arXiv subjects

Meeyoung Cha

Publications and source records attributed to Meeyoung Cha.

At least 37 records · Page 2Linked to original sources

arXiv2026

ERA: Evidence-based Reliability Alignment for Honest Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) grounds language models in factual evidence but introduces critical challenges regarding knowledge conflicts between internalized parameters and retrieved information. However, existing reliability methods, typically relying on scalar confidence, fail to explicitly distinguish between epistemic uncertainty and inherent data ambiguity in such hybrid scenarios. In this paper, we propose a new framework called ERA (Evidence-based Reliability Alignment) to enhance abstention behavior in RAG systems by shifting confidence estimation from scalar probabilities to explicit evidence distributions. Our method consists of two main components: (1) Contextual Evidence Quantification, which models internal and external knowledge as independent belief masses via the Dirichlet distribution, and (2) Quantifying Knowledge Conflict, which leverages Dempster-Shafer Theory (DST) to rigorously measure the geometric discordance between information sources. These components are used to disentangle epistemic uncertainty from aleatoric uncertainty and modulate the optimization objective based on detected conflicts. Experiments on standard benchmarks and a curated generalization dataset demonstrate that our approach significantly outperforms baselines, optimizing the trade-off between answer coverage and abstention with superior calibration.

cs.IR↗

arXiv2026

How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare

Advances in AI offer the prospect of manipulating beliefs and behaviors on a population-wide level. Large language models and autonomous agents now let influence campaigns reach unprecedented scale and precision. Generative tools can expand propaganda output without sacrificing credibility and inexpensively create falsehoods that are rated as more human-like than those written by humans. Techniques meant to refine AI reasoning, such as chain-of-thought prompting, can just as effectively be used to generate more convincing falsehoods. Enabled by these capabilities, a disruptive threat is emerging: swarms of collaborative, malicious AI agents. Fusing LLM reasoning with multi-agent architectures, these systems are capable of coordinating autonomously, infiltrating communities, and fabricating consensus efficiently. By adaptively mimicking human social dynamics, they threaten democracy. Because the resulting harms stem from design, commercial incentives, and governance, we prioritize interventions at multiple leverage points, focusing on pragmatic mechanisms over voluntary compliance.

cs.CY↗

arXiv2025

Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment

Humans display significant uncertainty when confronted with moral dilemmas, yet the extent of such uncertainty in machines and AI agents remains underexplored. Recent studies have confirmed the overly confident tendencies of machine-generated responses, particularly in large language models (LLMs). As these systems are increasingly embedded in ethical decision-making scenarios, it is important to understand their moral reasoning and the inherent uncertainties in building reliable AI systems. This work examines how uncertainty influences moral decisions in the classical trolley problem, analyzing responses from 32 open-source models and 9 distinct moral dimensions. We first find that variance in model confidence is greater across models than within moral dimensions, suggesting that moral uncertainty is predominantly shaped by model architecture and training method. To quantify uncertainty, we measure binary entropy as a linear combination of total entropy, conditional entropy, and mutual information. To examine its effects, we introduce stochasticity into models via "dropout" at inference time. Our findings show that our mechanism increases total entropy, mainly through a rise in mutual information, while conditional entropy remains largely unchanged. Moreover, this mechanism significantly improves human-LLM moral alignment, with correlations in mutual information and alignment score shifts. Our results highlight the potential to better align model-generated decisions and human preferences by deliberately modulating uncertainty and reducing LLMs' confidence in morally complex scenarios.

cs.AI↗

arXiv2025

Generalizable Slum Detection from Satellite Imagery with Mixture-of-Experts

Satellite-based slum segmentation holds significant promise in generating global estimates of urban poverty. However, the morphological heterogeneity of informal settlements presents a major challenge, hindering the ability of models trained on specific regions to generalize effectively to unseen locations. To address this, we introduce a large-scale high-resolution dataset and propose GRAM (Generalized Region-Aware Mixture-of-Experts), a two-phase test-time adaptation framework that enables robust slum segmentation without requiring labeled data from target regions. We compile a million-scale satellite imagery dataset from 12 cities across four continents for source training. Using this dataset, the model employs a Mixture-of-Experts architecture to capture region-specific slum characteristics while learning universal features through a shared backbone. During adaptation, prediction consistency across experts filters out unreliable pseudo-labels, allowing the model to generalize effectively to previously unseen regions. GRAM outperforms state-of-the-art baselines in low-resource settings such as African cities, offering a scalable and label-efficient solution for global slum mapping and data-driven urban planning.

cs.CV↗

arXiv2025

Learning Multidimensional Urban Poverty Representation with Satellite Imagery

Recent advances in deep learning have enabled the inference of urban socioeconomic characteristics from satellite imagery. However, models relying solely on urbanization traits often show weak correlations with poverty indicators, as unplanned urban growth can obscure economic disparities and spatial inequalities. To address this limitation, we introduce a novel representation learning framework that captures multidimensional deprivation-related traits from very high-resolution satellite imagery for precise urban poverty mapping. Our approach integrates three complementary traits: (1) accessibility traits, learned via contrastive learning to encode proximity to essential infrastructure; (2) morphological traits, derived from building footprints to reflect housing conditions in informal settlements; and (3) economic traits, inferred from nightlight intensity as a proxy for economic activity. To mitigate spurious correlations - such as those from non-residential nightlight sources that misrepresent poverty conditions - we incorporate a backdoor adjustment mechanism that leverages morphological traits during training of the economic module. By fusing these complementary features into a unified representation, our framework captures the complex nature of poverty, which often diverges from economic development trends. Evaluations across three capital cities - Cape Town, Dhaka, and Phnom Penh - show that our model significantly outperforms existing baselines, offering a robust tool for poverty mapping and policy support in data-scarce regions.

cs.CY↗

arXiv2025

Classifying and Tracking International Aid Contribution Towards SDGs

International aid is a critical mechanism for promoting economic growth and well-being in developing nations, supporting progress toward the Sustainable Development Goals (SDGs). However, tracking aid contributions remains challenging due to labor-intensive data management, incomplete records, and the heterogeneous nature of aid data. Recognizing the urgency of this challenge, we partnered with government agencies to develop an AI model that complements manual classification and mitigates human bias in subjective interpretation. By integrating SDG-specific semantics and leveraging prior knowledge from language models, our approach enhances classification accuracy and accommodates the diversity of aid projects. When applied to a comprehensive dataset spanning multiple years, our model can reveal hidden trends in the temporal evolution of international development cooperation. Expert interviews further suggest how these insights can empower policymakers with data-driven decision-making tools, ultimately improving aid effectiveness and supporting progress toward SDGs.

cs.CY↗

arXiv2025

Retrieval Augmented Time Series Forecasting

Time series forecasting uses historical data to predict future trends, leveraging the relationships between past observations and available features. In this paper, we propose RAFT, a retrieval-augmented time series forecasting method to provide sufficient inductive biases and complement the model's learning capacity. When forecasting the subsequent time frames, we directly retrieve historical data candidates from the training dataset with patterns most similar to the input, and utilize the future values of these candidates alongside the inputs to obtain predictions. This simple approach augments the model's capacity by externally providing information about past patterns via retrieval modules. Our empirical evaluations on ten benchmark datasets show that RAFT consistently outperforms contemporary baselines with an average win ratio of 86%.

cs.LG↗

arXiv2025

Adversarial Style Augmentation via Large Language Model for Robust Fake News Detection

The spread of fake news harms individuals and presents a critical social challenge that must be addressed. Although numerous algorithmic and insightful features have been developed to detect fake news, many of these features can be manipulated with style-conversion attacks, especially with the emergence of advanced language models, making it more difficult to differentiate from genuine news. This study proposes adversarial style augmentation, AdStyle, designed to train a fake news detector that remains robust against various style-conversion attacks. The primary mechanism involves the strategic use of LLMs to automatically generate a diverse and coherent array of style-conversion attack prompts, enhancing the generation of particularly challenging prompts for the detector. Experiments indicate that our augmentation strategy significantly improves robustness and detection performance when evaluated on fake news benchmark datasets.

cs.CL↗

arXiv2025

Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment

Deploying large language models (LLMs) with agency in real-world applications raises critical questions about how these models will behave. In particular, how will their decisions align with humans when faced with moral dilemmas? This study examines the alignment between LLM-driven decisions and human judgment in various contexts of the moral machine experiment, including personas reflecting different sociodemographics. We find that the moral decisions of LLMs vary substantially by persona, showing greater shifts in moral decisions for critical tasks than humans. Our data also indicate an interesting partisan sorting phenomenon, where political persona predominates the direction and degree of LLM decisions. We discuss the ethical implications and risks associated with deploying these models in applications that involve moral decisions.

cs.CY↗

arXiv2025

Generalizable Disaster Damage Assessment via Change Detection with Vision Foundation Model

The increasing frequency and intensity of natural disasters call for rapid and accurate damage assessment. In response, disaster benchmark datasets from high-resolution satellite imagery have been constructed to develop methods for detecting damaged areas. However, these methods face significant challenges when applied to previously unseen regions due to the limited geographical and disaster-type diversity in the existing datasets. We introduce DAVI (Disaster Assessment with VIsion foundation model), a novel approach that addresses domain disparities and detects structural damage at the building level without requiring ground-truth labels for target regions. DAVI combines task-specific knowledge from a model trained on source regions with task-agnostic knowledge from an image segmentation model to generate pseudo labels indicating potential damage in target regions. It then utilizes a two-stage refinement process, which operate at both pixel and image levels, to accurately identify changes in disaster-affected areas. Our evaluation, including a case study on the 2023 Türkiye earthquake, demonstrates that our model achieves exceptional performance across diverse terrains (e.g., North America, Asia, and the Middle East) and disaster types (e.g., wildfires, hurricanes, and tsunamis). This confirms its robustness in disaster assessment without dependence on ground-truth labels and highlights its practical applicability.

cs.CV↗

arXiv2024

Poverty mapping in Mongolia with AI-based Ger detection reveals urban slums persist after the COVID-19 pandemic

Mongolia is among the countries undergoing rapid urbanization, and its temporary nomadic dwellings-known as Ger-have expanded into urban areas. Ger settlements in cities are increasingly recognized as slums by their socio-economic deprivation. The distinctive circular, tent-like shape of gers enables their detection through very-high-resolution satellite imagery. We develop a computer vision algorithm to detect gers in Ulaanbaatar, the capital of Mongolia, utilizing satellite images collected from 2015 to 2023. Results reveal that ger settlements have been displaced towards the capital's peripheral areas. The predicted slum ratio based on our results exhibits a significant correlation (r = 0.84) with the World Bank's district-level poverty data. Our nationwide extrapolation suggests that slums may continue to take up one-fifth of the population after the COVID-19 pandemic, contrary to other official predictions that anticipated a decline. We discuss the potential of machine learning on satellite imagery in providing insights into urbanization patterns and monitoring the Sustainable Development Goals.

cs.CY↗

arXiv2024

Recent advances in interpretable machine learning using structure-based protein representations

Recent advancements in machine learning (ML) are transforming the field of structural biology. For example, AlphaFold, a groundbreaking neural network for protein structure prediction, has been widely adopted by researchers. The availability of easy-to-use interfaces and interpretable outcomes from the neural network architecture, such as the confidence scores used to color the predicted structures, have made AlphaFold accessible even to non-ML experts. In this paper, we present various methods for representing protein 3D structures from low- to high-resolution, and show how interpretable ML methods can support tasks such as predicting protein structures, protein function, and protein-protein interactions. This survey also emphasizes the significance of interpreting and visualizing ML-based inference for structure-based protein representations that enhance interpretability and knowledge discovery. Developing such interpretable approaches promises to further accelerate fields including drug development and protein design.

cs.LG↗

arXiv2024

Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption

Drawing parallels between human cognition and artificial intelligence, we explored how large language models (LLMs) internalize identities imposed by targeted prompts. Informed by Social Identity Theory, these identity assignments lead LLMs to distinguish between "we" (the ingroup) and "they" (the outgroup). This self-categorization generates both ingroup favoritism and outgroup bias. Nonetheless, existing literature has predominantly focused on ingroup favoritism, often overlooking outgroup bias, which is a fundamental source of intergroup prejudice and discrimination. Our experiment addresses this gap by demonstrating that outgroup bias manifests as strongly as ingroup favoritism. Furthermore, we successfully mitigated the inherent pro-liberal, anti-conservative bias in LLMs by guiding them to adopt the perspectives of the initially disfavored group. These results were replicated in the context of gender bias. Our findings highlight the potential to develop more equitable and balanced language models.

cs.CL↗

arXiv2024

GeoSEE: Regional Socio-Economic Estimation With a Large Language Model

Moving beyond traditional surveys, combining heterogeneous data sources with AI-driven inference models brings new opportunities to measure socio-economic conditions, such as poverty and population, over expansive geographic areas. The current research presents GeoSEE, a method that can estimate various socio-economic indicators using a unified pipeline powered by a large language model (LLM). Presented with a diverse set of information modules, including those pre-constructed from satellite imagery, GeoSEE selects which modules to use in estimation, for each indicator and country. This selection is guided by the LLM's prior socio-geographic knowledge, which functions similarly to the insights of a domain expert. The system then computes target indicators via in-context learning after aggregating results from selected modules in the format of natural language-based texts. Comprehensive evaluation across countries at various stages of development reveals that our method outperforms other predictive models in both unsupervised and low-shot contexts. This reliable performance under data-scarce setting in under-developed or developing countries, combined with its cost-effectiveness, underscores its potential to continuously support and monitor the progress of Sustainable Development Goals, such as poverty alleviation and equitable growth, on a global scale.

cs.CY↗

arXiv2024

Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space

Proteins are complex molecules responsible for different functions in nature. Enhancing the functionality of proteins and cellular fitness can significantly impact various industries. However, protein optimization using computational methods remains challenging, especially when starting from low-fitness sequences. We propose LatProtRL, an optimization method to efficiently traverse a latent space learned by an encoder-decoder leveraging a large protein language model. To escape local optima, our optimization is modeled as a Markov decision process using reinforcement learning acting directly in latent space. We evaluate our approach on two important fitness optimization tasks, demonstrating its ability to achieve comparable or superior fitness over baseline methods. Our findings and in vitro evaluation show that the generated sequences can reach high-fitness regions, suggesting a substantial potential of LatProtRL in lab-in-the-loop scenarios.

cs.LG↗

arXiv2024

FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning

Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors derived from projections of local updates on a Euclidean space; however, these methods fail to accurately represent the functionality and structure of local models, resulting in inconsistent performance. Here, we present a new paradigm to defend against poisoning attacks in federated learning using functional mappings of local models based on intermediate outputs. Experiments show that our mechanism is robust under a broad range of computing conditions and advanced attack scenarios, enabling safer collaboration among data-sensitive participants via federated learning.

cs.LG↗

arXiv2024

I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models

We explored cultural biases-individualism vs. collectivism-in ChatGPT across three Western languages (i.e., English, German, and French) and three Eastern languages (i.e., Chinese, Japanese, and Korean). When ChatGPT adopted an individualistic persona in Western languages, its collectivism scores (i.e., out-group values) exhibited a more negative trend, surpassing their positive orientation towards individualism (i.e., in-group values). Conversely, when a collectivistic persona was assigned to ChatGPT in Eastern languages, a similar pattern emerged with more negative responses toward individualism (i.e., out-group values) as compared to collectivism (i.e., in-group values). The results indicate that when imbued with a particular social identity, ChatGPT discerns in-group and out-group, embracing in-group values while eschewing out-group values. Notably, the negativity towards the out-group, from which prejudices and discrimination arise, exceeded the positivity towards the in-group. The experiment was replicated in the political domain, and the results remained consistent. Furthermore, this replication unveiled an intrinsic Democratic bias in Large Language Models (LLMs), aligning with earlier findings and providing integral insights into mitigating such bias through prompt engineering. Extensive robustness checks were performed using varying hyperparameter and persona setup methods, with or without social identity labels, across other popular language models.

cs.CL↗

arXiv2024

Self Supervised Vision for Climate Downscaling

Climate change is one of the most critical challenges that our planet is facing today. Rising global temperatures are already bringing noticeable changes to Earth's weather and climate patterns with an increased frequency of unpredictable and extreme weather events. Future projections for climate change research are based on Earth System Models (ESMs), the computer models that simulate the Earth's climate system. ESMs provide a framework to integrate various physical systems, but their output is bound by the enormous computational resources required for running and archiving higher-resolution simulations. For a given resource budget, the ESMs are generally run on a coarser grid, followed by a computationally lighter $downscaling$ process to obtain a finer-resolution output. In this work, we present a deep-learning model for downscaling ESM simulation data that does not require high-resolution ground truth data for model optimization. This is realized by leveraging salient data distribution patterns and the hidden dependencies between weather variables for an $\textit{individual}$ data point at $\textit{runtime}$. Extensive evaluation with $2$x, $3$x, and $4$x scaling factors demonstrates that the proposed model consistently obtains superior performance over that of various baselines. The improved downscaling performance and no dependence on high-resolution ground truth data make the proposed method a valuable tool for climate research and mark it as a promising direction for future research.

physics.ao-ph↗