Yuqicheng Zhu

Yunjie He, Mojtaba Nayyeri, Bo Xiong et al.

Answering first-order logical (FOL) queries over knowledge graphs (KG) remains a challenging task mainly due to KG incompleteness. Query embedding approaches this problem by computing the low-dimensional vector representations of entities, relations, and logical queries. KGs exhibit relational patterns such as symmetry and composition and modeling the patterns can further enhance the performance of query embedding models. However, the role of such patterns in answering FOL queries by query embedding models has not been yet studied in the literature. In this paper, we fill in this research gap and empower FOL queries reasoning with pattern inference by introducing an inductive bias that allows for learning relation patterns. To this end, we develop a novel query embedding method, RoConE, that defines query regions as geometric cones and algebraic query operators by rotations in complex space. RoConE combines the advantages of Cone as a well-specified geometric representation for query embedding, and also the rotation operator as a powerful algebraic operation for pattern inference. Our experimental results on several benchmark datasets confirm the advantage of relational patterns for enhancing logical query answering task.

Yuqicheng Zhu, Nico Potyka, Mojtaba Nayyeri et al.

Knowledge graph embedding (KGE) models are often used to predict missing links for knowledge graphs (KGs). However, multiple KG embeddings can perform almost equally well for link prediction yet give conflicting predictions for unseen queries. This phenomenon is termed \textit{predictive multiplicity} in the literature. It poses substantial risks for KGE-based applications in high-stake domains but has been overlooked in KGE research. We define predictive multiplicity in link prediction, introduce evaluation metrics and measure predictive multiplicity for representative KGE methods on commonly used benchmark datasets. Our empirical study reveals significant predictive multiplicity in link prediction, with $8\%$ to $39\%$ testing queries exhibiting conflicting predictions. We address this issue by leveraging voting methods from social choice theory, significantly mitigating conflicts by $66\%$ to $78\%$ in our experiments.

Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang et al. · oxford

Large language models (LLMs) achieve strong results on knowledge graph question answering (KGQA), but most benchmarks assume complete knowledge graphs (KGs) where direct supporting triples exist. This reduces evaluation to shallow retrieval and overlooks the reality of incomplete KGs, where many facts are missing and answers must be inferred from existing facts. We bridge this gap by proposing a methodology for constructing benchmarks under KG incompleteness, which removes direct supporting triples while ensuring that alternative reasoning paths required to infer the answer remain. Experiments on benchmarks constructed using our methodology show that existing methods suffer consistent performance degradation under incompleteness, highlighting their limited reasoning ability. To overcome this limitation, we present the Adaptive Graph Reasoning Agent (GR-Agent). It first constructs an interactive environment from the KG, and then formalizes KGQA as agent environment interaction within this environment. GR-Agent operates over an action space comprising graph reasoning tools and maintains a memory of potential supporting reasoning evidence, including relevant relations and reasoning paths. Extensive experiments demonstrate that GR-Agent outperforms non-training baselines and performs comparably to training-based methods under both complete and incomplete settings.

Boer Zhang, Mingyan Wu, Dongzhuoran Zhou et al.

Deep research requires reasoning over web evidence to answer open-ended questions, and it is a core capability for AI agents. Yet many deep research agents still rely on implicit, unstructured search behavior that causes redundant exploration and brittle evidence aggregation. Motivated by Anthropic's "think" tool paradigm and insights from the information-retrieval literature, we introduce Q+, a set of query and evidence processing tools that make web search more deliberate by guiding query planning, monitoring search progress, and extracting evidence from long web snapshots. We integrate Q+ into the browser sub-agent of Eigent, an open-source, production-ready multi-agent workforce for computer use, yielding EigentSearch-Q+. Across four benchmarks (SimpleQA-Verified, FRAMES, WebWalkerQA, and X-Bench DeepSearch), Q+ improves Eigent's browser agent benchmark-size-weighted average accuracy by 3.0, 3.8, and 0.6 percentage points (pp) for GPT-4.1, GPT-5.1, and Minimax M2.5 model backends, respectively. Case studies further suggest that EigentSearch-Q+ produces more coherent tool-calling trajectories by making search progress and evidence handling explicit.

Yunjie He, Daniel Hernandez, Mojtaba Nayyeri et al.

Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily rely on excessively parameterized neural networks and cannot explain the knowledge learned from the graph. We propose a novel query embedding method, AConE, which explains the knowledge learned from the graph in the form of $SROI^-$ description logic axioms while being more parameter-efficient than most existing approaches. AConE associates queries to a $SROI^-$ description logic concept. Every $SROI^-$ concept is embedded as a cone in complex vector space, and each $SROI^-$ relation is embedded as a transformation that rotates and scales cones. We show theoretically that AConE can learn $SROI^-$ axioms, and defines an algebra whose operations correspond one to one to $SROI^-$ description logic concept constructs. Our empirical study on multiple query datasets shows that AConE achieves superior results over previous baselines with fewer parameters. Notably on the WN18RR dataset, AConE achieves significant improvement over baseline models. We provide comprehensive analyses showing that the capability to represent axioms positively impacts the results of query answering.

Yuqicheng Zhu, Mohamed-Ali Tnani, Timo Jahnz et al.

The paucity of labeled data is a typical challenge in the automotive industry. Annotating time-series measurements requires solid domain knowledge and in-depth exploratory data analysis, which implies a high labeling effort. Conventional Active Learning (AL) addresses this issue by actively querying the most informative instances based on the estimated classification probability and retraining the model iteratively. However, the learning efficiency strongly relies on the initial model, resulting in the trade-off between the size of the initial dataset and the query number. This paper proposes a novel Few-Shot Learning (FSL)-based AL framework, which addresses the trade-off problem by incorporating a Prototypical Network (ProtoNet) in the AL iterations. The results show an improvement, on the one hand, in the robustness to the initial model and, on the other hand, in the learning efficiency of the ProtoNet through the active selection of the support set in each iteration. This framework was validated on UCI HAR/HAPT dataset and a real-world braking maneuver dataset. The learning performance significantly surpasses traditional AL algorithms on both datasets, achieving 90% classification accuracy with 10% and 5% labeling effort, respectively.

Yuqicheng Zhu, Nico Potyka, Bo Xiong et al.

Statistical information is ubiquitous but drawing valid conclusions from it is prohibitively hard. We explain how knowledge graph embeddings can be used to approximate probabilistic inference efficiently using the example of Statistical EL (SEL), a statistical extension of the lightweight Description Logic EL. We provide proofs for runtime and soundness guarantees, and empirically evaluate the runtime and approximation quality of our approach.

Yuqicheng Zhu, Nico Potyka, Jiarong Pan et al.

Knowledge graph embeddings (KGE) apply machine learning methods on knowledge graphs (KGs) to provide non-classical reasoning capabilities based on similarities and analogies. The learned KG embeddings are typically used to answer queries by ranking all potential answers, but rankings often lack a meaningful probabilistic interpretation - lower-ranked answers do not necessarily have a lower probability of being true. This limitation makes it difficult to quantify uncertainty of model's predictions, posing challenges for the application of KGE methods in high-stakes domains like medicine. We address this issue by applying the theory of conformal prediction that allows generating answer sets, which contain the correct answer with probabilistic guarantees. We explain how conformal prediction can be used to generate such answer sets for link prediction tasks. Our empirical evaluation on four benchmark datasets using six representative KGE methods validates that the generated answer sets satisfy the probabilistic guarantees given by the theory of conformal prediction. We also demonstrate that the generated answer sets often have a sensible size and that the size adapts well with respect to the difficulty of the query.

Yuan He, Bailan He, Zifeng Ding et al.

Understanding and mitigating hallucinations in Large Language Models (LLMs) is crucial for ensuring reliable content generation. While previous research has primarily focused on "when" LLMs hallucinate, our work explains "why" and directly links model behaviour to the pre-training data that forms their prior knowledge. Specifically, we demonstrate that an asymmetry exists in the recognition of logically equivalent facts, which can be attributed to frequency discrepancies of entities appearing as subjects versus objects. Given that most pre-training datasets are inaccessible, we leverage the fully open-source OLMo series by indexing its Dolma dataset to estimate entity frequencies. Using relational facts (represented as triples) from Wikidata5M, we construct probing datasets to isolate this effect. Our experiments reveal that facts with a high-frequency subject and a low-frequency object are better recognised than their inverse, despite their logical equivalence. The pattern reverses in low-to-high frequency settings, and no statistically significant asymmetry emerges when both entities are high-frequency. These findings highlight the influential role of pre-training data in shaping model predictions and provide insights for inferring the characteristics of pre-training data in closed or partially closed LLMs.

Nico Potyka, Yuqicheng Zhu, Yunjie He et al.

Large-language models (LLMs) can support a wide range of applications like conversational agents, creative writing or general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking queries in diagnostic settings like medical and fault diagnosis and discuss how the Partial Borda Choice function from the literature can be applied to merge multiple query results. We discuss some additional interesting properties in our setting and evaluate the robustness of our approach empirically.

Yunjie He, Bo Xiong, Daniel Hernández et al.

Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding methods use this decomposition to compute the embedding of a query as the combination of the embedding of the subqueries. This requirement limits the answerable queries to queries having a single free variable and being decomposable, which are called tree-form queries and correspond to the $\mathcal{SROI}^-$ description logic. In this paper, we define a more general set of queries, called DAG queries and formulated in the $\mathcal{ALCOIR}$ description logic, propose a query embedding method for them, called DAGE, and a new benchmark to evaluate query embeddings on them. Given the computational graph of a DAG query, DAGE combines the possibly multiple paths between two nodes into a single path with a trainable operator that represents the intersection of relations and learns DAG-DL from tautologies. We show that it is possible to implement DAGE on top of existing query embedding methods, and we empirically measure the improvement of our method over the results of vanilla methods evaluated in tree-form queries that approximate the DAG queries of our proposed benchmark.

Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang et al. · oxford

Knowledge Graph based Retrieval-Augmented Generation (KG-RAG) is a technique that enhances Large Language Model (LLM) inference in tasks like Question Answering (QA) by retrieving relevant information from knowledge graphs (KGs). However, real-world KGs are often incomplete, meaning that essential information for answering questions may be missing. Existing benchmarks do not adequately capture the impact of KG incompleteness on KG-RAG performance. In this paper, we systematically evaluate KG-RAG methods under incomplete KGs by removing triples using different methods and analyzing the resulting effects. We demonstrate that KG-RAG methods are sensitive to KG incompleteness, highlighting the need for more robust approaches in realistic settings.

Yuqicheng Zhu, Nico Potyka, Daniel Hernández et al.

Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, yet suffers from critical limitations in high-stakes domains -- namely, sensitivity to noisy or contradictory evidence and opaque, stochastic decision-making. We propose ArgRAG, an explainable, and contestable alternative that replaces black-box reasoning with structured inference using a Quantitative Bipolar Argumentation Framework (QBAF). ArgRAG constructs a QBAF from retrieved documents and performs deterministic reasoning under gradual semantics. This allows faithfully explaining and contesting decisions. Evaluated on two fact verification benchmarks, PubHealth and RAGuard, ArgRAG achieves strong accuracy while significantly improving transparency.

Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang et al. · oxford

Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the structured evidence of knowledge graphs. However, current evaluation practices fall short: existing benchmarks often include questions that can be directly answered using existing triples in KG, making it unclear whether models perform reasoning or simply retrieve answers directly. Moreover, inconsistent evaluation metrics and lenient answer matching criteria further obscure meaningful comparisons. In this work, we introduce a general method for constructing benchmarks, together with an evaluation protocol, to systematically assess KG-RAG methods under knowledge incompleteness. Our empirical results show that current KG-RAG methods have limited reasoning ability under missing knowledge, often rely on internal memorization, and exhibit varying degrees of generalization depending on their design.

Yuqicheng Zhu, Daniel Hernández, Yuan He et al.

Uncertainty quantification in Knowledge Graph Embedding (KGE) methods is crucial for ensuring the reliability of downstream applications. A recent work applies conformal prediction to KGE methods, providing uncertainty estimates by generating a set of answers that is guaranteed to include the true answer with a predefined confidence level. However, existing methods provide probabilistic guarantees averaged over a reference set of queries and answers (marginal coverage guarantee). In high-stakes applications such as medical diagnosis, a stronger guarantee is often required: the predicted sets must provide consistent coverage per query (conditional coverage guarantee). We propose CondKGCP, a novel method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets. CondKGCP merges predicates with similar vector representations and augments calibration with rank information. We prove the theoretical guarantees and demonstrate empirical effectiveness of CondKGCP by comprehensive evaluations.

Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka et al.

Despite the remarkable success of deep neural networks (DNNs) in computer vision, they fail to remain high-performing when facing distribution shifts between training and testing data. In this paper, we propose Knowledge-Guided Visual representation learning (KGV) - a distribution-based learning approach leveraging multi-modal prior knowledge - to improve generalization under distribution shift. It integrates knowledge from two distinct modalities: 1) a knowledge graph (KG) with hierarchical and association relationships; and 2) generated synthetic images of visual elements semantically represented in the KG. The respective embeddings are generated from the given modalities in a common latent space, i.e., visual embeddings from original and synthetic images as well as knowledge graph embeddings (KGEs). These embeddings are aligned via a novel variant of translation-based KGE methods, where the node and relation embeddings of the KG are modeled as Gaussian distributions and translations, respectively. We claim that incorporating multi-model prior knowledge enables more regularized learning of image representations. Thus, the models are able to better generalize across different data distributions. We evaluate KGV on different image classification tasks with major or minor distribution shifts, namely road sign classification across datasets from Germany, China, and Russia, image classification with the mini-ImageNet dataset and its variants, as well as the DVM-CAR dataset. The results demonstrate that KGV consistently exhibits higher accuracy and data efficiency across all experiments.

Yuqicheng Zhu, Jingcheng Wu, Yizhen Wang et al.

Uncertain knowledge graph embedding (UnKGE) methods learn vector representations that capture both structural and uncertainty information to predict scores of unseen triples. However, existing methods produce only point estimates, without quantifying predictive uncertainty-limiting their reliability in high-stakes applications where understanding confidence in predictions is crucial. To address this limitation, we propose \textsc{UnKGCP}, a framework that generates prediction intervals guaranteed to contain the true score with a user-specified level of confidence. The length of the intervals reflects the model's predictive uncertainty. \textsc{UnKGCP} builds on the conformal prediction framework but introduces a novel nonconformity measure tailored to UnKGE methods and an efficient procedure for interval construction. We provide theoretical guarantees for the intervals and empirically verify these guarantees. Extensive experiments on standard benchmarks across diverse UnKGE methods further demonstrate that the intervals are sharp and effectively capture predictive uncertainty.

Hongkuan Zhou, Lavdim Halilaj, Sebastian Monka et al.

Open-domain visual entity recognition aims to identify and link entities depicted in images to a vast and evolving set of real-world concepts, such as those found in Wikidata. Unlike conventional classification tasks with fixed label sets, it operates under open-set conditions, where most target entities are unseen during training and exhibit long-tail distributions. This makes the task inherently challenging due to limited supervision, high visual ambiguity, and the need for semantic disambiguation. We propose a Knowledge-guided Contrastive Learning (KnowCoL) framework that combines both images and text descriptions into a shared semantic space grounded by structured information from Wikidata. By abstracting visual and textual inputs to a conceptual level, the model leverages entity descriptions, type hierarchies, and relational context to support zero-shot entity recognition. We evaluate our approach on the OVEN benchmark, a large-scale open-domain visual recognition dataset with Wikidata IDs as the label space. Our experiments show that using visual, textual, and structured knowledge greatly improves accuracy, especially for rare and unseen entities. Our smallest model improves the accuracy on unseen entities by 10.5% compared to the state-of-the-art, despite being 35 times smaller.

Zifeng Ding, Shenyang Huang, Zeyu Cao et al. · cambridge

Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural approaches, such as temporal graph neural networks, achieve strong performance but lack explainability and cannot be applied to unseen graphs without retraining. Recent studies have begun to explore using large language models (LLMs) for graph reasoning, but most of them are constrained to static graphs or small synthetic TGs and lack the evaluation of the quality of reasoning traces generated by LLMs. In this work, we present Reasoning-Enhanced Learning for Temporal Graphs (ReaL-TG), a reinforcement learning framework that fine-tunes LLMs to perform explainable link forecasting on real-world TGs. ReaL-TG uses outcome-based reward to encourage models to self-explore reasoning strategies from graph structure and to produce explanations that directly justify their predictions. To enable evaluation on LLM-generated reasoning traces, we propose a new evaluation protocol combining ranking metrics with an LLM-as-a-Judge system that assesses both the quality of reasoning and the impact of hallucinations. Experiments with ReaL-TG-4B, obtained by fine-tuning Qwen3-4B under our framework, show that it outperforms much larger frontier LLMs, including GPT-5 mini, on ranking metrics, while producing high-quality explanations confirmed by both the LLM judge and human evaluation.