model one time with a large embedding size of 1200, we repeat the training of the model 6 times in parallel with an embedding size of 200 and then combine the 6 separate models for testing while the overall numbers of adjustable parameters are same (6*200=1200) and the total memory footprint remains the same. We show that our approach enables different models to better cope with their expressiveness issues on modeling various graph patterns such as symmetric, 1-n, n-1 and n-n. In order to justify our findings, we conduct experiments on various KGE models. Experimental results on standard benchmark datasets, namely FB15K, FB15K-237 and WN18RR, show that multiple low-dimensional models of the same kind outperform the corresponding single high-dimensional models on link prediction in a certain range and have advantages in training efficiency by using parallel training while the overall numbers of adjustable parameters are same.

Mojtaba Nayyeri, Chengjin Xu, Jens Lehmann et al.

Knowledge Graph Embeddings (KGEs) have shown promising performance on link prediction tasks by mapping the entities and relations from a knowledge graph into a geometric space (usually a vector space). Ultimately, the plausibility of the predicted links is measured by using a scoring function over the learned embeddings (vectors). Therefore, the capability in preserving graph characteristics including structural aspects and semantics highly depends on the design of the KGE, as well as the inherited abilities from the underlying geometry. Many KGEs use the flat geometry which renders them incapable of preserving complex structures and consequently causes wrong inferences by the models. To address this problem, we propose a neuro differential KGE that embeds nodes of a KG on the trajectories of Ordinary Differential Equations (ODEs). To this end, we represent each relation (edge) in a KG as a vector field on a smooth Riemannian manifold. We specifically parameterize ODEs by a neural network to represent various complex shape manifolds and more importantly complex shape vector fields on the manifold. Therefore, the underlying embedding space is capable of getting various geometric forms to encode complexity in subgraph structures with different motifs. Experiments on synthetic and benchmark dataset as well as social network KGs justify the ODE trajectories as a means to structure preservation and consequently avoiding wrong inferences over state-of-the-art KGE models.

Chengjin Xu, Mojtaba Nayyeri, Fouad Alkhoury et al.

In the last few years, there has been a surge of interest in learning representations of entitiesand relations in knowledge graph (KG). However, the recent availability of temporal knowledgegraphs (TKGs) that contain time information for each fact created the need for reasoning overtime in such TKGs. In this regard, we present a new approach of TKG embedding, TeRo, which defines the temporal evolution of entity embedding as a rotation from the initial time to the currenttime in the complex vector space. Specially, for facts involving time intervals, each relation isrepresented as a pair of dual complex embeddings to handle the beginning and the end of therelation, respectively. We show our proposed model overcomes the limitations of the existing KG embedding models and TKG embedding models and has the ability of learning and inferringvarious relation patterns over time. Experimental results on four different TKGs show that TeRo significantly outperforms existing state-of-the-art models for link prediction. In addition, we analyze the effect of time granularity on link prediction over TKGs, which as far as we know hasnot been investigated in previous literature.

Chengjin Xu, Mojtaba Nayyeri, Yung-Yu Chen et al.

Knowledge graph (KG) embedding aims at embedding entities and relations in a KG into a lowdimensional latent representation space. Existing KG embedding approaches model entities andrelations in a KG by utilizing real-valued , complex-valued, or hypercomplex-valued (Quaternionor Octonion) representations, all of which are subsumed into a geometric algebra. In this work,we introduce a novel geometric algebra-based KG embedding framework, GeomE, which uti-lizes multivector representations and the geometric product to model entities and relations. Ourframework subsumes several state-of-the-art KG embedding approaches and is advantageouswith its ability of modeling various key relation patterns, including (anti-)symmetry, inversionand composition, rich expressiveness with higher degree of freedom as well as good general-ization capacity. Experimental results on multiple benchmark knowledge graphs show that theproposed approach outperforms existing state-of-the-art models for link prediction.

Chengjin Xu, Mojtaba Nayyeri, Fouad Alkhoury et al.

Knowledge Graph (KG) embedding has attracted more attention in recent years. Most KG embedding models learn from time-unaware triples. However, the inclusion of temporal information beside triples would further improve the performance of a KGE model. In this regard, we propose ATiSE, a temporal KG embedding model which incorporates time information into entity/relation representations by using Additive Time Series decomposition. Moreover, considering the temporal uncertainty during the evolution of entity/relation representations over time, we map the representations of temporal KGs into the space of multi-dimensional Gaussian distributions. The mean of each entity/relation embedding at a time step shows the current expected position, whereas its covariance (which is temporally stationary) represents its temporal uncertainty. Experimental results show that ATiSE chieves the state-of-the-art on link prediction over four temporal KGs.

Mojtaba Nayyeri, Chengjin Xu, Yadollah Yaghoobzadeh et al.

Knowledge graphs (KGs) represent world's facts in structured forms. KG completion exploits the existing facts in a KG to discover new ones. Translation-based embedding model (TransE) is a prominent formulation to do KG completion. Despite the efficiency of TransE in memory and time, it suffers from several limitations in encoding relation patterns such as symmetric, reflexive etc. To resolve this problem, most of the attempts have circled around the revision of the score function of TransE i.e., proposing a more complicated score function such as Trans(A, D, G, H, R, etc) to mitigate the limitations. In this paper, we tackle this problem from a different perspective. We show that existing theories corresponding to the limitations of TransE are inaccurate because they ignore the effect of loss function. Accordingly, we pose theoretical investigations of the main limitations of TransE in the light of loss function. To the best of our knowledge, this has not been investigated so far comprehensively. We show that by a proper selection of the loss function for training the TransE model, the main limitations of the model are mitigated. This is explained by setting upper-bound for the scores of positive samples, showing the region of truth (i.e., the region that a triple is considered positive by the model). Our theoretical proofs with experimental results fill the gap between the capability of translation-based class of embedding models and the loss function. The theories emphasise the importance of the selection of the loss functions for training the models. Our experimental evaluations on different loss functions used for training the models justify our theoretical proofs and confirm the importance of the loss functions on the performance.

Mojtaba Nayyeri, Chengjin Xu, Jens Lehmann et al.

Knowledge graph embedding models have gained significant attention in AI research. Recent works have shown that the inclusion of background knowledge, such as logical rules, can improve the performance of embeddings in downstream machine learning tasks. However, so far, most existing models do not allow the inclusion of rules. We address the challenge of including rules and present a new neural based embedding model (LogicENN). We prove that LogicENN can learn every ground truth of encoded rules in a knowledge graph. To the best of our knowledge, this has not been proved so far for the neural based family of embedding models. Moreover, we derive formulae for the inclusion of various rules, including (anti-)symmetric, inverse, irreflexive and transitive, implication, composition, equivalence and negation. Our formulation allows to avoid grounding for implication and equivalence relations. Our experiments show that LogicENN outperforms the state-of-the-art models in link prediction.