arXiv subjects

Elena Zheleva

Publications and source records attributed to Elena Zheleva.

At least 19 recordsLinked to original sources

arXiv2026

Medical Causal Hypothesis Verification with Large Language Models

The growing use of large language models (LLMs) for search and information retrieval underscores the need to evaluate their reliability in high-stakes domains such as healthcare. Although LLMs can effectively answer questions about diseases, symptoms, and treatments, their ability to accurately assess causal relationships and ground their conclusions in verified scientific evidence remains unclear. Here, we present a preliminary, small-scale study that investigates the accuracy of LLMs in evaluating causal medical claims and supporting them with peer-reviewed research. We propose an evaluation framework for causal hypothesis verification that can be used to systematically track the performance of existing and future LLMs. We assess the performance of eight LLMs on 17 medical causal hypotheses to evaluate whether they can reliably verify these hypotheses using scientific evidence from the literature. We systematically annotate the scientific evidence they provide according to six criteria (a total of 1,067 annotation points) and assess them with nine evaluation metrics. Our analysis shows that while LLMs exhibit strong recall, they often perform poorly at providing valid scientific articles and evidence for support and at rejecting unsupported hypotheses. These findings highlight a critical limitation of current LLMs, as they cannot yet be trusted fully to verify causal relationships from the biomedical literature. This work underscores the need for rigorous evaluation before using LLMs for search and retrieval in healthcare settings.

cs.CL↗

arXiv2026

Contextual Bandits for Maximizing Stimulated Word-of-Mouth Rewards

Stimulated word-of-mouth is a strategy that promotes information sharing through prompts or incentives. Optimizing stimulated word-of-mouth through social networks requires identifying and targeting connected users who are most susceptible to spillover, a phenomenon where the influence of recommendations extends beyond the immediate audience to impact their connected users. The probability of spillover varies across individuals, and their connections, leading to heterogeneity. Understanding and accurately estimating the spillover probabilities among users in social networks is crucial for improving the effectiveness of stimulated word-of-mouth. To address this, we present a novel contextual multi-armed bandit framework that learns individual spillover probabilities and ranks connected users to maximize rewards from stimulated word-of-mouth. Experiments on real-world network datasets demonstrate that accounting for spillover heterogeneity enhances the targeting precision of top-$k$ connected users, boosting rewards and outperforming baseline methods that do not learn individual spillover effects.

cs.LG↗

arXiv2026

TriOpt: A Scalable Algorithm for Linear Causal Discovery

Learning causal relations from observational data is challenging because the graph search space grows super-exponentially with the number of variables. Ordering-based methods reduce this space by first identifying the topological ordering, whereas continuous optimization methods explore most likely regions of the space by casting DAG learning as a differentiable objective with an acyclicity constraint. Despite their conceptual appeal, both paradigms face significant scalability limitations in high-dimensional settings, restricting their practical applicability. In this work, we introduce a new formulation for linear causal discovery that tightly integrates these two paradigms to achieve substantial gains in scalability without sacrificing accuracy. Our approach, TriOpt, decomposes the problem into two efficient stages. First, it recovers the topological ordering by exploiting the Sherman-Morrison rank-1 downdate together with the additive structure of linear kernels, enabling fast and scalable ordering estimation. Second, given this ordering, we reformulate structure learning as a convex continuous optimization problem that entirely avoids the need for enforcing costly acyclicity constraints. We theoretically show that, under the true ordering, TriOpt exactly recovers the underlying linear DAG. Empirically, across synthetic, semi-synthetic, and real-world datasets, TriOpt achieves orders-of-magnitude speedups over state-of-the-art linear causal discovery methods in high-dimensional regimes, while maintaining comparable or superior accuracy.

cs.LG↗

arXiv2026

Debiasing Message Passing to Mitigate Popularity Bias in GNN-based Collaborative Filtering

Collaborative filtering (CF) models based on graph neural networks (GNNs) achieve strong performance in recommender systems by propagating user-item signals over interaction graphs. However, they are highly susceptible to popularity bias, since skewed interaction distributions and repeated message passing across high-order neighborhoods amplify the influence of popular items while suppressing long-tail ones. Existing debiasing approaches, including re-weighting objectives, regularization, causal methods, and post-processing, are less effective in GNN-based settings because they do not directly counteract bias propagated through the aggregation process, and recent in-aggregation weighting methods often rely on static heuristics or unstable embedding estimates. We propose Debiasing Popularity Amplification in Aggregation (DPAA), a popularity debiasing framework for GNN-based CF that integrates adaptive, embedding-aware interaction weighting and layer-wise weighting directly into message passing. DPAA assigns interaction-level weights from a representation-aware popularity signal, stabilized by a smooth transition from pre-trained to evolving model embeddings during training. It further introduces a layer-wise weighting that amplifies higher-order neighborhoods, surfacing long-range interactions with diverse and underexposed items. Experiments on real-world and semi-synthetic datasets show that DPAA outperforms state-of-the-art popularity-bias correction methods for GNN-based CF.

cs.IR↗

arXiv2025

Learning Peer Influence Probabilities with Linear Contextual Bandits

In networked environments, it is common for users to share recommendations about content, products, services, and possible courses of action. Whether these recommendations are accepted and acted upon is highly context-dependent, influenced by the characteristics of the sender and recipient, the nature of their relationship, the attributes of the recommended item, and the communication context. Consequently, probabilities of peer influence exhibit substantial heterogeneity across individuals and settings. Accurate estimation of these probabilities is key to understanding information diffusion processes and to improving the effectiveness of viral marketing strategies. However, learning these probabilities from data is challenging; static data may capture correlations between peer recommendations and peer actions but fails to reveal influence relationships. Online learning algorithms can learn these probabilities from interventions but either waste resources by learning from random exploration or optimize for rewards, thus favoring exploration of the space with higher influence probabilities. In this work, we study learning peer influence probabilities under a contextual linear bandit framework. We show that a fundamental trade-off can arise between regret minimization and estimation error, characterize all achievable rate pairs, and propose an uncertainty-guided exploration algorithm that, by tuning a parameter, attains any pair within this trade-off. Our experiments on semi-synthetic network datasets show the advantages of our method over static methods and contextual bandits that ignore this trade-off.

cs.LG↗

arXiv2025

Post-hoc Popularity Bias Correction in GNN-based Collaborative Filtering

User historical interaction data is the primary signal for learning user preferences in collaborative filtering (CF). However, the training data often exhibits a long-tailed distribution, where only a few items have the majority of interactions. CF models trained directly on such imbalanced data are prone to learning popularity bias, which reduces personalization and leads to suboptimal recommendation quality. Graph Neural Networks (GNNs), while effective for CF due to their message passing mechanism, can further propagate and amplify popularity bias through their aggregation process. Existing approaches typically address popularity bias by modifying training objectives but fail to directly counteract the bias propagated during GNN's neighborhood aggregation. Applying weights to interactions during aggregation can help alleviate this problem, yet it risks distorting model learning due to unstable node representations in the early stages of training. In this paper, we propose a Post-hoc Popularity Debiasing (PPD) method that corrects for popularity bias in GNN-based CF and operates directly on pre-trained embeddings without requiring retraining. By estimating interaction-level popularity and removing popularity components from node representations via a popularity direction vector, PPD reduces bias while preserving user preferences. Experimental results show that our method outperforms state-of-the-art approaches for popularity bias correction in GNN-based CF.

cs.IR↗

arXiv2025

Causal Representation Learning from Network Data

Causal disentanglement from soft interventions is identifiable under the assumptions of linear interventional faithfulness and availability of both observational and interventional data. Prior work has focused on unstructured observations without leveraging known relational context among measured entities. In many scientific applications, however, the measured variables come with an observed interaction network that provides structured context, such as protein-protein interactions and pathway-gene membership. We propose GraCE-VAE, a graph-aware causal discrepancy variational autoencoder that treats pathway-level information as an auxiliary view of the latent causal programs. The graph neural network encoder conditions on this auxiliary pathway view and the biological graph to improve amortized inference, while the causal decoder remains a latent SCM with soft interventions. Assuming samples are i.i.d. within each intervention regime, we show that GraCE-VAE inherits the identifiability guarantees of causal discrepancy VAEs and identifies the latent causal graph and intervention targets up to the standard equivalence class. Experiments on three CRISPR perturbation datasets demonstrate that leveraging structured biological context improves prediction of interventional outcomes, including unseen perturbation combinations.

cs.LG↗

arXiv2025

Relational Causal Discovery with Latent Confounders

Estimating causal effects from real-world relational data can be challenging when the underlying causal model and potential confounders are unknown. While several causal discovery algorithms exist for learning causal models with latent confounders from data, they assume that the data is independent and identically distributed (i.i.d.) and are not well-suited for learning from relational data. Similarly, existing relational causal discovery algorithms assume causal sufficiency, which is unrealistic for many real-world datasets. To address this gap, we propose RelFCI, a sound and complete causal discovery algorithm for relational data with latent confounders. Our work builds upon the Fast Causal Inference (FCI) and Relational Causal Discovery (RCD) algorithms and it defines new graphical models, necessary to support causal discovery in relational domains. We also establish soundness and completeness guarantees for relational d-separation with latent confounders. We present experimental results demonstrating the effectiveness of RelFCI in identifying the correct causal structure in relational causal models with latent confounders.

cs.LG↗

arXiv2025

A Control Function Framework for Mitigating Position Bias in Learning to Rank Systems

Learning-to-rank (LTR) systems commonly depend on implicit feedback, such as user clicks, because it is easy to collect and can serve as a valuable signal of user preferences. However, directly optimizing ranking models using implicit feedback data often yields suboptimal performance because such data is inherently skewed by systematic biases. Among these biases, position bias is particularly pervasive: items ranked higher tend to receive disproportionately more interactions, regardless of their actual relevance. To address this, we introduce a novel two-stage framework based on control functions. In the first stage, we utilize exogenous variation from the residuals of the ranking process, which are then incorporated into a second stage click model to account for position-dependent distortions. In contrast to existing methods, our approach avoids explicit propensity estimation, supports nonlinear ranking models, and can be flexibly incorporated into any state-of-the-art ranking algorithm for position bias correction. We also propose a debiasing strategy for validation clicks that enables reliable hyperparameter tuning in the absence of unbiased validation data. Empirical results show that our method outperforms state-of-the-art position bias correction methods on both benchmark and real-world industrial datasets.

cs.IR↗

arXiv2025

Estimating Causal Effects in Networks with Cluster-Based Bandits

The gold standard for estimating causal effects is randomized controlled trial (RCT) or A/B testing where a random group of individuals from a population of interest are given treatment and the outcome is compared to a random group of individuals from the same population. However, A/B testing is challenging in the presence of interference, commonly occurring in social networks, where individuals can impact each others outcome. Moreover, A/B testing can incur a high performance loss when one of the treatment arms has a poor performance and the test continues to treat individuals with it. Therefore, it is important to design a strategy that can adapt over time and efficiently learn the total treatment effect in the network. We introduce two cluster-based multi-armed bandit (MAB) algorithms to gradually estimate the total treatment effect in a network while maximizing the expected reward by making a tradeoff between exploration and exploitation. We compare the performance of our MAB algorithms with a vanilla MAB algorithm that ignores clusters and the corresponding RCT methods on semi-synthetic data with simulated interference. The vanilla MAB algorithm shows higher reward-action ratio at the cost of higher treatment effect error due to undesired spillover. The cluster-based MAB algorithms show higher reward-action ratio compared to their corresponding RCT methods without sacrificing much accuracy in treatment effect estimation.

cs.LG↗

arXiv2025

Heterogeneous Causal Discovery of Repeated Undesirable Health Outcomes

Understanding the factors that trigger or prevent undesirable health outcomes across patient subpopulations is essential for designing targeted interventions. While randomized controlled trials and expert-led patient interviews are standard methods for identifying these factors, they can be time-consuming or infeasible. Causal discovery offers an alternative to conventional approaches by generating cause-and-effect hypotheses from observational data, yet its practical utility is limited by strong or untestable assumptions. This work presents a novel, end-to-end framework that uniquely integrates an ensemble of causal structure learning (CSL) algorithms with heterogeneous causal effect estimation. By aggregating results across multiple algorithms, the framework identifies robust causal relationships that persist under different modeling assumptions while simultaneously revealing how these effects vary across specific patient contexts. The proposed heterogeneous causal discovery framework improves robustness and provides practitioners with a prioritized set of actionable, clinically interpretable hypotheses. We demonstrate the framework's effectiveness through two large-scale healthcare applications: identifying drivers and inhibitors of repeat emergency department visits among diabetic patients and hospital readmissions among ICU patients, using insurance claims and electronic health record datasets. Our results, across both settings, identify chronic disease management and care coordination as key interventions, while revealing that intervention effectiveness depends on specific patient-level modifiers. We employ a multi-layered validation strategy, including ground-truth recovery via simulations, alignment with clinical literature, validation by expert clinicians, and portability in modern healthcare systems using an external dataset, to demonstrate the framework's practical utility.

cs.AI↗

arXiv2025

Learning Exposure Mapping Functions for Inferring Heterogeneous Peer Effects

In causal inference, interference refers to the phenomenon in which the actions of peers in a network can influence an individual's outcome. Peer effect refers to the difference in counterfactual outcomes of an individual for different levels of peer exposure, the extent to which an individual is exposed to the treatments, actions, or behaviors of peers. Estimating peer effects requires deciding how to represent peer exposure. Typically, researchers define an exposure mapping function that aggregates peer treatments and outputs peer exposure. Most existing approaches for defining exposure mapping functions assume peer exposure based on the number or fraction of treated peers. Recent studies have investigated more complex functions of peer exposure which capture that different peers can exert different degrees of influence. However, none of these works have explicitly considered the problem of automatically learning the exposure mapping function. In this work, we focus on learning this function for the purpose of estimating heterogeneous peer effects, where heterogeneity refers to the variation in counterfactual outcomes for the same peer exposure but different individual's contexts. We develop EgoNetGNN, a graph neural network (GNN)-based method, to automatically learn the appropriate exposure mapping function allowing for complex peer influence mechanisms that, in addition to peer treatments, can involve the local neighborhood structure and edge attributes. We show that GNN models that use peer exposure based on the number or fraction of treated peers or learn peer exposure naively face difficulty accounting for such influence mechanisms. Our comprehensive evaluation on synthetic and semi-synthetic network data shows that our method is more robust to different unknown underlying influence mechanisms when estimating heterogeneous peer effects when compared to state-of-the-art baselines.

cs.AI↗

arXiv2024

See Me, Believe Me: Causality, Intersectionality, and Interventions Improving the Appearance of Patients

In the context of medical records, patients often experience testimonial injustice, where the textual account undermines the validity of their experiences. Past work has demonstrated that intersectionality of demographic features is crucial to \emph{detect} such injustice. We use causal discovery to study the degree to which certain demographic features tied to marginalization (namely age, gender, and race), together lead to specific types of testimonial injustice terms. This offers us an insightful Structural Causal Model (SCM) relating those demographic features to the different ways a patients' reality may be undermined. We then move toward \emph{addressing} such injustice, by very selectively (based on insights from the SCM) editing physicians' notes. For comparison, we contrast these rule-based edits with blanket context-based modifications using an LLM. We assess the impact of these changes on the perception of patients' experiences, using human experts and an LLM. We find that edits, in general, enhance clarity regarding the urgency and causes of patients' conditions. Additionally, for human experts, rule-based modifications show a tendency to shift blame away from patients, and toward more objective external factors. These findings (1) underscore the importance of quantifying sources of injustice in how patients' testimonies are recorded, (2) reveal that making minimal intentional changes accordingly can effect improved patient perception, and (3) call for larger efforts to assess health outcomes under such more just representation.

cs.LG↗

arXiv2024

Cascade-based Randomization for Inferring Causal Effects under Diffusion Interference

The presence of interference, where the outcome of an individual may depend on the treatment assignment and behavior of neighboring nodes, can lead to biased causal effect estimation. Current approaches to network experiment design focus on limiting interference through cluster-based randomization, in which clusters are identified using graph clustering, and cluster randomization dictates the node assignment to treatment and control. However, cluster-based randomization approaches perform poorly when interference propagates in cascades, whereby the response of individuals to treatment propagates to their multi-hop neighbors. When we have knowledge of the cascade seed nodes, we can leverage this interference structure to mitigate the resulting causal effect estimation bias. With this goal, we propose a cascade-based network experiment design that initiates treatment assignment from the cascade seed node and propagates the assignment to their multi-hop neighbors to limit interference during cascade growth and thereby reduce the overall causal effect estimation error. Our extensive experiments on real-world and synthetic datasets demonstrate that our proposed framework outperforms the existing state-of-the-art approaches in estimating causal effects in network data.

cs.LG↗

arXiv2024

MOTIV: Visual Exploration of Moral Framing in Social Media

We present a visual computing framework for analyzing moral rhetoric on social media around controversial topics. Using Moral Foundation Theory, we propose a methodology for deconstructing and visualizing the \textit{when}, \textit{where}, and \textit{who} behind each of these moral dimensions as expressed in microblog data. We characterize the design of this framework, developed in collaboration with experts from language processing, communications, and causal inference. Our approach integrates microblog data with multiple sources of geospatial and temporal data, and leverages unsupervised machine learning (generalized additive models) to support collaborative hypothesis discovery and testing. We implement this approach in a system named MOTIV. We illustrate this approach on two problems, one related to Stay-at-home policies during the COVID-19 pandemic, and the other related to the Black Lives Matter movement. Through detailed case studies and discussions with collaborators, we identify several insights discovered regarding the different drivers of moral sentiment in social media. Our results indicate that this visual approach supports rapid, collaborative hypothesis testing, and can help give insights into the underlying moral values behind controversial political issues. Supplemental Material: https://osf.io/ygkzn/?view_only=6310c0886938415391d977b8aae8b749

cs.CY↗

arXiv2024

Bridging or Breaking: Impact of Intergroup Interactions on Religious Polarization

While exposure to diverse viewpoints may reduce polarization, it can also have a backfire effect and exacerbate polarization when the discussion is adversarial. Here, we examine the question whether intergroup interactions around important events affect polarization between majority and minority groups in social networks. We compile data on the religious identity of nearly 700,000 Indian Twitter users engaging in COVID-19-related discourse during 2020. We introduce a new measure for an individual's group conformity based on contextualized embeddings of tweet text, which helps us assess polarization between religious groups. We then use a meta-learning framework to examine heterogeneous treatment effects of intergroup interactions on an individual's group conformity in the light of communal, political, and socio-economic events. We find that for political and social events, intergroup interactions reduce polarization. This decline is weaker for individuals at the extreme who already exhibit high conformity to their group. In contrast, during communal events, intergroup interactions can increase group conformity. Finally, we decompose the differential effects across religious groups in terms of emotions and topics of discussion. The results show that the dynamics of religious polarization are sensitive to the context and have important implications for understanding the role of intergroup interactions.

cs.SI↗

arXiv2023

Contagion Effect Estimation Using Proximal Embeddings

Contagion effect refers to the causal effect of peers' behavior on the outcome of an individual in social networks. Contagion can be confounded due to latent homophily which makes contagion effect estimation very hard: nodes in a homophilic network tend to have ties to peers with similar attributes and can behave similarly without influencing one another. One way to account for latent homophily is by considering proxies for the unobserved confounders. However, as we demonstrate in this paper, existing proxy-based methods for contagion effect estimation have a very high variance when the proxies are high-dimensional. To address this issue, we introduce a novel framework, Proximal Embeddings (ProEmb), that integrates variational autoencoders with adversarial networks to create low-dimensional representations of high-dimensional proxies and help with identifying contagion effects. While VAEs have been used previously for representation learning in causal inference, a novel aspect of our approach is the additional component of adversarial networks to balance the representations of different treatment groups, which is essential in causal inference from observational data where these groups typically come from different distributions. We empirically show that our method significantly increases the accuracy and reduces the variance of contagion effect estimation in observational network data compared to state-of-the-art methods.

cs.LG↗

arXiv2023

Leveraging heterogeneous spillover in maximizing contextual bandit rewards

Recommender systems relying on contextual multi-armed bandits continuously improve relevant item recommendations by taking into account the contextual information. The objective of bandit algorithms is to learn the best arm (e.g., best item to recommend) for each user and thus maximize the cumulative rewards from user engagement with the recommendations. The context that these algorithms typically consider are the user and item attributes. However, in the context of social networks where $\textit{the action of one user can influence the actions and rewards of other users,}$ neighbors' actions are also a very important context, as they can have not only predictive power but also can impact future rewards through spillover. Moreover, influence susceptibility can vary for different people based on their preferences and the closeness of ties to other users which leads to heterogeneity in the spillover effects. Here, we present a framework that allows contextual multi-armed bandits to account for such heterogeneous spillovers when choosing the best arm for each user. Our experiments on several semi-synthetic and real-world datasets show that our framework leads to significantly higher rewards than existing state-of-the-art solutions that ignore the network information and potential spillover.

cs.LG↗