🎯 Top Personalized Recommendations
FUTA
Why we think this paper is great for you:
This paper directly addresses the critical role of women's empowerment in improving public health outcomes, particularly in vulnerable populations. It offers valuable insights into measurable interventions for societal well-being.
This paper directly addresses the critical role of women's empowerment in improving public health outcomes, particularly in vulnerable populations. It offers valuable insights into measurable interventions for societal well-being.
Abstract
Immunization remains one of the most effective public health interventions, substantially reducing childhood morbidity and mortality worldwide. Yet, gender disparity and women's disempowerment continue to hinder access to vaccination services in low- and middle-income countries. In Nigeria, variations in social norms and cultural values shape gender roles, limiting women's autonomy in healthcare decisions and household participation. These constraints contribute to spatial differences in immunization uptake. Using data from four waves of the Nigeria Demographic and Health Survey, we developed two empowerment indices capturing women's participation in household decision-making and their ability to decide on personal healthcare needs. A structured spatiotemporal statistical model was applied to assess how much of the observed vaccination disparities could be attributed to women's empowerment and to predict vaccination outcomes at the third administrative level. We examined five indicators: Bacillus Calmette-Guerin (BCG), zero-dose, complete DPT, MCV-1 (first dose of measles-containing vaccine), and all-basic vaccination coverage. Model validation involved comparing empirical estimates with projections at the second administrative level. Results indicate that empowerment related to household participation and healthcare autonomy generally increases vaccination uptake, though the magnitude of effects varies geographically, particularly among highly empowered women. Despite ongoing national efforts to close immunization gaps, the study highlights the need for context-specific strategies that enhance women's decision-making power and community engagement to reduce regional disparities and improve overall vaccination coverage.
Immunization remains one of the most effective public health interventions, substantially reducing childhood morbidity and mortality worldwide. Yet, gender disparity and women's disempowerment continue to hinder access to vaccination services in low- and middle-income countries. In Nigeria, variations in social norms and cultural values shape gender roles, limiting women's autonomy in healthcare decisions and household participation. These constraints contribute to spatial differences in immunization uptake. Using data from four waves of the Nigeria Demographic and Health Survey, we developed two empowerment indices capturing women's participation in household decision-making and their ability to decide on personal healthcare needs. A structured spatiotemporal statistical model was applied to assess how much of the observed vaccination disparities could be attributed to women's empowerment and to predict vaccination outcomes at the third administrative level. We examined five indicators: Bacillus Calmette-Guerin (BCG), zero-dose, complete DPT, MCV-1 (first dose of measles-containing vaccine), and all-basic vaccination coverage. Model validation involved comparing empirical estimates with projections at the second administrative level. Results indicate that empowerment related to household participation and healthcare autonomy generally increases vaccination uptake, though the magnitude of effects varies geographically, particularly among highly empowered women. Despite ongoing national efforts to close immunization gaps, the study highlights the need for context-specific strategies that enhance women's decision-making power and community engagement to reduce regional disparities and improve overall vaccination coverage.
AI Summary
- In northern Nigeria, specific interventions are needed to link immunization with antenatal and delivery services, expand health facility-based births, and combat vaccine mistrust through community and religious engagement, as even empowered women in these regions show lower BCG uptake. [3]
- Women's Empowerment Indices: Two specific indices constructed using factor analysis from Nigeria Demographic and Health Survey (NDHS) data: (1) household decision-making (DM) and (2) healthcare utilization (HC). [3]
- The positive impact of women's empowerment on vaccination uptake is not uniform; highly empowered women exhibit pronounced inequalities in immunization, suggesting potential conflicts with other economic or social activities that limit their ability to prioritize vaccination. [2]
- Tailored public health strategies are crucial, focusing on up-scaling women's ability to participate in decision-making and decide on healthcare needs, especially in regions with persistent disparities, to effectively bridge immunization gaps. [2]
- Supportive health system structures, such as flexible clinic hours, mobile outreach programs, targeted health communication, and community childcare support, must complement empowerment initiatives to ensure improved vaccination outcomes, particularly for working mothers. [2]
- Addressing structural and contextual barriers like poor road networks, long travel times to health facilities, vaccine stock-outs, and shortages of skilled health personnel is as critical as women's empowerment for eliminating inequalities in immunization uptake. [2]
- The consistently low coverage for all basic vaccinations (around 10% nationwide throughout the study period) highlights a systemic failure that requires comprehensive, multi-faceted interventions beyond individual empowerment. [2]
- These are categorized into 'not empowered', 'moderately empowered', and 'highly empowered' tertiles. [2]
- Spatio-temporal Statistical Model: A structured Bayesian model (implemented using R-INLA) that accounts for both geographical (spatial) and time-varying (temporal) patterns of vaccine coverage, integrating women's empowerment indicators as key covariates. [2]
- Intrinsic Conditional Autoregressive (ICAR) Model: A spatial statistical model used to define the conditional prior distribution for the latent spatiotemporal effects (γ_jt), allowing for borrowing strength across neighboring Local Government Areas (LGAs) to improve local estimates. [2]
- Women's empowerment, particularly in household decision-making and healthcare utilization, is generally associated with increased childhood vaccination uptake in Nigeria, but its effects vary significantly across geographical locations and empowerment levels. [1]
Imperial College
Why we think this paper is great for you:
This work provides a fundamental understanding of how socio-economic structures emerge and contribute to wealth concentration. It offers a theoretical framework for analyzing and potentially addressing societal disparities.
This work provides a fundamental understanding of how socio-economic structures emerge and contribute to wealth concentration. It offers a theoretical framework for analyzing and potentially addressing societal disparities.
Abstract
Bridging the gap between individual agent behavior and macroscopic societal patterns is a central challenge in the social sciences. In this work, we propose a solution to this problem via a kinetic theory formulation. We demonstrate that complex, empirically-observed phenomena, such as the concentration of populations in cities and the emergence of power-law wealth distributions, can be derived directly from a microscopic model of agents governed by underdamped Langevin dynamics. Our multi-scale derivation yields the exact mesoscopic fluctuating (Dean-Kawasaki) dynamics and the macroscopic Vlasov-Fokker-Planck system of equations. The analytical solution of this system reveals how a heterogeneous resource landscape alone is sufficient to generate the coupled structures of spatial and economic inequality, thus providing a formal link between micro-level stochasticity and macro-level deterministic order.
Bridging the gap between individual agent behavior and macroscopic societal patterns is a central challenge in the social sciences. In this work, we propose a solution to this problem via a kinetic theory formulation. We demonstrate that complex, empirically-observed phenomena, such as the concentration of populations in cities and the emergence of power-law wealth distributions, can be derived directly from a microscopic model of agents governed by underdamped Langevin dynamics. Our multi-scale derivation yields the exact mesoscopic fluctuating (Dean-Kawasaki) dynamics and the macroscopic Vlasov-Fokker-Planck system of equations. The analytical solution of this system reveals how a heterogeneous resource landscape alone is sufficient to generate the coupled structures of spatial and economic inequality, thus providing a formal link between micro-level stochasticity and macro-level deterministic order.
Why we think this paper is great for you:
This paper delves into the long-term consequences of policy decisions like school choice on wealth segregation, offering crucial insights into factors that perpetuate societal divides. It highlights systemic issues impacting equitable opportunities.
This paper delves into the long-term consequences of policy decisions like school choice on wealth segregation, offering crucial insights into factors that perpetuate societal divides. It highlights systemic issues impacting equitable opportunities.
Abstract
We study how school choice mechanisms shape wealth segregation in the long term by endogenizing residential choice. Families buy houses in school zones that determine admission priority, experience shocks to school preferences, and participate in one of three mechanisms: neighborhood assignment (N), Deferred Acceptance (DA), or Top Trading Cycles (TTC). Neighborhood segregation increases from N to DA to TTC. DA and TTC reduce school-level segregation relative to neighborhoods but typically not enough to reverse this ranking, and housing prices in oversubscribed zones rise in the same order. Two desegregation policies further illustrate how short- and long-term perspectives can differ.
We study how school choice mechanisms shape wealth segregation in the long term by endogenizing residential choice. Families buy houses in school zones that determine admission priority, experience shocks to school preferences, and participate in one of three mechanisms: neighborhood assignment (N), Deferred Acceptance (DA), or Top Trading Cycles (TTC). Neighborhood segregation increases from N to DA to TTC. DA and TTC reduce school-level segregation relative to neighborhoods but typically not enough to reverse this ranking, and housing prices in oversubscribed zones rise in the same order. Two desegregation policies further illustrate how short- and long-term perspectives can differ.
Why we think this paper is great for you:
This paper explores how AI can be leveraged to restore trust in public discourse and ensure fair participation in societal dynamics. It offers a practical application of technology for enhancing social good.
This paper explores how AI can be leveraged to restore trust in public discourse and ensure fair participation in societal dynamics. It offers a practical application of technology for enhancing social good.
Abstract
The emergence of crowdsourced data has significantly reshaped social science, enabling extensive exploration of collective human actions, viewpoints, and societal dynamics. However, ensuring safe, fair, and reliable participation remains a persistent challenge. Traditional polling methods have seen a notable decline in engagement over recent decades, raising concerns about the credibility of collected data. Meanwhile, social and peer-to-peer networks have become increasingly widespread, but data from these platforms can suffer from credibility issues due to fraudulent or ineligible participation. In this paper, we explore how social interactions can help restore credibility in crowdsourced data collected over social networks. We present an empirical study to detect ineligible participation in a polling task through AI-based graph analysis of social interactions among imperfect participants composed of honest and dishonest actors. Our approach focuses solely on the structure of social interaction graphs, without relying on the content being shared. We simulate different levels and types of dishonest behavior among participants who attempt to propagate the task within their social networks. We conduct experiments on real-world social network datasets, using different eligibility criteria and modeling diverse participation patterns. Although structural differences in social interaction graphs introduce some performance variability, our study achieves promising results in detecting ineligibility across diverse social and behavioral profiles, with accuracy exceeding 90% in some configurations.
The emergence of crowdsourced data has significantly reshaped social science, enabling extensive exploration of collective human actions, viewpoints, and societal dynamics. However, ensuring safe, fair, and reliable participation remains a persistent challenge. Traditional polling methods have seen a notable decline in engagement over recent decades, raising concerns about the credibility of collected data. Meanwhile, social and peer-to-peer networks have become increasingly widespread, but data from these platforms can suffer from credibility issues due to fraudulent or ineligible participation. In this paper, we explore how social interactions can help restore credibility in crowdsourced data collected over social networks. We present an empirical study to detect ineligible participation in a polling task through AI-based graph analysis of social interactions among imperfect participants composed of honest and dishonest actors. Our approach focuses solely on the structure of social interaction graphs, without relying on the content being shared. We simulate different levels and types of dishonest behavior among participants who attempt to propagate the task within their social networks. We conduct experiments on real-world social network datasets, using different eligibility criteria and modeling diverse participation patterns. Although structural differences in social interaction graphs introduce some performance variability, our study achieves promising results in detecting ineligibility across diverse social and behavioral profiles, with accuracy exceeding 90% in some configurations.
Penn State University
Why we think this paper is great for you:
This research directly tackles the fundamental concept of equitability and fair division, which is essential for understanding and mitigating various forms of societal imbalance. It provides a theoretical basis for achieving more just distributions.
This research directly tackles the fundamental concept of equitability and fair division, which is essential for understanding and mitigating various forms of societal imbalance. It provides a theoretical basis for achieving more just distributions.
Abstract
Equitability is a fundamental notion in fair division which requires that all agents derive equal value from their allocated bundles. We study, for general (possibly non-monotone) valuations, a popular relaxation of equitability known as equitability up to one item (EQ1). An EQ1 allocation may fail to exist even with additive non-monotone valuations; for instance, when there are two agents, one valuing every item positively and the other negatively. This motivates a mild and natural assumption: all agents agree on the sign of their value for the grand bundle. Under this assumption, we prove the existence and provide an efficient algorithm for computing EQ1 allocations for two agents with general valuations. When there are more than two agents, we show the existence and polynomial-time computability of EQ1 allocations for valuation classes beyond additivity and monotonicity, in particular for (1) doubly monotone valuations and (2) submodular (resp. supermodular) valuations where the value for the grand bundle is nonnegative (resp. nonpositive) for all agents. Furthermore, we settle an open question of Bil`o et al. by showing that an EQ1 allocation always exists for nonnegative(resp. nonpositive) valuations, i.e., when every agent values each subset of items nonnegatively (resp. nonpositively). Finally, we complete the picture by showing that for general valuations with more than two agents, EQ1 allocations may not exist even when agents agree on the sign of the grand bundle, and that deciding the existence of an EQ1 allocation is computationally intractable.
Equitability is a fundamental notion in fair division which requires that all agents derive equal value from their allocated bundles. We study, for general (possibly non-monotone) valuations, a popular relaxation of equitability known as equitability up to one item (EQ1). An EQ1 allocation may fail to exist even with additive non-monotone valuations; for instance, when there are two agents, one valuing every item positively and the other negatively. This motivates a mild and natural assumption: all agents agree on the sign of their value for the grand bundle. Under this assumption, we prove the existence and provide an efficient algorithm for computing EQ1 allocations for two agents with general valuations. When there are more than two agents, we show the existence and polynomial-time computability of EQ1 allocations for valuation classes beyond additivity and monotonicity, in particular for (1) doubly monotone valuations and (2) submodular (resp. supermodular) valuations where the value for the grand bundle is nonnegative (resp. nonpositive) for all agents. Furthermore, we settle an open question of Bil`o et al. by showing that an EQ1 allocation always exists for nonnegative(resp. nonpositive) valuations, i.e., when every agent values each subset of items nonnegatively (resp. nonpositively). Finally, we complete the picture by showing that for general valuations with more than two agents, EQ1 allocations may not exist even when agents agree on the sign of the grand bundle, and that deciding the existence of an EQ1 allocation is computationally intractable.
Why we think this paper is great for you:
This paper is highly relevant as it focuses on improving methods for understanding human attitudes and preferences, which is crucial for informed policymaking and fostering a more inclusive society. It addresses challenges in ensuring broad representation.
This paper is highly relevant as it focuses on improving methods for understanding human attitudes and preferences, which is crucial for informed policymaking and fostering a more inclusive society. It addresses challenges in ensuring broad representation.
Abstract
Understanding human attitudes, preferences, and behaviors through social surveys is essential for academic research and policymaking. Yet traditional surveys face persistent challenges, including fixed-question formats, high costs, limited adaptability, and difficulties ensuring cross-cultural equivalence. While recent studies explore large language models (LLMs) to simulate survey responses, most are limited to structured questions, overlook the entire survey process, and risks under-representing marginalized groups due to training data biases. We introduce AlignSurvey, the first benchmark that systematically replicates and evaluates the full social survey pipeline using LLMs. It defines four tasks aligned with key survey stages: social role modeling, semi-structured interview modeling, attitude stance modeling and survey response modeling. It also provides task-specific evaluation metrics to assess alignment fidelity, consistency, and fairness at both individual and group levels, with a focus on demographic diversity. To support AlignSurvey, we construct a multi-tiered dataset architecture: (i) the Social Foundation Corpus, a cross-national resource with 44K+ interview dialogues and 400K+ structured survey records; and (ii) a suite of Entire-Pipeline Survey Datasets, including the expert-annotated AlignSurvey-Expert (ASE) and two nationally representative surveys for cross-cultural evaluation. We release the SurveyLM family, obtained through two-stage fine-tuning of open-source LLMs, and offer reference models for evaluating domain-specific alignment. All datasets, models, and tools are available at github and huggingface to support transparent and socially responsible research.
Understanding human attitudes, preferences, and behaviors through social surveys is essential for academic research and policymaking. Yet traditional surveys face persistent challenges, including fixed-question formats, high costs, limited adaptability, and difficulties ensuring cross-cultural equivalence. While recent studies explore large language models (LLMs) to simulate survey responses, most are limited to structured questions, overlook the entire survey process, and risks under-representing marginalized groups due to training data biases. We introduce AlignSurvey, the first benchmark that systematically replicates and evaluates the full social survey pipeline using LLMs. It defines four tasks aligned with key survey stages: social role modeling, semi-structured interview modeling, attitude stance modeling and survey response modeling. It also provides task-specific evaluation metrics to assess alignment fidelity, consistency, and fairness at both individual and group levels, with a focus on demographic diversity. To support AlignSurvey, we construct a multi-tiered dataset architecture: (i) the Social Foundation Corpus, a cross-national resource with 44K+ interview dialogues and 400K+ structured survey records; and (ii) a suite of Entire-Pipeline Survey Datasets, including the expert-annotated AlignSurvey-Expert (ASE) and two nationally representative surveys for cross-cultural evaluation. We release the SurveyLM family, obtained through two-stage fine-tuning of open-source LLMs, and offer reference models for evaluating domain-specific alignment. All datasets, models, and tools are available at github and huggingface to support transparent and socially responsible research.
KIT
Why we think this paper is great for you:
This paper is a strong match because it investigates how to optimize human-AI collaboration for better decision-making, which is vital for effectively deploying AI solutions for societal benefit. It ensures that AI tools are used wisely to achieve positive outcomes.
This paper is a strong match because it investigates how to optimize human-AI collaboration for better decision-making, which is vital for effectively deploying AI solutions for societal benefit. It ensures that AI tools are used wisely to achieve positive outcomes.
Abstract
Collaboration with artificial intelligence (AI) has improved human decision-making across various domains by leveraging the complementary capabilities of humans and AI. Yet, humans systematically overrely on AI advice, even when their independent judgment would yield superior outcomes, fundamentally undermining the potential of human-AI complementarity. Building on prior work, we identify prevailing incentive structures in human-AI decision-making as a structural driver of this overreliance. To address this misalignment, we propose an alternative incentive mechanism designed to counteract systemic overreliance. We empirically evaluate this approach through a behavioral experiment with 180 participants, finding that the proposed mechanism significantly reduces overreliance. We also show that while appropriately designed incentives can enhance collaboration and decision quality, poorly designed incentives may distort behavior, introduce unintended consequences, and ultimately degrade performance. These findings underscore the importance of aligning incentives with task context and human-AI complementarities, and suggest that effective collaboration requires a shift toward context-sensitive incentive design.
Collaboration with artificial intelligence (AI) has improved human decision-making across various domains by leveraging the complementary capabilities of humans and AI. Yet, humans systematically overrely on AI advice, even when their independent judgment would yield superior outcomes, fundamentally undermining the potential of human-AI complementarity. Building on prior work, we identify prevailing incentive structures in human-AI decision-making as a structural driver of this overreliance. To address this misalignment, we propose an alternative incentive mechanism designed to counteract systemic overreliance. We empirically evaluate this approach through a behavioral experiment with 180 participants, finding that the proposed mechanism significantly reduces overreliance. We also show that while appropriately designed incentives can enhance collaboration and decision quality, poorly designed incentives may distort behavior, introduce unintended consequences, and ultimately degrade performance. These findings underscore the importance of aligning incentives with task context and human-AI complementarities, and suggest that effective collaboration requires a shift toward context-sensitive incentive design.
Inequality
Abstract
Two types of Bernstein inequalities are established on the unit ball in $\mathbb{R}^d$, which are stronger than those known in the literature. The first type consists of inequalities in $L^p$ norm for a fully symmetric doubling weight on the unit ball. The second type consists of sharp inequalities in $L^2$ norm for the Jacobi weight, which are established via a new self-adjoint form of the spectral operator that has orthogonal polynomials as eigenfunctions.
Two types of Bernstein inequalities are established on the unit ball in $\mathbb{R}^d$, which are stronger than those known in the literature. The first type consists of inequalities in $L^p$ norm for a fully symmetric doubling weight on the unit ball. The second type consists of sharp inequalities in $L^2$ norm for the Jacobi weight, which are established via a new self-adjoint form of the spectral operator that has orthogonal polynomials as eigenfunctions.
Abstract
In this paper, we provide suitable characterisations of pairs of weights $(V,W),$ known as Bessel pairs, that ensure the validity of weighted Hardy-type inequalities. The abstract approach adopted here makes it possible to establish such inequalities also going beyond the classical Euclidean setting and also within a more general $L^p$ framework. As a byproduct of our method, we obtain explicit expressions for the maximizing functions and, in certain specific situations, we show that the associated constants are sharp. We emphasise that our approach unifies, generalises and improves several existing results in the literature.
In this paper, we provide suitable characterisations of pairs of weights $(V,W),$ known as Bessel pairs, that ensure the validity of weighted Hardy-type inequalities. The abstract approach adopted here makes it possible to establish such inequalities also going beyond the classical Euclidean setting and also within a more general $L^p$ framework. As a byproduct of our method, we obtain explicit expressions for the maximizing functions and, in certain specific situations, we show that the associated constants are sharp. We emphasise that our approach unifies, generalises and improves several existing results in the literature.
Casual ML for Social Good
Xiaohongshu Inc
Abstract
As a key medium for human interaction and information exchange, social networking services (SNS) pose unique challenges for large language models (LLMs): heterogeneous workloads, fast-shifting norms and slang, and multilingual, culturally diverse corpora that induce sharp distribution shift. Supervised fine-tuning (SFT) can specialize models but often triggers a ``seesaw'' between in-distribution gains and out-of-distribution robustness, especially for smaller models. To address these challenges, we introduce RedOne 2.0, an SNS-oriented LLM trained with a progressive, RL-prioritized post-training paradigm designed for rapid and stable adaptation. The pipeline consist in three stages: (1) Exploratory Learning on curated SNS corpora to establish initial alignment and identify systematic weaknesses; (2) Targeted Fine-Tuning that selectively applies SFT to the diagnosed gaps while mixing a small fraction of general data to mitigate forgetting; and (3) Refinement Learning that re-applies RL with SNS-centric signals to consolidate improvements and harmonize trade-offs across tasks. Across various tasks spanning three categories, our 4B scale model delivers an average improvements about 2.41 over the 7B sub-optimal baseline. Additionally, RedOne 2.0 achieves average performance lift about 8.74 from the base model with less than half the data required by SFT-centric method RedOne, evidencing superior data efficiency and stability at compact scales. Overall, RedOne 2.0 establishes a competitive, cost-effective baseline for domain-specific LLMs in SNS scenario, advancing capability without sacrificing robustness.
As a key medium for human interaction and information exchange, social networking services (SNS) pose unique challenges for large language models (LLMs): heterogeneous workloads, fast-shifting norms and slang, and multilingual, culturally diverse corpora that induce sharp distribution shift. Supervised fine-tuning (SFT) can specialize models but often triggers a ``seesaw'' between in-distribution gains and out-of-distribution robustness, especially for smaller models. To address these challenges, we introduce RedOne 2.0, an SNS-oriented LLM trained with a progressive, RL-prioritized post-training paradigm designed for rapid and stable adaptation. The pipeline consist in three stages: (1) Exploratory Learning on curated SNS corpora to establish initial alignment and identify systematic weaknesses; (2) Targeted Fine-Tuning that selectively applies SFT to the diagnosed gaps while mixing a small fraction of general data to mitigate forgetting; and (3) Refinement Learning that re-applies RL with SNS-centric signals to consolidate improvements and harmonize trade-offs across tasks. Across various tasks spanning three categories, our 4B scale model delivers an average improvements about 2.41 over the 7B sub-optimal baseline. Additionally, RedOne 2.0 achieves average performance lift about 8.74 from the base model with less than half the data required by SFT-centric method RedOne, evidencing superior data efficiency and stability at compact scales. Overall, RedOne 2.0 establishes a competitive, cost-effective baseline for domain-specific LLMs in SNS scenario, advancing capability without sacrificing robustness.
Interests not found
We did not find any papers that match the below interests.
Try other terms also consider if the content exists in arxiv.org.
- Healthy Society
- Animal Welfare
- Tech for Social Good
- Racism
You can edit or add more interests any time.
Help us improve your experience!
This project is on its early stages your feedback can be pivotal on the future of the project.
Let us know what you think about this week's papers and suggestions!
Give Feedback