Xinbang Dai

Yongrui Chen, Zhiqiang Liu, Jing Yu et al.

Large Language Models (LLMs) have demonstrated substantial progress on reasoning tasks involving unstructured text, yet their capabilities significantly deteriorate when reasoning requires integrating structured external knowledge such as knowledge graphs, code snippets, or formal logic. This limitation is partly due to the absence of benchmarks capable of systematically evaluating LLM performance across diverse structured knowledge modalities. To address this gap, we introduce \textbf{\textsc{OneEval}}, a comprehensive benchmark explicitly designed to assess the knowledge-intensive reasoning capabilities of LLMs across four structured knowledge modalities, unstructured text, knowledge graphs, code, and formal logic, and five critical domains (general knowledge, government, science, law, and programming). \textsc{OneEval} comprises 4,019 carefully curated instances and includes a challenging subset, \textsc{OneEval}\textsubscript{Hard}, consisting of 1,285 particularly difficult cases. Through extensive evaluation of 18 state-of-the-art open-source and proprietary LLMs, we establish three core findings: a) \emph{persistent limitations in structured reasoning}, with even the strongest model achieving only 32.2\% accuracy on \textsc{OneEval}\textsubscript{Hard}; b) \emph{performance consistently declines as the structural complexity of the knowledge base increases}, with accuracy dropping sharply from 53\% (textual reasoning) to 25\% (formal logic); and c) \emph{diminishing returns from extended reasoning chains}, highlighting the critical need for models to adapt reasoning depth appropriately to task complexity. We release the \textsc{OneEval} datasets, evaluation scripts, and baseline results publicly, accompanied by a leaderboard to facilitate ongoing advancements in structured knowledge reasoning.

Xinbang Dai, Yuncheng Hua, Tongtong Wu et al.

When we integrate factual knowledge from knowledge graphs (KGs) into large language models (LLMs) to enhance their performance, the cost of injection through training increases with the scale of the models. Consequently, there is significant interest in developing prompt strategies that effectively incorporate KG information into LLMs. However, the community has not yet comprehensively understood how LLMs process and interpret KG information in different input formats and organizations within prompts, and researchers often rely on trial and error. To address this gap, we design extensive experiments to empirically study LLMs' comprehension of different KG prompts. At the literal level, we reveal LLMs' preferences for various input formats (from linearized triples to fluent natural language text). At the attention distribution level, we discuss the underlying mechanisms driving these preferences. We then investigate how the organization of structured knowledge impacts LLMs and evaluate LLMs' robustness in processing and utilizing KG information in practical scenarios. Our experiments show that (1) linearized triples are more effective than fluent NL text in helping LLMs understand KG information and answer fact-intensive questions; (2) Different LLMs exhibit varying preferences for different organizational formats of triples; (3) LLMs with larger scales are more susceptible to noisy, incomplete subgraphs.

Yongrui Chen, Junhao He, Linbo Fu et al.

Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions (NLQs) by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods either rely on employing task-specific strategies or custom-defined representations, which struggle to leverage the knowledge transfer between different SKR tasks or align with the prior of LLMs, thereby limiting their performance. This paper proposes a novel USKR framework named \textsc{Pandora}, which takes advantage of \textsc{Python}'s \textsc{Pandas} API to construct a unified knowledge representation for alignment with LLM pre-training. It employs an LLM to generate textual reasoning steps and executable Python code for each question. Demonstrations are drawn from a memory of training examples that cover various SKR tasks, facilitating knowledge transfer. Extensive experiments on four benchmarks involving three SKR tasks demonstrate that \textsc{Pandora} outperforms existing unified frameworks and competes effectively with task-specific methods.

Xinbang Dai, Huikang Hu, Yuncheng Hua et al.

Retrieval-augmented generation (RAG) systems face critical challenges in balancing internal (parametric) and external (retrieved) knowledge, especially when these sources conflict or are unreliable. To analyze these scenarios comprehensively, we construct the Trustworthiness Response Dataset (TRD) with 36,266 questions spanning four RAG settings. We reveal that existing approaches address isolated scenarios-prioritizing one knowledge source, naively merging both, or refusing answers-but lack a unified framework to handle different real-world conditions simultaneously. Therefore, we propose the BRIDGE framework, which dynamically determines a comprehensive response strategy of large language models (LLMs). BRIDGE leverages an adaptive weighting mechanism named soft bias to guide knowledge collection, followed by a Maximum Soft-bias Decision Tree to evaluate knowledge and select optimal response strategies (trust internal/external knowledge, or refuse). Experiments show BRIDGE outperforms baselines by 5-15% in accuracy while maintaining balanced performance across all scenarios. Our work provides an effective solution for LLMs' trustworthy responses in real-world RAG applications.

Xinbang Dai, Huikang Hu, Yongrui Chen et al.

While large language models (LLMs) excel at many domain-specific tasks, their ability to deeply comprehend and reason about full-length academic papers remains underexplored. Existing benchmarks often fall short of capturing such depth, either due to surface-level question design or unreliable evaluation metrics. To address this gap, we introduce ELAIPBench, a benchmark curated by domain experts to evaluate LLMs' comprehension of artificial intelligence (AI) research papers. Developed through an incentive-driven, adversarial annotation process, ELAIPBench features 403 multiple-choice questions from 137 papers. It spans three difficulty levels and emphasizes non-trivial reasoning rather than shallow retrieval. Our experiments show that the best-performing LLM achieves an accuracy of only 39.95%, far below human performance. Moreover, we observe that frontier LLMs equipped with a thinking mode or a retrieval-augmented generation (RAG) system fail to improve final results-even harming accuracy due to overthinking or noisy retrieval. These findings underscore the significant gap between current LLM capabilities and genuine comprehension of academic papers.

Yongrui Chen, Junhao He, Linbo Fu et al.

Unified Structured Knowledge Reasoning (USKR) aims to answer natural language questions by using structured sources such as tables, databases, and knowledge graphs in a unified way. Existing USKR methods rely on task-specific strategies or bespoke representations, which hinder their ability to dismantle barriers between different SKR tasks, thereby constraining their overall performance in cross-task scenarios. In this paper, we introduce \textsc{Pandora}, a novel USKR framework that addresses the limitations of existing methods by leveraging two key innovations. First, we propose a code-based unified knowledge representation using \textsc{Python}'s \textsc{Pandas} API, which aligns seamlessly with the pre-training of LLMs. This representation facilitates a cohesive approach to handling different structured knowledge sources. Building on this foundation, we employ knowledge transfer to bolster the unified reasoning process of LLMs by automatically building cross-task memory. By adaptively correcting reasoning using feedback from code execution, \textsc{Pandora} showcases impressive unified reasoning capabilities. Extensive experiments on six widely used benchmarks across three SKR tasks demonstrate that \textsc{Pandora} outperforms existing unified reasoning frameworks and competes effectively with task-specific methods.

Yuxin Zhang, Yan Wang, Yongrui Chen et al.

Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by incorporating external retrieved information, mitigating issues such as hallucination and outdated knowledge. However, RAG systems are highly sensitive to retrieval noise prevalent in real-world scenarios. Existing benchmarks fail to emulate the complex and heterogeneous noise distributions encountered in real-world retrieval environments, undermining reliable robustness assessment. In this paper, we define four categories of retrieval noise based on linguistic properties and noise characteristics, aiming to reflect the heterogeneity of noise in real-world scenarios. Building on this, we introduce Magic Mushroom, a benchmark for replicating "magic mushroom" noise: contexts that appear relevant on the surface but covertly mislead RAG systems. Magic Mushroom comprises 7,468 single-hop and 3,925 multi-hop question-answer pairs. More importantly, Magic Mushroom enables researchers to flexibly configure combinations of retrieval noise according to specific research objectives or application scenarios, allowing for highly controlled evaluation setups. We evaluate LLM generators of varying parameter scales and classic RAG denoising strategies under diverse noise distributions to investigate their performance dynamics during progressive noise encroachment. Our analysis reveals that both generators and denoising strategies have significant room for improvement and exhibit extreme sensitivity to noise distributions. Magic Mushroom emerges as a promising tool for evaluating and advancing noise-robust RAG systems, accelerating their widespread deployment in real-world applications. The Magic Mushroom benchmark is available at https://drive.google.com/file/d/1aP5kyPuk4L-L_uoI6T9UhxuTyt8oMqjT/view?usp=sharing.

Xinbang Dai, Huiying Li, Guilin Qi

Spatio-temporal knowledge graphs (STKGs) extend the concept of knowledge graphs (KGs) by incorporating time and location information. While the research community's focus on Knowledge Graph Question Answering (KGQA), the field of answering questions incorporating both spatio-temporal information based on STKGs remains largely unexplored. Furthermore, a lack of comprehensive datasets also has hindered progress in this area. To address this issue, we present STQAD, a dataset comprising 10,000 natural language questions for spatio-temporal knowledge graph question answering (STKGQA). Unfortunately, various state-of-the-art KGQA approaches fall far short of achieving satisfactory performance on our dataset. In response, we propose STCQA, a new spatio-temporal KGQA approach that utilizes a novel STKG embedding method named STComplEx. By extracting temporal and spatial information from a question, our QA model can better comprehend the question and retrieve accurate answers from the STKG. Through extensive experiments, we demonstrate the quality of our dataset and the effectiveness of our STKGQA method.