arXiv subjects

Meeyoung Cha

Publications and source records attributed to Meeyoung Cha.

At least 19 recordsLinked to original sources

arXiv2026

IO Factory: Simulating AI-Enabled Influence Campaigns at Scale

We introduce IO Factory, an AI-driven framework for simulating information and influence campaigns as fully integrated, traceable processes. The threat of digital manipulation now extends beyond persuasive text from individual language models to AI swarms, i.e., persistent groups of coordinated agents that adapt to platform feedback and disguise organized campaigns as ordinary social interaction. Because such campaigns cannot be identified from isolated messages alone, they must be analyzed across a continuous spectrum of planning, platform action, exposure, interpretation, measurement, and adaptation. IO Factory represents this process inside a controlled simulated platform, linking actor roles, platform actions, exposure records, structured model-based evaluations, and configured changes in the simulated population. We implement the architecture and evaluate it across configurations of up to 100,000 agents. The results show that IO Factory executes campaign timelines at scale and produces inspectable evidence of exposure and measured movement in configured belief variables. By recording the actors, objectives, action constraints, exposure paths, and measurement rules used in each run, IO Factory supports reproducible research and red-team analysis of coordinated influence.

cs.AI↗

arXiv2026

Cross-National Information Attacks: A Two-Decade Analysis of Troll Behavior in Korea

Coordinated foreign influence operations pose a growing threat to online platforms, but detecting state-linked troll activity and tracking its evolution remain challenging. This paper presents an explainable machine learning framework for theory-guided detection and longitudinal analysis of suspected trolling within Korean online news comment sections. Our hierarchical model classifies comments along three dimensions central to influence campaigns: foreign origin, moral-emotional framing, and target country. To support explainability, it also extracts brief span-level textual evidence that provides human-interpretable rationales. We apply the approach to 112M South Korean news comments authored by 4M users over nearly 20 years, identifying 23,998 accounts exhibiting behavior consistent with coordinated manipulation. Analyzing these accounts, we find that they predominantly rely on morally condemning rhetoric rather than direct promotion of foreign-aligned narratives; this rhetoric receives significantly higher user engagement. Among the highest-engagement comments, the moral condemnation most frequently targets domestic political figures (e.g., presidents or party leaders) on both the left and the right, potentially amplifying polarization. Our framework supports transparent platform governance through explainable, evidence-based moderation. These observed rhetorical and engagement patterns can inform how platforms and observatories prioritize defenses and intervene before harmful narrative-target combinations achieve widespread reach.

cs.SI↗

arXiv2026

AI Engram: In Search of Memory Traces in Artificial Intelligence

Memory formation is fundamental to intelligence, yet whether deep neural networks preserve identifiable memory traces analogous to biological memory units remains an open question. This work introduces a geometric framework to identify such "AI engrams" by formalizing the neuroscientific criteria of specificity, reactivation, sufficiency, and necessity into a constrained inverse problem. We derive a closed-form estimator that isolates individual memory traces from globally entangled parameters, and show that this biologically-derived solution corresponds to a natural gradient update on the parameter manifold. AI engrams enable surgical manipulation of learned knowledge: any subset of memories can be composed or erased through linear arithmetic, without iterative optimization. Experiments ranging from simple MLPs to LLMs demonstrate the causal validity and substantial scalability of AI engrams. Together, these results bridge theories of biological memory and artificial representation learning and offer geometric insight into how deep networks simultaneously support functional specificity within distributed storage.

cs.AI↗

arXiv2026

Textual Supervision Enhances Geospatial Representations in Vision-Language Models

Geospatial understanding is a critical yet underexplored dimension in the development of machine learning systems for tasks such as image geolocation and spatial reasoning. In this work, we analyze the geospatial representations acquired by three model families: vision-only architectures (e.g., ViT), vision-language models (e.g., CLIP), and large-scale multimodal foundation models (e.g., LLaVA, Qwen, and Gemma). By evaluating across image clusters, including people, landmarks, and everyday objects, grouped based on the degree of localizability, we reveal systematic gaps in spatial accuracy and show that textual supervision enhances the learning of geospatial representations. Our findings suggest the role of language as an effective complementary modality for encoding spatial context and multimodal learning as a key direction for advancing geospatial AI.

cs.CV↗

arXiv2026

GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards

Geospatial reasoning requires solving image-grounded problems over the complex spatial structure of a scene. However, developing this capability is hindered by the cost of annotating a vast and combinatorial question space. We propose GeoX, a self-play framework that acquires spatial logic through executable programs that yield verifiable rewards, without relying on large-scale human-curated data Given a satellite or aerial image, our framework employs a single multimodal policy that proposes spatial problems as executable programs and solves them under three reasoning modes-abduction, deduction, and induction-over spatial primitives and an image understanding tool. A verifier executes each program to covert a reward signal that jointly optimizes the two roles via reinforcement learning. GeoX consistently improves its base VLMs by up to 5.5 points on average, matching or exceeding conventional baselines trained on millions of curated data. Along-side the proposed method, we release a benchmark for geospatial understanding accumulated through self-play.

cs.AI↗

arXiv2026

Moir: Let the Model Direct Its Own Story for Robust Cross-Domain Knowledge Editing

While language models remain frozen at their training state, the world evolves continuously. Knowledge editing has emerged as a key alternative to full retraining, but its deployment is bottlenecked by the erosion of core capabilities: mathematical and programmatic reasoning collapse while encyclopedic recall remains intact. We trace this asymmetric degradation to a distributional mismatch. Covariance-based editors preserve only the subspaces spanned by their reference corpus, but fail to capture the operative distribution shaped by post-training such as SFT and DPO. Static external corpora, including Wikipedia and even the original pretraining mixture, cannot recover this shifted manifold. We propose Moir, which estimates the preservation covariance $C$ directly from the model itself by sampling from its own decoding distribution. Seeding generation with a single random vocabulary token bypasses the instruction-following templates that otherwise dominate sampled outputs, exposing the broader subspaces the model has internalized. Moir requires no external data and serves as a drop-in component for any covariance-based editor, a practical advantage given that the pre- and post-training corpora of most modern LLMs are not publicly accessible. Across OLMo-2, Llama-3.1, and Qwen-3 (7-8B), under both MEMIT and AlphaEdit and in batch and sequential regimes, Moir consistently extends preservation in the most vulnerable domains, most strikingly on Qwen3-8B after 20,000 AlphaEdit batch edits, it retains 79.9% GSM8K accuracy compared to 10.9% with the Wikipedia baseline. These results suggest that aligning the preservation distribution with the model's operative distribution is a key factor in non-destructive editing, and that the model itself may be the most accessible source of that distribution for deployed systems.

cs.CL↗

arXiv2026

Mapping Emerging Climate Misinformation Playbooks in the Global South

Climate misinformation continues to erode support for climate action, a challenge that is especially acute in the Global South, where high climate vulnerability intersects with development pressures. In rapidly evolving digital ecosystems, misinformation adapts to platform incentives, shifting from overt rejection of climate science toward more subtle narratives that contest proposed solutions. This study integrates large-scale platform data with qualitative content analysis to examine how information systems shape contemporary climate discourse. Using a dataset of 226,775 climate-related YouTube videos from Brazil (2019-2025), we identify two dominant misinformation strategies: traditional denial that disputes scientific evidence and an emerging "new denial" that accepts climate change while undermining mitigation and adaptation policies. We find a pronounced transition to solution-focused narratives that target renewable energy, climate governance, and environmental advocates. New denial content is produced by a wider array of actors, attracts higher engagement, and employs more sophisticated persuasive techniques. These patterns disproportionately affect regions already facing structural inequities and bring broader concerns about platform accountability in unequal information environments and suggest the need for governance approaches capable of addressing new denial, a rapidly adapting form of harmful content that often evades existing moderation policies.

cs.SI↗

arXiv2026

Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions

Human moral judgment is context-dependent and modulated by interpersonal relationships. As large language models (LLMs) increasingly function as decision-support systems, determining whether they encode these social nuances is critical. We characterize machine behavior using the Whistleblower's Dilemma by varying two experimental dimensions: crime severity and relational closeness. Our study evaluates three distinct perspectives: (1) moral rightness (prescriptive norms), (2) predicted human behavior (descriptive social expectations), and (3) autonomous model decision-making. By analyzing the reasoning processes, we identify a clear cross-perspective divergence: while moral rightness remains consistently fairness-oriented, predicted human behavior shifts significantly toward loyalty as relational closeness increases. Crucially, model decisions align with moral rightness judgments rather than their own behavioral predictions. This inconsistency suggests that LLM decision-making prioritizes rigid, prescriptive rules over the social sensitivity present in their internal world-modeling, which poses a gap that may lead to significant misalignments in real-world deployments.

cs.CL↗

arXiv2026

How You Ask Matters! Adaptive RAG Robustness to Query Variations

Adaptive Retrieval-Augmented Generation (RAG) promises accuracy and efficiency by dynamically triggering retrieval only when needed and is widely used in practice. However, real-world queries vary in surface form even with the same intent, and their impact on Adaptive RAG remains under-explored. We introduce the first large-scale benchmark of diverse yet semantically identical query variations, combining human-written and model-generated rewrites. Our benchmark facilitates a systematic evaluation of Adaptive RAG robustness by examining its key components across three dimensions: answer quality, computational cost, and retrieval decisions. We discover a critical robustness gap, where small surface-level changes in queries dramatically alter retrieval behavior and accuracy. Although larger models show better performance, robustness does not improve accordingly. These findings reveal that Adaptive RAG methods are highly vulnerable to query variations that preserve identical semantics, exposing a critical robustness challenge.

cs.CL↗

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

Puppets or partners? Governing cyborg propaganda in the digital public square

The distinction between genuine grassroots activism and automated influence operations is collapsing. While contemporary policy debates prioritize fully autonomous generative agents and synthetic content, this paper offers a conceptual contribution: we develop 'cyborg propaganda,' a closed-loop architecture combining verified human accounts with algorithmic automation to generate personalized content at scale, as a distinct and undertheorized threat to democratic discourse. By relying on verified citizens to ratify AI-generated messages, these campaigns exploit a regulatory gray zone that frameworks built on the human/bot binary (including the EU AI Act and Section 230) are structurally unable to address. Drawing on a conceptual analysis of coordination platforms and comparative examination of governance frameworks across democratic and non-democratic contexts, we analyze this paradox across micro, meso, and macro levels. We examine whether cyborg propaganda democratizes political power by unionizing influence or reduces citizens to cognitive proxies of a hidden directive, arguing that it shifts political discourse from a contest of ideas to a battle of algorithmic campaigns. We propose three regulatory responses: classifying coordination hubs as political action committees to enforce supply-chain transparency; mandating researcher access to platform data through DSA-style mechanisms; and establishing risk standards penalizing amplification of synthetically coordinated content. Comparative analysis reveals that viability varies structurally. Democratic states are simultaneously the most capable of regulation and the most rule-of-law constrained. By contrast, non-democratic actors face no comparable accountability, making international risk standards the primary cross-border enforcement mechanism.

cs.CY↗

arXiv2025

Dual-Margin Embedding for Fine-Grained Long-Tailed Plant Taxonomy

Taxonomic classification of ecological families, genera, and species underpins biodiversity monitoring and conservation. Existing computer vision methods typically address fine-grained recognition and long-tailed learning in isolation. However, additional challenges such as spatiotemporal domain shift, hierarchical taxonomic structure, and previously unseen taxa often co-occur in real-world deployment, leading to brittle performance under open-world conditions. We propose TaxoNet, an embedding learning framework with a theoretically grounded dual-margin objective that reshapes class decision boundaries under class imbalance to improve fine-grained discrimination while strengthening rare-class representation geometry. We evaluate TaxoNet in open-world settings that capture co-occurring recognition challenges. Leveraging diverse plant datasets, including Google Auto-Arborist (urban tree imagery), iNaturalist (Plantae observations across heterogeneous ecosystems), and NAFlora-Mini (herbarium collections), we demonstrate that TaxoNet consistently outperforms strong baselines, including multimodal foundation models.

cs.CV↗

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

Semi-supervised Shelter Mapping for WASH Accessibility Assessment in Rohingya Refugee Camps

Lack of access to Water, Sanitation, and Hygiene (WASH) services is a major public health concern in refugee camps, where extreme crowding accelerates the spread of communicable diseases. The Rohingya settlements in Cox's Bazar, Bangladesh, exemplify these conditions, with large populations living under severe spatial constraints. We develop a semi-supervised segmentation framework using the Segment Anything Model (SAM) to map shelters from multi-temporal sub-meter remote sensing imagery (2017-2025), improving detection in complex camp environments by 4.9% in F1-score over strong baselines. The detected shelter maps show that shelter expansion stabilized after 2020, whereas continued population growth reduced per capita living space by approximately 14% between 2020 and 2025. WASH accessibility, measured with an enhanced network-based two-step floating catchment area (2SFCA) method, declined from 2022 to 2025, increasing facility loads and exceeding global benchmarks. Gender-disaggregated scenarios that incorporate safety penalty further reveal pronounced inequities, with female accessibility approximately 27% lower than male. Together, these results demonstrate that remote sensing-driven AI diagnostics can generate equity-focused evidence to prioritize WASH investments and mitigate health risks in protracted displacement settings.

cs.CV↗

arXiv2025

Characterizing AI Manipulation Risks in Brazilian YouTube Climate Discourse

Climate change poses a global threat to public health, food security, and economic stability. Addressing it requires evidence-based policies and a nuanced understanding of how the threat is perceived by the public, particularly within visual social media, where narratives quickly evolve through voices of individuals, politicians, NGOs, and institutions. This study investigates climate-related discourse on YouTube within the Brazilian context, a geopolitically significant nation in global environmental negotiations. Through three case studies, we examine (1) which psychological content traits most effectively drive audience engagement, (2) the extent to which these traits influence content popularity, and (3) whether such insights can inform the design of persuasive synthetic campaigns--such as climate denialism--using recent generative language models. Another contribution of this work is the release of a large publicly available dataset of 226K Brazilian YouTube videos and 2.7M user comments on climate change. The dataset includes fine-grained annotations of persuasive strategies, theory-of-mind categorizations in user responses, and typologies of content creators. This resource can help support future research on digital climate communication and the ethical risk of algorithmically amplified narratives and generative media.

cs.SI↗

arXiv2025

EconCausal: A Context-Aware Economic Reasoning Benchmark for Large Language Models

Socio-economic causal effects depend heavily on their institutional and environmental contexts. The same intervention can produce different, even opposite, effects across regulatory regimes, market conditions, time periods, or populations. This poses a challenge for large language models (LLMs) in decision-support roles: can they infer the direction of a causal effect under a specified context, and revise that judgment when the context changes? To address this, we introduce EconCausal, a large-scale benchmark of 10,490 context-annotated causal triplets extracted from 2,595 high-quality empirical studies in top-tier economics and finance journals, constructed through a rigorous four-stage pipeline with multi-run consensus, context refinement, and multi-critic filtering. Across models, LLMs often fail to condition their predictions on context. While top models reach 88% accuracy in fixed, explicit contexts, accuracy falls by 32.6~pp on cases that require revising the sign across contexts (73.9% to 41.3%), and drops below 50% once misleading signed evidence is introduced. Models also over-commit to directional (+/-) signs, recognizing null effects only 13.8% of the time while remaining poorly calibrated on these categories. The dataset and benchmark are publicly available at https://anonymous.4open.science/r/econcausal-benchmark-6F12.

cs.CL↗

arXiv2025

How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models

Large language models leverage both parametric knowledge acquired during pretraining and in-context knowledge provided at inference time. Crucially, when these sources conflict, models arbitrate based on their internal confidence, preferring parametric knowledge for high-confidence facts while deferring to context for less familiar ones. However, the training conditions that give rise to these fundamental behaviors remain unclear. Here we conduct controlled experiments using synthetic corpora to identify the specific data properties that shape knowledge utilization. Our results reveal a counterintuitive finding: the robust, balanced use of both knowledge sources is an emergent property that requires the co-occurrence of three factors typically considered detrimental, including (i) intra-document repetition, (ii) a moderate degree of intra-document inconsistency, and (iii) a skewed knowledge distribution. We further show that these dynamics arise in real-world language model pretraining and analyze how post-training procedures reshape arbitration strategies. Together, our findings provide empirical guidance for designing training data that supports the reliable integration of parametric and in-context knowledge in language models.

cs.CL↗