arXiv subjects

Veronika Solopova

Publications and source records attributed to Veronika Solopova.

At least 19 recordsLinked to original sources

arXiv2026

From Repetition to Recognition: Inductive Discovery of Disinformation Narratives

In disinformation datasets, narratives are often understood as recurring interpretive patterns that group texts under narrative labels. Recent work formalized narrative mining as inductively inferring narrative labels from corpora, but its evaluation stays tied to predefined taxonomies, a closed-world setting that cannot capture narratives absent from the reference labels. We introduce a three-tier evaluation framework for unsupervised narrative label generation: recovery (against a corpus's own taxonomy), mining (against external label sets), and discovery (without predefined labels). Applying it, we compare clustering-based and graph-community-based pipelines across seven disinformation datasets, with human validation of discovery on two. The two families are complementary under automated metrics, but in a corpus with two prominent topics, clustering can reduce one topic to 2% of generated labels while graph-based pipelines stay balanced. Discovery validation also reveals many singletons (narrative labels derived from single claims, 30-62% of graph outputs), which clustering cannot produce. Annotators confirm many as recognizable disinformation narratives, suggesting that in open-world discovery the repetition assumed by narrative mining may be recognized outside the corpus, not within it. We release human-validated narrative candidate labels for the Climate Obstruction and PolyNarrative datasets to support taxonomy development and dataset extension.

cs.CL↗

arXiv2026

From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence

Fact-checking articles encode rich supporting evidence and reasoning, yet this evidence remains largely inaccessible to automated verification systems due to unstructured presentation. We introduce PrimeFacts, a methodology and resource for extracting fine-grained evidence from full fact-checking articles. We compile 13,106 PolitiFact articles with claims, verdicts, and all referenced sources, and we identify 49,718 in-article hyperlinks as natural anchors to pinpoint key evidence. Our framework leverages large language models (LLMs) to rewrite these anchor sentences into stand-alone, context-independent premises and investigates the extraction of additional implicit evidence. In evaluations on cross-article evidence retrieval and claim verification, the extracted premises substantially improve performance. Decontextualized evidence yields higher retrievability, achieving up to a 30 percent relative gain in Mean Reciprocal Rank over verbatim sentences, and using the evidence for verdict prediction raises Macro-F1 by 10-20 points over the baseline. These gains are consistent across different verdict granularities (2-class vs. 5-class) and model architectures. A qualitative analysis indicates that the decontextualized premises remain faithful to the original sources. Our work highlights the promise of reusing fact-checkers' evidence for automation and provides a large-scale resource of structured evidence from real-world fact-checks.

cs.CL↗

arXiv2026

Uncovering Temporal Framing in the News

Temporal language does more than place events on a timeline. In news discourse, references to the past, present, and future can function as rhetorical devices that shape interpretation and persuasion. Here, we study temporal framing, defined as the persuasive use of time-related language to structure meaning rather than to report chronology. We propose a taxonomy of eight temporal frames grounded in prior work on temporality and framing, and we realize it through expert annotation of a multilingual news corpus. The resulting dataset includes 458 English and German news articles, with over 2K temporally framed sentences and approximately 3K temporal framing annotations identified from a corpus of more than 20K sentences. We analyze frame prevalence, co-occurrence patterns, and lexical cues, and evaluate temporal framing detection using supervised fine-tuning and zero-shot classification. Our experiments show that temporal framing is learnable at the sentence level, with supervised models substantially outperforming zero-shot approaches. We publicly release the corpus to support future research on temporal framing: https://mbzuai-nlp.github.io/temporal-framing/.

cs.CL↗

arXiv2026

What Are We Measuring in NLG? A Meta-Analysis of Evaluation Trends 2020-2025

As Natural Language Generation (NLG) dominates modern NLP, scalable evaluation remains a critical bottleneck. Consequently, LLM-as-a-judge (LaaJ) adoption has accelerated rapidly, appearing in more papers than human evaluation in 2025. This pivotal shift motivates a critical analysis of current evaluation practices. Overcoming the limits of rigid keyword filtering and manual review, we employ a multi-LLM information extraction pipeline to gather structured metadata from 14,171 papers across four major NLP conferences (2020-2025). Analyzing 3,334 filtered NLG papers, we identify three systemic challenges. (1) Metric inertia: despite the shift toward open-ended generation, legacy lexical metrics (BLEU, ROUGE) persist as primary indicators, typically used alongside rather than replaced by semantic alternatives. (2) Metric-criteria mapping problem: our paper-level co-occurrence data reveals that general-purpose automatic metrics are applied as broad proxies for quality, without specifying which dimension of text generation they are intended to evaluate. (3) Validation gap: LaaJ has grown rapidly without commensurate human validation (fewer than 8% of papers). Crucially, while LaaJ correlates with aggregate quality, alignment collapses on fine-grained criteria like fluency. To address these gaps, we distill our findings into a minimal Evaluation Checklist to guide metric selection, construct validity, and LaaJ deployment.

cs.CL↗

arXiv2026

Fine-tuning with Hierarchical Prompting for Robust Propaganda Classification Across Annotation Schemas

Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. We introduce a new intent-focused taxonomy of propaganda techniques and compare it against an established, higher-agreement schema. Along three dimensions (model portfolio, schema effects, and prompting strategy) we evaluate the taxonomies as a classification task with the help of four language models (GPT-4.1-nano, Phi-4 14B, Qwen2.5-14B, Qwen3-14B). Our results show that fine-tuning is essential, since it transforms weak zero-shot baselines into competitive systems and reveals methodological differences that are hidden using base models. Across schemas, the Qwen models achieve the strongest overall performance, and Phi-4 14B consistently outperforms GPT-4.1-nano. Our hierarchical prompting method (HiPP), which predicts fine-grained techniques before aggregating them, is especially beneficial after fine-tuning and on the more ambiguous, low-agreement taxonomy, while remaining competitive on the simpler schema. The HQP dataset, annotated with the new intent-based labels, provides a richer lens on propaganda's strategic goals and a challenging benchmark for future work on robust, real-world detection.

cs.CL↗

arXiv2026

Graph-Based Detection of Disinformation Narrative Diffusion between Russian and Ukrainian Telegram Channels

Detecting disinformation narratives on social media is challenging due to the scale of amplification, rapid evolution, and linguistic variability of online content. We propose a graph-based framework for identifying and analyzing disinformation narratives in Telegram ecosystems by combining weak supervision with propagation graph analysis. The approach aggregates semantically related claims into narrative-level clusters and models their diffusion across interconnected channels. This enables the detection of coordinated narrative amplification that is difficult to capture through post-level analysis alone. Our results demonstrate that integrating textual signals with network structure provides a scalable method for detecting disinformation narratives and offers insights into how they propagate within large-scale messaging environments.

cs.CL↗

arXiv2026

Retrieving Climate Change Disinformation by Narrative

Detecting climate disinformation narratives typically relies on fixed taxonomies, which do not accommodate emerging narratives. Thus, we re-frame narrative detection as a retrieval task: given a narrative's core message as a query, rank texts from a corpus by alignment with that narrative. This formulation requires no predefined label set and can accommodate emerging narratives. We repurpose three climate disinformation datasets (CARDS, Climate Obstruction, climate change subset of PolyNarrative) for retrieval evaluation and propose SpecFi, a framework that generates hypothetical documents to bridge the gap between abstract narrative descriptions and their concrete textual instantiations. SpecFi uses community summaries from graph-based community detection as few-shot examples for generation, achieving a MAP of 0.505 on CARDS without access to narrative labels. We further introduce narrative variance, an embedding-based difficulty metric, and show via partial correlation analysis that standard retrieval degrades on high-variance narratives (BM25 loses 63.4% of MAP), while SpecFi-CS remains robust (32.7% loss). Our analysis also reveals that unsupervised community summaries converge on descriptions close to expert-crafted taxonomies, suggesting that graph-based methods can surface narrative structure from unlabeled text.

cs.CL↗

arXiv2026

ClimateCheck 2026: Scientific Fact-Checking and Disinformation Narrative Classification of Climate-related Claims

Automatically verifying climate-related claims against scientific literature is a challenging task, complicated by the specialised nature of scholarly evidence and the diversity of rhetorical strategies underlying climate disinformation. ClimateCheck 2026 is the second iteration of a shared task addressing this challenge, expanding on the 2025 edition with tripled training data and a new disinformation narrative classification task. Running from January to February 2026 on the CodaBench platform, the competition attracted 20 registered participants and 8 leaderboard submissions, with systems combining dense retrieval pipelines, cross-encoder ensembles, and large language models with structured hierarchical reasoning. In addition to standard evaluation metrics (Recall@K and Binary Preference), we adapt an automated framework to assess retrieval quality under incomplete annotations, exposing systematic biases in how conventional metrics rank systems. A cross-task analysis further reveals that not all climate disinformation is equally verifiable, potentially implicating how future fact-checking systems should be designed.

cs.CL↗

arXiv2026

Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation

LLMs are increasingly embedded in programming workflows, from code generation to automated code review. Yet, how gendered communication styles interact with LLM-assisted programming and code review remains underexplored. We present a mixed-methods pilot study examining whether gender-related linguistic differences in prompts influence code generation outcomes and code review decisions. Across three complementary studies, we analyze (i) collected real-world coding prompts, (ii) a controlled user study, in which developers solve identical programming tasks with LLM assistance, and (iii) an LLM-based simulated evaluation framework that systematically varies gender-coded prompt styles and reviewer personas. We find that gender-related differences in prompting style are subtle but measurable, with female-authored prompts exhibiting more indirect and involved language, which does not translate into consistent gaps in functional correctness or static code quality. For LLM code review, in contrast, we observe systematic biases: on average, models approve female-authored code more, despite comparable quality. Controlled experiments show that gender-coded prompt style affect code length and maintainability, while reviewer behavior varies across models. Our findings suggest that fairness risks in LLM-assisted programming arise less from generation accuracy than from LLM evaluation, as LLMs are increasingly deployed as automated code reviewers.

cs.SE↗

arXiv2026

Multiperspectivity as a Resource for Narrative Similarity Prediction

Predicting narrative similarity can be understood as an inherently interpretive task: different, equally valid readings of the same text can produce divergent interpretations and thus different similarity judgments, posing a fundamental challenge for semantic evaluation benchmarks that encode a single ground truth. Rather than treating this multiperspectivity as a challenge to overcome, we propose to incorporate it in the decision making process of predictive systems. To explore this strategy, we created an ensemble of 31 LLM personas. These range from practitioners following interpretive frameworks to more intuitive, lay-style characters. Our experiments were conducted on the SemEval-2026 Task 4 dataset, where the system achieved an accuracy score of 0.705. Accuracy improves with ensemble size, consistent with Condorcet Jury Theorem-like dynamics under weakened independence. Practitioner personas perform worse individually but produce less correlated errors, yielding larger ensemble gains under majority voting. Our error analysis reveals a consistent negative association between gender-focused interpretive vocabulary and accuracy across all persona categories, suggesting either attention to dimensions not relevant for the benchmark or valid interpretations absent from the ground truth. This finding underscores the need for evaluation frameworks that account for interpretive plurality.

cs.CL↗

arXiv2026

LLMs as Strategic Actors: Behavioral Alignment, Risk Calibration, and Argumentation Framing in Geopolitical Simulations

Large language models (LLMs) are increasingly proposed as agents in strategic decision environments, yet their behavior in structured geopolitical simulations remains under-researched. We evaluate six popular state-of-the-art LLMs alongside results from human results across four real-world crisis simulation scenarios, requiring models to select predefined actions and justify their decisions across multiple rounds. We compare models to humans in action alignment, risk calibration through chosen actions' severity, and argumentative framing grounded in international relations theory. Results show that models approximate human decision patterns in base simulation rounds but diverge over time, displaying distinct behavioural profiles and strategy updates. LLM explanations for chosen actions across all models exhibit a strong normative-cooperative framing centered on stability, coordination, and risk mitigation, with limited adversarial reasoning.

cs.CL↗

arXiv2026

Beyond Text-to-SQL: Autonomous Research-Driven Database Exploration with DAR

Large language models can already query databases, yet most existing systems remain reactive: they rely on explicit user prompts and do not actively explore data. We introduce DAR (Data Agnostic Researcher), a multi-agent system that performs end-to-end database research without human-initiated queries. DAR orchestrates specialized AI agents across three layers: initialization (intent inference and metadata extraction), execution (SQL and AI-based query synthesis with iterative validation), and synthesis (report generation with built-in quality control). All reasoning is executed directly inside BigQuery using native generative AI functions, eliminating data movement and preserving data governance. On a realistic asset-incident dataset, DAR completes the full analytical task in 16 minutes, compared to 8.5 hours for a professional analyst (approximately 32x times faster), while producing useful pattern-based insights and evidence-grounded recommendations. Although human experts continue to offer deeper contextual interpretation, DAR excels at rapid exploratory analysis. Overall, this work shifts database interaction from query-driven assistance toward autonomous, research-driven exploration within cloud data warehouses.

cs.DB↗

arXiv2026

Online Density-Based Clustering for Real-Time Narrative Evolution Monitorin

Automated narrative intelligence systems for social media monitoring face significant scalability challenges when relying on batch clustering methods to process continuous data streams. We investigate replacing offline HDBSCAN with online density-based clustering algorithms in a production narrative report generation pipeline that processes large volumes of multilingual social media data. While HDBSCAN effectively discovers hierarchical clusters and handles noise, its batch-only nature requires full retraining for each time window, limiting scalability and real-time adaptability. We evaluate online clustering methods with respect to cluster quality, computational efficiency, memory footprint, and integration with downstream narrative extraction. Our evaluation combines standard clustering metrics, narrative-specific measures, and human validation of cluster correctness to assess both structural quality and semantic interpretability. Experiments using sliding-window simulations on historical data from the Ukrainian information space reveal trade-offs between temporal stability and narrative coherence, with DenStream achieving the strongest overall performance. These findings bridge the gap between batch-oriented clustering approaches and the streaming requirements of large-scale narrative monitoring systems.

cs.CL↗

arXiv2025

XplaiNLP at CheckThat! 2025: Multilingual Subjectivity Detection with Finetuned Transformers and Prompt-Based Inference with Large Language Models

This notebook reports the XplaiNLP submission to the CheckThat! 2025 shared task on multilingual subjectivity detection. We evaluate two approaches: (1) supervised fine-tuning of transformer encoders, EuroBERT, XLM-RoBERTa, and German-BERT, on monolingual and machine-translated training data; and (2) zero-shot prompting using two LLMs: o3-mini for Annotation (rule-based labelling) and gpt-4.1-mini for DoubleDown (contrastive rewriting) and Perspective (comparative reasoning). The Annotation Approach achieves 1st place in the Italian monolingual subtask with an F_1 score of 0.8104, outperforming the baseline of 0.6941. In the Romanian zero-shot setting, the fine-tuned XLM-RoBERTa model obtains an F_1 score of 0.7917, ranking 3rd and exceeding the baseline of 0.6461. The same model also performs reliably in the multilingual task and improves over the baseline in Greek. For German, a German-BERT model fine-tuned on translated training data from typologically related languages yields competitive performance over the baseline. In contrast, performance in the Ukrainian and Polish zero-shot settings falls slightly below the respective baselines, reflecting the challenge of generalization in low-resource cross-lingual scenarios.

cs.CL↗

arXiv2025

Hybrid Annotation for Propaganda Detection: Integrating LLM Pre-Annotations with Human Intelligence

Propaganda detection on social media remains challenging due to task complexity and limited high-quality labeled data. This paper introduces a novel framework that combines human expertise with Large Language Model (LLM) assistance to improve both annotation consistency and scalability. We propose a hierarchical taxonomy that organizes 14 fine-grained propaganda techniques into three broader categories, conduct a human annotation study on the HQP dataset that reveals low inter-annotator agreement for fine-grained labels, and implement an LLM-assisted pre-annotation pipeline that extracts propagandistic spans, generates concise explanations, and assigns local labels as well as a global label. A secondary human verification study shows significant improvements in both agreement and time-efficiency. Building on this, we fine-tune smaller language models (SLMs) to perform structured annotation. Instead of fine-tuning on human annotations, we train on high-quality LLM-generated data, allowing a large model to produce these annotations and a smaller model to learn to generate them via knowledge distillation. Our work contributes towards the development of scalable and robust propaganda detection systems, supporting the idea of transparent and accountable media ecosystems in line with SDG 16. The code is publicly available at our GitHub repository.

cs.CL↗

arXiv2025

MisinfoTeleGraph: Network-driven Misinformation Detection for German Telegram Messages

Connectivity and message propagation are central, yet often underutilized, sources of information in misinformation detection -- especially on poorly moderated platforms such as Telegram, which has become a critical channel for misinformation dissemination, namely in the German electoral context. In this paper, we introduce Misinfo-TeleGraph, the first German-language Telegram-based graph dataset for misinformation detection. It includes over 5 million messages from public channels, enriched with metadata, channel relationships, and both weak and strong labels. These labels are derived via semantic similarity to fact-checks and news articles using M3-embeddings, as well as manual annotation. To establish reproducible baselines, we evaluate both text-only models and graph neural networks (GNNs) that incorporate message forwarding as a network structure. Our results show that GraphSAGE with LSTM aggregation significantly outperforms text-only baselines in terms of Matthews Correlation Coefficient (MCC) and F1-score. We further evaluate the impact of subscribers, view counts, and automatically versus human-created labels on performance, and highlight both the potential and challenges of weak supervision in this domain. This work provides a reproducible benchmark and open dataset for future research on misinformation detection in German-language Telegram networks and other low-moderation social platforms.

cs.CL↗

arXiv2025

From Trust to Truth: Actionable policies for the use of AI in fact-checking in Germany and Ukraine

The rise of Artificial Intelligence (AI) presents unprecedented opportunities and challenges for journalism, fact-checking and media regulation. While AI offers tools to combat disinformation and enhance media practices, its unregulated use and associated risks necessitate clear policies and collaborative efforts. This policy paper explores the implications of artificial intelligence (AI) for journalism and fact-checking, with a focus on addressing disinformation and fostering responsible AI integration. Using Germany and Ukraine as key case studies, it identifies the challenges posed by disinformation, proposes regulatory and funding strategies, and outlines technical standards to enhance AI adoption in media. The paper offers actionable recommendations to ensure AI's responsible and effective integration into media ecosystems. AI presents significant opportunities to combat disinformation and enhance journalistic practices. However, its implementation lacks cohesive regulation, leading to risks such as bias, transparency issues, and over-reliance on automated systems. In Ukraine, establishing an independent media regulatory framework adapted to its governance is crucial, while Germany can act as a leader in advancing EU-wide collaborations and standards. Together, these efforts can shape a robust AI-driven media ecosystem that promotes accuracy and trust.

cs.CY↗

arXiv2025

How desirable is alignment between LLMs and linguistically diverse human users?

We discuss how desirable it is that Large Language Models (LLMs) be able to adapt or align their language behavior with users who may be diverse in their language use. User diversity may come about among others due to i) age differences; ii) gender characteristics, and/or iii) multilingual experience, and associated differences in language processing and use. We consider potential consequences for usability, communication, and LLM development.

cs.CL↗