arXiv subjects

Yi Bu

Publications and source records attributed to Yi Bu.

At least 19 recordsLinked to original sources

arXiv2026

The conservative turn in science: The changing character of knowledge recombination

This study examines how the dominant mode of cross-disciplinary knowledge combination has changed over time. It addresses a limitation of existing studies that document declining disruptiveness at the level of individual works but do not reveal whether the mechanisms of cross-disciplinary knowledge flow have themselves shifted. Drawing on 56 million publications and 816 million citations from OpenAlex (1960-2025), the study classifies cross-disciplinary citations into five types based on the set relationship between the subfield portfolios of citing and cited publications and introduces a semantic-distance measure derived from SPECTER-v2 embeddings of publication abstracts. It subsequently demonstrates that cross-disciplinary citations have shifted markedly away from configurations with no shared disciplinary ground toward types built on partially overlapping knowledge bases, a reorientation further reflected in a steady decline in average semantic distance between citing and cited fields. This shift co-occurs with a diffusion of brokerage positions across the network and a greater reliance on older literature, consistent with a system that has become broader and more decentralized in its interdisciplinary reach. Finally, this study discusses the implications of these findings for science policy and for the design of cross-disciplinary funding mechanisms.

cs.SI↗

arXiv2026

Translating AI into scientific impact: Field context, career position, and institutional capability in AI-enabled research

Artificial intelligence (AI) is increasingly embedded in scientific research, but its scientific value is unlikely to be distributed evenly. This study examines how AI knowledge integration is associated with scientific impact and asks who benefits from AI-related knowledge in science. Using large-scale bibliographic data, we measure AI integration through references to papers in the OpenAlex Artificial intelligence subfield and link it to five-year citation impact. The results show that AI references are generally associated with higher citation impact, but the returns vary substantially across scientific fields. Career stage also matters: senior scholars benefit more from the extensive margin of AI referencing, whereas junior scholars benefit more from intensive AI referencing and tend to cite newer and higher-impact AI papers. At the institutional level, returns are non-monotonic: institutions with intermediate AI capability achieve the largest proportional gains, while leading AI institutions are more deeply embedded in AI-centered knowledge spaces, attract more AI-related audiences, and more often become substitute citation gateways to cited AI sources. These findings suggest that the value of AI knowledge depends not only on technical capability, but also on translational capacity: the ability to make AI knowledge meaningful, legitimate, and useful across scientific communities.

cs.CY↗

arXiv2026

A Double Bind: Gendered Funding, Research Topics, and Academic Performance in the Social Sciences

While female representation in social sciences is increasing, systemic gender disparities may persist in research funding and academic performance. Some argue that female scholars now receive equal opportunities, yet evidence suggests that gender imbalances remain, particularly in specific research areas. This study examines 12,945 National Science Foundation (NSF)-funded principal investigators in social sciences from 2000 to 2019 to assess gender disparities in grant allocation, research topics, and post-award academic performance. Findings reveal a dual imbalance. First, despite similar overall funding success rates, female scholars remain underrepresented in high-impact and traditionally male-dominated research topics. Male recipients are more represented in most funded topics, especially technology- and methodology-related ones, whereas female recipients are more concentrated in a smaller set of topics related to children, family, cognition, and health. Second, post-award performance patterns suggest that females outperform males in male-dominated fields, whereas males excel in female-dominated ones, undermining any presumed advantage of female scholars in their own research areas. These patterns may be associated with gendered constraints in academic career trajectories. Furthermore, early-career experiences shape these outcomes asymmetrically. In male-dominated topics, postdoctoral experience is associated with lower publication and citation performance for women but higher publication and citation performance for men. In female-dominated topics, postdoctoral experience is positively associated with women's publications and citations and with men's publication output. These findings suggest that policy discussions should consider not just overall funding equality, but also gendered disparities across research topics and career trajectories.

cs.DL↗

arXiv2026

Smaller, Younger, and More Impactful: How AI-Assisted Writing Transforms Research Teams

The era of Big Science has long been defined by increasingly large and specialized research teams pushing the frontiers of knowledge. However, recent advances in artificial intelligence (AI), particularly large language models (LLMs), are beginning to reshape academic writing and scientific research, potentially disrupting the longstanding trend toward ever-larger teams and transforming other dimensions of research team structure. Drawing on 147,074 full-text publications from the PLoS family and the Nature portfolio since 2020, we examined whether and how AI-assisted writing influences team structure and team outcomes in science. Using multiple methods, including ordinary least square, quantile regression, Poisson regression, logistic regression and propensity score matching, we found that research teams using AI-assisted writing tend to be younger and smaller. Importantly, this shift toward more compact, junior-leaning teams does not come at the expense of scientific impact. On the contrary, we observed a higher probability of research teams that employed AI-assisted writing producing highly impactful publications. These results highlight the significant role of AI-assisted writing in reshaping not only how research is produced, but also how research teams are formed and assembled. Our findings call for policy improvements in research evaluation, funding, and training to address this emerging trend.

cs.CY↗

arXiv2026

Academic match-makers in sociology: Their role in collaboration network formation

In modern scientific collaboration networks, certain researchers play a pivotal role in bridging scholars who have never worked together - a phenomenon we term academic "match-makers." Despite their potential importance, the prevalence, characteristics, benefits, and long-term trajectory of these individuals remain underexplored. Using the Microsoft Academic Graph (MAG), we operationalized a match-maker as an author who, in a given publication, introduced a first-time collaboration between two co-authors, each of whom had previously collaborated with the match-maker but not with each other. We employed a configuration null model to distinguish observed patterns from random chance. Our findings reveal that the match-maker phenomenon is deliberate, prevalent, and consequential. Among authors with over 20 publications, nearly 30% have served as a match-maker, and the probability of acting as one increased eightfold from 1980 to 2019. Publications involving a match-maker are more likely to appear in high-impact journals and exhibit higher disruptiveness - particularly in larger teams - suggesting that match-makers help facilitate what we term integrative disruption. Match-makers tend to emerge early in their careers, peaking around the 20th publication and at an academic age of roughly ten years. While nearly all match-makers eventually experience "abandonment" in the sense that the connected researchers later collaborate without them, their continued involvement remains substantial and is driven by research needs rather than structural factors. This reframes abandonment not as exclusion but as a natural evolution within project-based collaborations. The academic match-maker phenomenon is a strategic feature of collaboration networks characterized by early-career emergence, context-dependent persistence, and tangible contributions to high-impact, disruptive research.

cs.DL↗

arXiv2026

RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation

Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most existing methods rely mainly on models internal parametric knowledge, without explicit grounding in external normative principles. This often leads to inconsistent judgments in socially nuanced contexts, limited interpretability, and redundant reasoning across turns. To address this, we propose RoTRAG, a retrieval augmented framework that incorporates concise human written moral norms, called Rules of Thumb (RoTs), into LLM based harm assessment. For each turn, RoTRAG retrieves relevant RoTs from an external corpus and uses them as explicit normative evidence for turn level reasoning and final severity classification. To improve efficiency, we further introduce a lightweight binary routing classifier that decides whether a new turn requires retrieval grounded reasoning or can reuse existing context. Experiments on ProsocialDialog and Safety Reasoning Multi Turn Dialogue show that RoTRAG consistently improves both harm classification and severity estimation over competitive baselines, with an average relative gain of around 40% in F1 across benchmark datasets and an average relative reduction of 8.4% in distributional error, while reducing redundant computation without sacrificing performance.

cs.CL↗

arXiv2026

A Semantic Geometry for Uncovering Paradigm Dynamics via Scientific Publications

Science advances not only by accumulating discovered patterns but by changing how new problems and solutions are expressed. While structural indicators track scholarly attention, they offer only an indirect proxy for the reorganization of meaning. We propose a semantic geometry based on the R-P-C (references, focal publication, and citing publications) framework to quantify how a publication positions itself relative to its knowledge base and diffusion. This geometry identifies three publication types: consolidating, exploratory and balanced. Our results show that the semantic similarity and distance between a publication's knowledge base and diffusion serve as a semantic foundation for disruption, with novelty (atypical reference combinations) acting as an antecedent disturbance that triggers a semantic rupture. This is related to team size, where small teams preserve a higher potential for exploratory departures while large collaborations systematically align with paradigmatic consolidation. Crucially, this geometry explains why citation trajectories differ; consolidating research earns rapid recognition by lowering comprehension costs, while exploratory work faces high paradigm conversion costs that result in slower, more selective diffusion. Collectively, this R-P-C framework provides a robust instrument for monitoring the dynamics of scientific paradigms.

cs.DL↗

arXiv2026

Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning

Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured value representations. Existing methods can steer outputs, but often lack demographic grounding and treat values as independent, unstructured signals, reducing consistency and interpretability. We propose OG-MAR, an Ontology-Guided Multi-Agent Reasoning framework. OG-MAR summarizes respondent-specific values from the World Values Survey (WVS) and constructs a global cultural ontology by eliciting relations over a fixed taxonomy via competency questions. At inference time, it retrieves ontology-consistent relations and demographically similar profiles to instantiate multiple value-persona agents, whose outputs are synthesized by a judgment agent that enforces ontology consistency and demographic proximity. Experiments on regional social-survey benchmarks across four LLM backbones show that OG-MAR improves cultural alignment and robustness over competitive baselines, while producing more transparent reasoning traces.

cs.CL↗

arXiv2026

Scilit with the Integrated Impact Indicator Assessment

In this study, we systematically elucidate the background and functionality of the Scilit database and evaluate the feasibility and advantages of the comprehensive impact metrics I3 and I3/N, introduced within the Scilit framework. Using a matched dataset of 17,816 journals, we conduct a comparative analysis of Scilit I3/N, Journal Impact Factor, and CiteScore for 2023 and 2024, covering descriptive statistics and distributional characteristics from both disciplinary and publisher perspectives. The comparison reveals that the Scilit I3 and I3/N framework significantly outperforms traditional mean-based metrics in terms of coverage, methodological robustness, and disciplinary fairness. It provides a more accurate, diagnosable, and responsible solution for interdisciplinary journal impact assessment. Our research serves as a "getting started guide" for Scilit, offering scholars, librarians, and academic publishers in the fields of bibliometrics or scientometrics a valuable perspective for exploring I3 and I3/N within an inclusive database. This enables a more accurate and comprehensive understanding of disciplinary development and scientific progress. We advocate for piloting and validating this method in broader evaluation contexts to foster a more precise and diverse representation of scientific progress.

cs.DL↗

arXiv2025

Academic journals' AI policies fail to curb the surge in AI-assisted academic writing

The rapid integration of generative AI into academic writing has prompted widespread policy responses from journals and publishers. However, the effectiveness of these policies remains unclear. Here, we analyze 5,114 journals and over 5.2 million papers to evaluate the real-world impact of AI usage guidelines. We show that despite 70% of journals adopting AI policies (primarily requiring disclosure), researchers' use of AI writing tools has increased dramatically across disciplines, with no significant difference between journals with or without policies. Non-English-speaking countries, physical sciences, and high-OA journals exhibit the highest growth rates. Crucially, full-text analysis on 164k scientific publications reveals a striking transparency gap: Of the 75k papers published since 2023, only 76 (~0.1%) explicitly disclosed AI use. Our findings suggest that current policies have largely failed to promote transparency or restrain AI adoption. We urge a re-evaluation of ethical frameworks to foster responsible AI integration in science.

cs.AI↗

arXiv2025

AI-Assisted Writing Is Growing Fastest Among Less Established Scientists in Non-English-Speaking Countries

The recent emergence of AI-assisted writing raises an important question: how is this new technology being adopted across the scientific community, and how does adoption vary across linguistic and professional contexts? We analyze over two million full-text biomedical publications from PubMed Central from 2021 to 2024 using a distribution-based framework to estimate AI-generated content. We found that, in biomedical publications, AI-generated content increased substantially after ChatGPT, with larger increases in publications from countries with lower English proficiency. Increases were also greater among scientists with fewer publications and citations, those at earlier career stages, and those at lower-ranked institutions. Prior AI research experience was associated with greater increases in AI-assisted writing, which were also modestly associated with greater increases in publication productivity. These findings show that AI-assisted writing is growing fastest among biomedical scientists who may have historically faced barriers, a pattern with potentially positive implications for equity in science.

cs.DL↗

arXiv2025

MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization

Prompt optimization has become a practical way to improve the performance of Large Language Models (LLMs) without retraining. However, most existing frameworks treat evaluation as a black box, relying solely on outcome scores without explaining why prompts succeed or fail. Moreover, they involve repetitive trial-and-error refinements that remain implicit, offering limited interpretability or actionable guidance for systematic improvement. In this paper, we propose MA-SAPO: a new Multi-Agent Reasoning for Score Aware Prompt Optimization framework that links evaluation outcomes directly to targeted refinements. Specifically, in the Training Phase, multiple agents interpret evaluation scores, diagnose weaknesses, and generate concrete revision directives, which are stored as reusable reasoning assets. In the Test Phase, an analyzer agent retrieves relevant exemplars and assets for a new prompt, and a refiner agent applies evidence-based edits to improve the prompt and its response. By grounding optimization in structured reasoning, MA-SAPO ensures edits are interpretable, auditable, and controllable. Experiments on the HelpSteer1/2 benchmarks show that our framework consistently outperforms single-pass prompting, retrieval-augmented generation, and prior multi-agent methods across multiple evaluation metrics.

cs.MA↗

arXiv2025

Better by Comparison: Retrieval-Augmented Contrastive Reasoning for Automatic Prompt Optimization

Automatic prompt optimization has recently emerged as a strategy for improving the quality of prompts used in Large Language Models (LLMs), with the goal of generating more accurate and useful responses. However, most prior work focuses on direct prompt refinement or model fine-tuning, overlooking the potential of leveraging LLMs' inherent reasoning capability to learn from contrasting examples. In this paper, we present Contrastive Reasoning Prompt Optimization (CRPO), a novel framework that formulates prompt optimization as a retrieval-augmented reasoning process. Our approach retrieves top k reference prompt-response pairs from the HelpSteer2 dataset, an open source collection where each response is annotated for helpfulness, correctness, coherence, complexity, and verbosity, and constructs two complementary optimization paradigms: (1) tiered contrastive reasoning, where the LLM compares high-, medium-, and low-quality exemplars (both prompts and responses) to refine its own generation through reflective reasoning, and (2) multi-metric contrastive reasoning, where the LLM analyzes the best exemplars along each evaluation dimension and integrates their strengths into an optimized prompt. By explicitly contrasting high and low quality exemplars, CRPO enables the model to deduce why certain prompts succeed while others fail, thereby achieving more robust and interpretable optimization. Experimental results on the HelpSteer2 benchmark demonstrate that CRPO significantly outperforms baselines. Our findings highlight the promise of contrastive, retrieval-augmented reasoning for advancing automatic prompt optimization.

cs.CL↗

arXiv2025

Understanding discrepancies in the coverage of OpenAlex: the case of China

Citation indexes play a crucial role for understanding how science is produced, disseminated, and used. However, these databases often face a critical trade-off: those offering extensive and high-quality coverage are typically proprietary, whereas publicly accessible datasets frequently exhibit fragmented coverage and inconsistent data quality. OpenAlex was developed to address this challenge, providing a freely available database with broad open coverage, with a particular emphasis on non-English speaking countries. Yet, few studies have assessed the quality of the OpenAlex dataset. This paper assesses the coverage, by OpenAlex, of China's papers, which shows an abnormal trend, and compares it with other countries that do not have English as their main language. Our analysis reveals that while OpenAlex increases the coverage of China's publications, primarily those disseminated by a national database, this coverage is incomplete and discontinuous when compared to other countries' records in the database. We observe similar issues in other non-English-speaking countries, with coverage varying across regions. These findings indicate that although OpenAlex expands coverage of research outputs, continuity issues persist and disproportionately affect certain countries. We emphasize the need for researchers to use OpenAlex data cautiously, being mindful of its potential limitations in cross-national analyses.

cs.DL↗

arXiv2025

Dynamic disruption index across citation and cited references windows: Recommendations for thresholds in research evaluation

The temporal dimension of citation accumulation poses fundamental challenges for quantitative research evaluations, particularly in assessing disruptive and consolidating research through the disruption index (D). While prior studies emphasize minimum citation windows (mostly 3-5 years) for reliable citation impact measurements, the time-sensitive nature of D - which quantifies a paper' s capacity to eclipse prior knowledge - remains underexplored. This study addresses two critical gaps: (1) determining the temporal thresholds required for publications to meet citation/reference prerequisites, and (2) identifying "optimal" citation windows that balance early predictability and longitudinal validity. By analyzing millions of publications across four fields with varying citation dynamics, we employ some metrics to track D stabilization patterns. Key findings reveal that a 10-year window achieves >80% agreement with final D classifications, while shorter windows (3 years) exhibit instability. Publications with >=30 references stabilize 1-3 years faster, and extreme cases (top/bottom 5% D values) become identifiable within 5 years - enabling early detection of 60-80% of highly disruptive and consolidating works. The findings offer significant implications for scholarly evaluation and science policy, emphasizing the need for careful consideration of citation window length in research assessment (based on D).

cs.DL↗

arXiv2025

SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science

Large Language Models (LLMs) have enabled dynamic reasoning in automated data analytics, yet recent multi-agent systems remain limited by rigid, single-path workflows that restrict strategic exploration and often lead to suboptimal outcomes. To overcome these limitations, we propose SPIO (Sequential Plan Integration and Optimization), a framework that replaces rigid workflows with adaptive, multi-path planning across four core modules: data preprocessing, feature engineering, model selection, and hyperparameter tuning. In each module, specialized agents generate diverse candidate strategies, which are cascaded and refined by an optimization agent. SPIO offers two operating modes: SPIO-S for selecting a single optimal pipeline, and SPIO-E for ensembling top-k pipelines to maximize robustness. Extensive evaluations on Kaggle and OpenML benchmarks show that SPIO consistently outperforms state-of-the-art baselines, achieving an average performance gain of 5.6%. By explicitly exploring and integrating multiple solution paths, SPIO delivers a more flexible, accurate, and reliable foundation for automated data science.

cs.AI↗

arXiv2025

Automated Visualization Code Synthesis via Multi-Path Reasoning and Feedback-Driven Optimization

Large Language Models (LLMs) have become a cornerstone for automated visualization code generation, enabling users to create charts through natural language instructions. Despite improvements from techniques like few-shot prompting and query expansion, existing methods often struggle when requests are underspecified in actionable details (e.g., data preprocessing assumptions, solver or library choices, etc.), frequently necessitating manual intervention. To overcome these limitations, we propose VisPath: a Multi-Path Reasoning and Feedback-Driven Optimization Framework for Visualization Code Generation. VisPath handles underspecified queries through structured, multi-stage processing. It begins by using Chain-of-Thought (CoT) prompting to reformulate the initial user input, generating multiple extended queries in parallel to surface alternative plausible concretizations of the request. These queries then generate candidate visualization scripts, which are executed to produce diverse images. By assessing the visual quality and correctness of each output, VisPath generates targeted feedback that is aggregated to synthesize an optimal final result. Extensive experiments on MatPlotBench and Qwen-Agent Code Interpreter Benchmark show that VisPath outperforms state-of-the-art methods, providing a more reliable framework for AI-driven visualization generation.

cs.SE↗

arXiv2025

Position: Open and Closed Large Language Models in Healthcare

This position paper analyzes the evolving roles of open-source and closed-source large language models (LLMs) in healthcare, emphasizing their distinct contributions and the scientific community's response to their development. Due to their advanced reasoning capabilities, closed LLMs, such as GPT-4, have dominated high-performance applications, particularly in medical imaging and multimodal diagnostics. Conversely, open LLMs, like Meta's LLaMA, have gained popularity for their adaptability and cost-effectiveness, enabling researchers to fine-tune models for specific domains, such as mental health and patient communication.

cs.CY↗