arXiv subjects

Mengjia Wu

Publications and source records attributed to Mengjia Wu.

15 recordsLinked to original sources

arXiv2026

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation

Hallucination detection is crucial for large language models (LLMs), as hallucinated content creates significant barriers in applications requiring factual accuracy. Current detection methods mainly depend on internal signals like uncertainty and self-consistency checks, using the model's pre-trained knowledge to identify unreliable outputs. However, pre-trained knowledge may become outdated and has coverage limitations, especially for specialized or recent information. To address these limitations, retrieval-augmented generation (RAG) has emerged as a promising solution by retrieving relevant evidence at inference time, grounding outputs beyond the model's parametric knowledge. In this paper, we target a critical and practical learning problem RAG-based hallucination detection (RHD), where RAG is employed to enhance hallucination detection by addressing information updating challenges. To address RHD, we propose a novel method Evidence-Aligned Entity Verification (EAEV), which detects entity-level hallucinations by leveraging RAG to align generated entities with retrieved evidence contexts. Specifically, EAEV evaluates entity-evidence alignment through three complementary dimensions and introduces counterfactual stability analysis to ensure robust alignments under evidence perturbations. Experiments across multiple RAG benchmarks demonstrate that EAEV achieves consistent improvements over existing methods with strong generalization capabilities.

cs.AI↗

arXiv2026

Agent-Enhanced Heterogeneous Graph RAG for Academic Question Answering

Academic question answering requires reasoning over heterogeneous scholarly graphs, where queries range from simple attribute lookups to multi-hop inference across author--paper--venue structures. Existing retrieval-augmented generation (RAG) systems struggle in this setting due to three limitations: (1) fixed retrieval strategies that do not adapt to varying query complexity, (2) the absence of sufficiency evaluation leading to incomplete or misaligned evidence, and (3) a lack of structured verification against graph facts. To address these issues, we propose an agentic heterogeneous graph RAG method that transforms the three core stages of the RAG pipeline into explicit agentic decision steps. A query-aware retrieval agent analyzes query type and selects an appropriate graph traversal strategy; a sufficiency-aware reranking agent assesses evidence completeness and adaptively expands the retrieved subgraph; and a graph-grounded verification agent checks entity, relation, and attribute correctness before finalizing the answer. Experiments on heterogeneous graphs constructed from OpenAlex and DBLP suggest that our method consistently outperforms strong LLM, graph-augmented RAG, and agent-based baselines.

cs.SI↗

arXiv2026

Understanding before verifying: Claim normalization for automated citation verification

Citation accuracy has been studied for decades because of its importance to research reliability. Content-level citation verification assesses the reliability of scholarly claims. Recent work adopts a two-stage retrieval-classification framework inherited from fact-checking. However, this design overlooks the complexity of the raw citing claim and introduces three issues into the verification system, namely scope mismatch, perspective mismatch, and proposition entanglement. These issues increase the difficulty of retrieval and classification, thereby limiting model performance. Motivated by this gap, we propose claim normalization, which applies three rewriting strategies to the raw citing claim before retrieval and classification, allowing each downstream model to perform a single, well-defined task. Building on this method, we develop Claim-Normalized Citation Verification (CNCV), a new three-stage framework consisting of claim normalization, evidence retrieval with grounding, and citation classification. We evaluate CNCV across 18 classifiers using a factorial experiment on human-annotated citation instances. Compared with the prior two-stage framework, CNCV improves macro F1 by an average of 12% for encoders and 10% for generative LLMs, driven by improved evidence quality, the dominant factor identified in our experiments. Evidence retrieved from automatically normalized claims yields downstream classification performance statistically equivalent to that obtained with manually annotated evidence.

cs.IR↗

arXiv2026

Beyond Citations: Comparing Scholarly, Policy, and Patent Impact Across the FT50 Journals

The Financial Times 50 (FT50) journal list shapes hiring, promotion, accreditation, and research evaluation across business schools worldwide. Yet journals on the list are typically treated as if they represent a homogeneous tier of excellence. We test this assumption by comparing 53 FT50 and recently removed journals across three distinct impact channels: scholarly influence (field-weighted citations and visibility), policy uptake, and technological reach through patent citations. Using a panel of more than 60,000 publications from 2005 to 2019, we find striking heterogeneity hidden beneath the binary FT50 label. Elite economics journals dominate policy influence, information systems and marketing journals lead technological impact, while many highly cited management journals exhibit limited reach beyond academia. Citation, policy, and patent indicators behave as largely independent dimensions of impact, with a citation-only ranking correlating only moderately with a multidimensional ranking. Nearly half of all journals change quartile once policy and patent indicators are incorporated, demonstrating that assessments based solely on scholarly citations overlook important dimensions of research influence. While the FT50 remains widely used as a binary classification of journal quality, our results reveal a substantial within-list impact spectrum and show that journal rankings are highly sensitive to how impact is defined and measured.

cs.DL↗

arXiv2026

Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs

Representation learning on dynamic graphs requires capturing complex dependencies that evolve across both time and structure. Existing approaches typically adopt fixed temporal decay schemes or predetermined structural propagation depths, limiting their ability to generalize across graphs with diverse interaction frequencies and topological characteristics. We propose Dual-Scale Retentive Dynamics (DSRD), a unified framework that maintains a retentive representation state encoding both temporal memory and structural context. DSRD introduces two key components: (i) a retentive state with dual-scale adaptation that jointly models temporal dynamics and structural propagation within a single recurrent formulation, and (ii) adaptive decay kernels with learnable time-sensitivity parameters that automatically balance short-term responsiveness and long-term retention based on the underlying interaction patterns. We provide theoretical analysis establishing the equivalence between event-wise parallel aggregation and efficient recurrent state updates, as well as stability and boundedness guarantees for the learned dynamics. Extensive experiments on 14 real-world benchmarks demonstrate that DSRD consistently achieves state-of-the-art performance on both link prediction and node classification tasks, with strong generalization across transductive and inductive settings.

cs.LG↗

arXiv2026

From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation

Legal consultation question answering (Legal CQA) presents unique challenges compared to traditional legal QA tasks, including the scarcity of high-quality training data, complex task composition, and strong contextual dependencies. To address these, we construct JurisCQAD, a large-scale dataset of over 43,000 real-world Chinese legal queries annotated with expert-validated positive and negative responses, and design a structured task decomposition that converts each query into a legal element graph integrating entities, events, intents, and legal issues. We further propose JurisMA, a modular multi-agent framework supporting dynamic routing, statutory grounding, and stylistic optimization. Combined with the element graph, the framework enables strong context-aware reasoning, effectively capturing dependencies across legal facts, norms, and procedural logic. Trained on JurisCQAD and evaluated on a refined LawBench, our system significantly outperforms both general-purpose and legal-domain LLMs across multiple lexical and semantic metrics, demonstrating the benefits of interpretable decomposition and modular collaboration in Legal CQA.

cs.CL↗

arXiv2026

Large language models for post-publication research evaluation: Evidence from expert recommendations and citation indicators

Assessing the quality of scientific research is essential for scholarly communication, yet widely used approaches face limitations in scalability, subjectivity, and time delay. Recent advances in large language models (LLMs) offer new opportunities for automated research evaluation based on textual content. This study examines whether LLMs can support post-publication peer review tasks by benchmarking their outputs against expert judgments and citation-based indicators. Two evaluation tasks are constructed using articles from the H1 Connect platform: identifying high-quality articles and performing finer-grained evaluation including article rating, merit classification, and expert style commenting. Multiple model families, including BERT models, general-purpose LLMs, and reasoning oriented LLMs, are evaluated under multiple learning strategies. Results show that LLMs perform well in coarse grained evaluation tasks, achieving accuracy above 0.8 in identifying highly recommended articles. However, performance decreases substantially in fine-grained rating tasks. Few-shot prompting improves performance over zero-shot settings, while supervised fine-tuning produces the strongest and most balanced results. Retrieval augmented prompting improves classification accuracy in some cases but does not consistently strengthen alignment with citation indicators. The overall correlations between model outputs and citation indicators remain positive but moderate.

cs.IR↗

arXiv2026

From Newborn to Impact: Bias-Aware Citation Prediction

As a key to accessing research impact, citation dynamics underpins research evaluation, scholarly recommendation, and the study of knowledge diffusion. Citation prediction is particularly critical for newborn papers, where early assessment must be performed without citation signals and under highly long-tailed distributions. We identify two key research gaps: (i) insufficient modeling of implicit factors of scientific impact, leading to reliance on coarse proxies; and (ii) a lack of bias-aware learning that can deliver stable predictions on lowly cited papers. We address these gaps by proposing a Bias-Aware Citation Prediction Framework, which combines multi-agent feature extraction with robust graph representation learning. First, a multi-agent x graph co-learning module derives fine-grained, interpretable signals, such as reproducibility, collaboration network, and text quality, from metadata and external resources, and fuses them with heterogeneous-network embeddings to provide rich supervision even in the absence of early citation signals. Second, we incorporate a set of robust mechanisms: a two-stage forward process that routes explicit factors through an intermediate exposure estimate, GroupDRO to optimize worst-case group risk across environments, and a regularization head that performs what-if analyses on controllable factors under monotonicity and smoothness constraints. Comprehensive experiments on two real-world datasets demonstrate the effectiveness of our proposed model. Specifically, our model achieves around a 13% reduction in error metrics (MALE and RMSLE) and a notable 5.5% improvement in the ranking metric (NDCG) over the baseline methods.

cs.SI↗

arXiv2026

Choosing How to Remember: Adaptive Memory Structures for LLM Agents

Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing agent memory systems suffer from two key gaps: they rely on a one-size-fits-all memory structure and do not model memory structure selection as a context-adaptive decision, limiting their ability to handle heterogeneous interaction patterns and resulting in suboptimal performance. We propose a unified framework, FluxMem, that enables adaptive memory organization for LLM agents. Our framework equips agents with multiple complementary memory structures. It explicitly learns to select among these structures based on interaction-level features, using offline supervision derived from downstream response quality and memory utilization. To support robust long-horizon memory evolution, we further introduce a three-level memory hierarchy and a Beta Mixture Model-based probabilistic gate for distribution-aware memory fusion, replacing brittle similarity thresholds. Experiments on two long-horizon benchmarks, PERSONAMEM and LoCoMo, demonstrate that our method achieves average improvements of 9.18% and 6.14%.

cs.AI↗

arXiv2026

HetGCoT: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Academic Question Answering

Academic question answering (QA) in heterogeneous scholarly networks presents unique challenges requiring both structural understanding and interpretable reasoning. While graph neural networks (GNNs) capture structured graph information and large language models (LLMs) demonstrate strong capabilities in semantic comprehension, current approaches lack integration at the reasoning level. We propose HetGCoT, a framework enabling LLMs to effectively leverage and learn information from graphs to reason interpretable academic QA results. Our framework introduces three technical contributions: (1) a framework that transforms heterogeneous graph structural information into LLM-processable reasoning chains, (2) an adaptive metapath selection mechanism identifying relevant subgraphs for specific queries, and (3) a multi-step reasoning strategy systematically incorporating graph contexts into the reasoning process. Experiments on OpenAlex and DBLP datasets show our approach outperforms all sota baselines. The framework demonstrates adaptability across different LLM architectures and applicability to various scholarly question answering tasks.

cs.SI↗

arXiv2025

AI-Enhanced Multi-Dimensional Measurement of Technological Convergence through Heterogeneous Graph and Semantic Learning

Technological convergence refers to the phenomenon where boundaries between technological areas and disciplines are increasingly blurred. It enables the integration of previously distinct domains and has become a mainstream trend in today's innovation process. However, accurately measuring technological convergence remains a persistent challenge due to its inherently multidimensional and evolving nature. This study designs an Technological Convergence Index (TCI) that comprehensively measures convergence along two fundamental dimensions: depth and breadth. For depth calculation, we use IPC textual descriptions as the analytical foundation and enhance this assessment by incorporating supplementary patent metadata into a heterogeneous graph structure. This graph is then modeled using Heterogeneous Graph Transformers in combination with Sentence-BERT, enabling a precise representation of knowledge integration across technological boundaries. Complementing this, the breadth dimension captures the diversity of technological fields involved, quantified through the Shannon Diversity Index to measure the variety of technological combinations within patents. Our final TCI is constructed using the Entropy Weight Method, which objectively assigns weights to both dimensions based on their information entropy. To validate our approach, we compare the proposed TCI against established convergence measures, demonstrating its comparative advantages. We further establish empirical reliability through a novel robustness test that regresses TCI against indicators of patent quality. These findings are further substantiated through comprehensive robustness checks. Our multidimensional approach provides valuable practical insights for innovation policy and industry strategies in managing emerging cross-domain technologies.

cs.SI↗

arXiv2024

Two Birds with One Stone: Improving Rumor Detection by Addressing the Unfairness Issue

The degraded performance and group unfairness caused by confounding sensitive attributes in rumor detection remains relatively unexplored. To address this, we propose a two-step framework. Initially, it identifies confounding sensitive attributes that limit rumor detection performance and cause unfairness across groups. Subsequently, we aim to learn equally informative representations through invariant learning. Our method considers diverse sets of groups without sensitive attribute annotations. Experiments show our method easily integrates with existing rumor detectors, significantly improving both their detection performance and fairness.

cs.SI↗

arXiv2024

Responsible AI: Portraits with Intelligent Bibliometrics

Shifting the focus from principles to practical implementation, responsible artificial intelligence (AI) has garnered considerable attention across academia, industry, and society at large. Despite being in its nascent stages, this emerging field grapples with nebulous concepts and intricate knowledge frameworks. By analyzing three prevailing concepts - explainable AI, trustworthy AI, and ethical AI, this study defined responsible AI and identified its core principles. Methodologically, this study successfully demonstrated the implementation of leveraging AI's capabilities into bibliometrics for enhanced knowledge discovery and the cross-validation of experimentally examined models with domain insights. Empirically, this study investigated 17,799 research articles contributed by the AI community since 2015. This involves recognizing key technological players and their relationships, unveiling the topical landscape and hierarchy of responsible AI, charting its evolution, and elucidating the interplay between the responsibility principles and primary AI techniques. An analysis of a core cohort comprising 380 articles from multiple disciplines captures the most recent advancements in responsible AI. As one of the pioneering bibliometric studies dedicated to exploring responsible AI, this study will provide comprehensive macro-level insights, enhancing the understanding of responsible AI while furnishing valuable knowledge support for AI regulation and governance initiatives.

cs.AI↗

arXiv2022

Stepping beyond your comfort zone: Diffusion-based network analytics for knowledge trajectory recommendation

Interest in tracing the research interests of scientific researchers is rising, and particularly that of predicting a researcher's knowledge trajectories beyond their current foci into potential inter-/cross-/multi-disciplinary interactions. Hence, in this study, we present a method of diffusion-based network analytics for knowledge trajectory recommendation. The method begins by constructing a heterogeneous bibliometric network consisting of a co-topic layer and a co-authorship layer. A novel link prediction approach with a diffusion strategy is then used to reflect real-world academic activity, such as knowledge sharing between co-authors or diffusing between similar research topics. This strategy differentiates the interactions occurring between homogeneous and heterogeneous nodes and weights the strengths of these interactions. Two sets of experiments - one with a local dataset and another with a global dataset - demonstrate that the proposed method is prior to selected baselines. In addition, to further examine the reliability of our method, we conducted a case study on recommending knowledge trajectories of selected information scientists and their research groups. The results demonstrate the empirical insights our method yields for individual researchers, communities, and research institutions in the information science discipline.

cs.SI↗

arXiv2020

How to Investigate the Historical Roots and Evolution of Research Fields in China? A Case Study on iMetrics Using RootCite

This paper aimed to provide an approach to investigate the historical roots and evolution of research fields in China by extending the reference publication year spectroscopy (RPYS). RootCite, an open source software accepts raw data from both the Web of Science and the China Social Science Citation Index (CSSCI), was developed using python. We took iMetrics in China as the research case. 5,141 Chinese iMetrics related publications with 73,376 non-distinct cited references (CR) collected from the CSSCI were analyzed using RootCite. The results showed that the first CR in the field can be dated back to 1882 and written in English; but the majority (64.2%) of the CR in the field were Chinese publications. 17 peaks referring to 18 seminal works (13 in English and 5 in Chinese) were located during the period from 1900 to 2017. The field shared the same roots with that in the English world but has its own characteristics, and it was then shaped by contributions from both the English world and China. The five Chinese works have played irreplaceable and positive roles in the historical evolutionary path of the field, which should not be ignored, especially for the evolution of the field. This research demonstrated how RootCite aided the task of identifying the origin and evolution of research fields in China, which could be valuable for extending RPYS for countries with other languages.

cs.DL↗