Search arXiv⌕ Search

arXiv subjects

Kevin Roitero

Publications and source records attributed to Kevin Roitero.

18 recordsLinked to original sources
arXiv2026

Overview of ROMCIR 2026: The 6th Workshop on Reducing Online Misinformation through Credible Information Retrieval

In the digital online ecosystem, we are surrounded by distinct forms of information pollution, posing significant threats to both individuals and society. Fake news, for instance, wields power to sway public opinion on matters of politics and finance. Deceptive reviews can either bolster or tarnish the reputation of businesses, while unverified medical advice may steer people toward harmful health practices. In light of this challenging landscape, it has become imperative to ensure that users have access to both topically relevant and factually accurate information that does not warp their perception of reality, and there has been a surge of interest in various strategies to combat misinformation through different contexts and multiple tasks. The purpose of the ROMCIR Workshop, for some years now, is precisely that of engaging the Information Retrieval community to explore potential solutions that extend beyond conventional misinformation detection approaches. Key objectives include identifying subjective and objective factors associated with information credibility and truthfulness, respectively, and integrating such factors as fundamental dimensions of relevance within IR Systems (IRSs), achieving early detection of misinformation, and ensuring that the search results retrieved are not only truthful but also explainable to the users of IRSs. Moreover, it is essential to evaluate the role of generative models such as Large Language Models (LLMs) in inadvertently amplifying misinformation problems, and how they can be used to support IRSs, together with the contribution that the human-in-the-loop paradigm can have in this context.

cs.IR↗
arXiv2026

Exploring Geographic Relative Space in Large Language Models through Activation Patching

The increased use of Large Language Models (LLMs) in geography raises substantial questions about the safety of integrating these tools across a wide range of processes and analyses, given our very limited understanding of their inner workings. In this extended abstract, we examine how LLMs process relative geographic space using activation patching, an emerging tool for mechanistic interpretability.

cs.LG↗
arXiv2026

Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectiveness

Large language models (LLMs) show strong reasoning abilities across diverse tasks, yet their performance on extended contexts remains inconsistent. While prior research has emphasized mid-context degradation in question answering, this study examines the impact of context in LLM-based fact verification. Using three datasets (HOVER, FEVEROUS, and ClimateFEVER) and five open-source models accross different parameters sizes (7B, 32B and 70B parameters) and model families (Llama-3.1, Qwen2.5 and Qwen3), we evaluate both parametric factual knowledge and the impact of evidence placement across varying context lengths. We find that LLMs exhibit non-trivial parametric knowledge of factual claims and that their verification accuracy generally declines as context length increases. Similarly to what has been shown in previous works, in-context evidence placement plays a critical role with accuracy being consistently higher when relevant evidence appears near the beginning or end of the prompt and lower when placed mid-context. These results underscore the importance of prompt structure in retrieval-augmented fact-checking systems.

cs.CL↗
arXiv2025

Behavior and Representation in Open-Weight Large Language Models for Combinatorial Optimization: From Feature Extraction to Algorithm Selection

Recent advances in Large Language Models (LLMs) open new perspectives for automation in optimization, yet little is known about whether their internal representations capture problem structure or algorithmic behavior. We investigate whether representations learned by frozen, open-weight LLMs for combinatorial optimization instances can support downstream decision tasks. The goal is not to replace exact feature extractors or to propose a new algorithm, but to assess whether such representations are reusable for feature recovery and algorithm selection. Our methodology combines direct querying, which tests explicit feature extraction, with probing analyses of whether this information is implicitly encoded in the hidden layers. The probing framework is further extended to a per-instance algorithm selection task. Experiments span four benchmark problems, three instance representations, and five open-weight models from 3B to 120B parameters across the Llama instruct and GPT reasoning families, including a chain-of-thought study on Llama models. Results show a limited ability to recover features explicitly, particularly those requiring structured computation, while part of this information remains implicitly encoded in the hidden states. A consistent gap separates implicit encoding from explicit retrieval. Model scale attenuates this gap, whereas the effect of chain-of-thought prompting depends strongly on model size, and in all cases the gap remains open. Reasoning-oriented models also tend to abstain more when reliable computation is not possible. Notably, the predictive power of LLM hidden-layer representations is comparable to traditional feature extraction across all five models, indicating they can act as effective surrogate descriptors for downstream optimization tasks.

cs.AI↗
arXiv2025

The Effect of Document Summarization on LLM-Based Relevance Judgments

Relevance judgments are central to the evaluation of Information Retrieval (IR) systems, but obtaining them from human annotators is costly and time-consuming. Large Language Models (LLMs) have recently been proposed as automated assessors, showing promising alignment with human annotations. Most prior studies have treated documents as fixed units, feeding their full content directly to LLM assessors. We investigate how text summarization affects the reliability of LLM-based judgments and their downstream impact on IR evaluation. Using state-of-the-art LLMs across multiple TREC collections, we compare judgments made from full documents with those based on LLM-generated summaries of different lengths. We examine their agreement with human labels, their effect on retrieval effectiveness evaluation, and their influence on IR systems' ranking stability. Our findings show that summary-based judgments achieve comparable stability in systems' ranking to full-document judgments, while introducing systematic shifts in label distributions and biases that vary by model and dataset. These results highlight summarization as both an opportunity for more efficient large-scale IR evaluation and a methodological choice with important implications for the reliability of automatic judgments.

cs.IR↗
arXiv2025

On Robustness and Reliability of Benchmark-Based Evaluation of LLMs

Large Language Models (LLMs) effectiveness is usually evaluated by means of benchmarks such as MMLU, ARC-C, or HellaSwag, where questions are presented in their original wording, thus in a fixed, standardized format. However, real-world applications involve linguistic variability, requiring models to maintain their effectiveness across diverse rewordings of the same question or query. In this study, we systematically assess the robustness of LLMs to paraphrased benchmark questions and investigate whether benchmark-based evaluations provide a reliable measure of model capabilities. We systematically generate various paraphrases of all the questions across six different common benchmarks, and measure the resulting variations in effectiveness of 34 state-of-the-art LLMs, of different size and effectiveness. Our findings reveal that while LLM rankings remain relatively stable across paraphrased inputs, absolute effectiveness scores change, and decline significantly. This suggests that LLMs struggle with linguistic variability, raising concerns about their generalization abilities and evaluation methodologies. Furthermore, the observed performance drop challenges the reliability of benchmark-based evaluations, indicating that high benchmark scores may not fully capture a model's robustness to real-world input variations. We discuss the implications of these findings for LLM evaluation methodologies, emphasizing the need for robustness-aware benchmarks that better reflect practical deployment scenarios.

cs.CL↗
arXiv2025

Political Ideology Shifts in Large Language Models

Large language models (LLMs) are increasingly deployed in politically sensitive contexts, raising concerns about their susceptibility to ideological biases. In this work, we examine how synthetic persona conditioning shapes ideological expression across seven open-weight instruction-tuned models (7B-72B parameters) using the Political Compass Test (62 statements) as a standardized behavioral probe. Across three studies involving 200,000 synthetic personas and more than 260 million model responses, we analyze implicit and explicit malleability, as well as theme-associated variations. We find that: (i) larger models exhibit broader implicit ideological coverage, increasing from 14-35% for 7-8B models to up to 49% for 70B+ models; (ii) explicit ideological priming induces large and statistically significant shifts, with right-authoritarian cues moving all models in the intended direction and producing larger effects in most model-axis comparisons; (iii) left-libertarian priming produces more heterogeneous responses, including counter-directional economic shifts in three of four 7-8B models, while all 70B+ models move in the intended direction; and (iv) theme-associated semantic content in persona descriptions is linked to systematic and interpretable directional shifts in ideological space. While our results identify an upstream mechanism through which persona conditioning can alter model responses under a standardized ideological probe, we do not test whether such shifts affect users beliefs, decisions, or political behavior. Our findings are best understood as evidence of ideological malleability at the generation layer, highlighting the need to account for interactional factors when evaluating political neutrality, fairness, and safety in English-prompted, persona-conditioned language models.

cs.CL↗
arXiv2025

Large Language Models for Combinatorial Optimization: A Systematic Review

This systematic review explores the application of Large Language Models (LLMs) in Combinatorial Optimization (CO). We report our findings using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We conduct a literature search via Scopus and Google Scholar, examining over 2,000 publications. We assess publications against four inclusion and four exclusion criteria related to their language, research focus, publication year, and type. Eventually, we select 103 studies. We classify these studies into semantic categories and topics to provide a comprehensive overview of the field, including the tasks performed by LLMs, the architectures of LLMs, the existing datasets specifically designed for evaluating LLMs in CO, and the field of application. Finally, we identify future directions for leveraging LLMs in this field.

cs.AI↗
arXiv2025

Geospatial Mechanistic Interpretability of Large Language Models

Large Language Models (LLMs) have demonstrated unprecedented capabilities across various natural language processing tasks. Their ability to process and generate viable text and code has made them ubiquitous in many fields, while their deployment as knowledge bases and "reasoning" tools remains an area of ongoing research. In geography, a growing body of literature has been focusing on evaluating LLMs' geographical knowledge and their ability to perform spatial reasoning. However, very little is still known about the internal functioning of these models, especially about how they process geographical information. In this chapter, we establish a novel framework for the study of geospatial mechanistic interpretability - using spatial analysis to reverse engineer how LLMs handle geographical information. Our aim is to advance our understanding of the internal representations that these complex models generate while processing geographical information - what one might call "how LLMs think about geographic information" if such phrasing was not an undue anthropomorphism. We first outline the use of probing in revealing internal structures within LLMs. We then introduce the field of mechanistic interpretability, discussing the superposition hypothesis and the role of sparse autoencoders in disentangling polysemantic internal representations of LLMs into more interpretable, monosemantic features. In our experiments, we use spatial autocorrelation to show how features obtained for placenames display spatial patterns related to their geographic location and can thus be interpreted geospatially, providing insights into how these models process geographical information. We conclude by discussing how our framework can help shape the study and use of foundation models in geography.

cs.LG↗
arXiv2025

Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking

Evaluating the truthfulness of online content is critical for combating misinformation. This study examines the efficiency and effectiveness of crowdsourced truthfulness assessments through a comparative analysis of two approaches: one involving full-length webpages as evidence for each claim, and another using summaries for each evidence document generated with a large language model. Using an A/B testing setting, we engage a diverse pool of participants tasked with evaluating the truthfulness of statements under these conditions. Our analysis explores both the quality of assessments and the behavioral patterns of participants. The results reveal that relying on summarized evidence offers comparable accuracy and error metrics to the Standard modality while significantly improving efficiency. Workers in the Summary setting complete a significantly higher number of assessments, reducing task duration and costs. Additionally, the Summary modality maximizes internal agreement and maintains consistent reliance on and perceived usefulness of evidence, demonstrating its potential to streamline large-scale truthfulness evaluations.

cs.IR↗
arXiv2024

Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas

The analysis of political biases in large language models (LLMs) has primarily examined these systems as single entities with fixed viewpoints. While various methods exist for measuring such biases, the impact of persona-based prompting on LLMs' political orientation remains unexplored. In this work we leverage PersonaHub, a collection of synthetic persona descriptions, to map the political distribution of persona-based prompted LLMs using the Political Compass Test (PCT). We then examine whether these initial compass distributions can be manipulated through explicit ideological prompting towards diametrically opposed political orientations: right-authoritarian and left-libertarian. Our experiments reveal that synthetic personas predominantly cluster in the left-libertarian quadrant, with models demonstrating varying degrees of responsiveness when prompted with explicit ideological descriptors. While all models demonstrate significant shifts towards right-authoritarian positions, they exhibit more limited shifts towards left-libertarian positions, suggesting an asymmetric response to ideological manipulation that may reflect inherent biases in model training.

cs.CL↗
arXiv2023

Data Bias Management

Due to the widespread use of data-powered systems in our everyday lives, concepts like bias and fairness gained significant attention among researchers and practitioners, in both industry and academia. Such issues typically emerge from the data, which comes with varying levels of quality, used to train supervised machine learning systems. With the commercialization and deployment of such systems that are sometimes delegated to make life-changing decisions, significant efforts are being made towards the identification and removal of possible sources of data bias that may resurface to the final end user or in the decisions being made. In this paper, we present research results that show how bias in data affects end users, where bias is originated, and provide a viewpoint about what we should do about it. We argue that data bias is not something that should necessarily be removed in all cases, and that research attention should instead shift from bias removal towards the identification, measurement, indexing, surfacing, and adapting for bias, which we name bias management.

cs.LG↗
arXiv2021

Managing Bias in Human-Annotated Data: Moving Beyond Bias Removal

Due to the widespread use of data-powered systems in our everyday lives, the notions of bias and fairness gained significant attention among researchers and practitioners, in both industry and academia. Such issues typically emerge from the data, which comes with varying levels of quality, used to train systems. With the commercialization and employment of such systems that are sometimes delegated to make life-changing decisions, a significant effort is being made towards the identification and removal of possible sources of bias that may surface to the final end-user. In this position paper, we instead argue that bias is not something that should necessarily be removed in all cases, and the attention and effort should shift from bias removal to the identification, measurement, indexing, surfacing, and adjustment of bias, which we name bias management. We argue that if correctly managed, bias can be a resource that can be made transparent to the the users and empower them to make informed choices about their experience with the system.

cs.IR↗
arXiv2021

The Many Dimensions of Truthfulness: Crowdsourcing Misinformation Assessments on a Multidimensional Scale

Recent work has demonstrated the viability of using crowdsourcing as a tool for evaluating the truthfulness of public statements. Under certain conditions such as: (1) having a balanced set of workers with different backgrounds and cognitive abilities; (2) using an adequate set of mechanisms to control the quality of the collected data; and (3) using a coarse grained assessment scale, the crowd can provide reliable identification of fake news. However, fake news are a subtle matter: statements can be just biased ("cherrypicked"), imprecise, wrong, etc. and the unidimensional truth scale used in existing work cannot account for such differences. In this paper we propose a multidimensional notion of truthfulness and we ask the crowd workers to assess seven different dimensions of truthfulness selected based on existing literature: Correctness, Neutrality, Comprehensibility, Precision, Completeness, Speaker's Trustworthiness, and Informativeness. We deploy a set of quality control mechanisms to ensure that the thousands of assessments collected on 180 publicly available fact-checked statements distributed over two datasets are of adequate quality, including a custom search engine used by the crowd workers to find web pages supporting their truthfulness assessments. A comprehensive analysis of crowdsourced judgments shows that: (1) the crowdsourced assessments are reliable when compared to an expert-provided gold standard; (2) the proposed dimensions of truthfulness capture independent pieces of information; (3) the crowdsourcing task can be easily learned by the workers; and (4) the resulting assessments provide a useful basis for a more complete estimation of statement truthfulness.

cs.IR↗
arXiv2021

Can the Crowd Judge Truthfulness? A Longitudinal Study on Recent Misinformation about COVID-19

Recently, the misinformation problem has been addressed with a crowdsourcing-based approach: to assess the truthfulness of a statement, instead of relying on a few experts, a crowd of non-expert is exploited. We study whether crowdsourcing is an effective and reliable method to assess truthfulness during a pandemic, targeting statements related to COVID-19, thus addressing (mis)information that is both related to a sensitive and personal issue and very recent as compared to when the judgment is done. In our experiments, crowd workers are asked to assess the truthfulness of statements, and to provide evidence for the assessments. Besides showing that the crowd is able to accurately judge the truthfulness of the statements, we report results on workers behavior, agreement among workers, effect of aggregation functions, of scales transformations, and of workers background and bias. We perform a longitudinal study by re-launching the task multiple times with both novice and experienced workers, deriving important insights on how the behavior and quality change over time. Our results show that: workers are able to detect and objectively categorize online (mis)information related to COVID-19; both crowdsourced and expert judgments can be transformed and aggregated to improve quality; worker background and other signals (e.g., source of information, behavior) impact the quality of the data. The longitudinal study demonstrates that the time-span has a major effect on the quality of the judgments, for both novice and experienced workers. Finally, we provide an extensive failure analysis of the statements misjudged by the crowd-workers.

cs.IR↗
arXiv2020

Cheap IR Evaluation: Fewer Topics, No Relevance Judgements, and Crowdsourced Assessments

To evaluate Information Retrieval (IR) effectiveness, a possible approach is to use test collections, which are composed of a collection of documents, a set of description of information needs (called topics), and a set of relevant documents to each topic. Test collections are modelled in a competition scenario: for example, in the well known TREC initiative, participants run their own retrieval systems over a set of topics and they provide a ranked list of retrieved documents; some of the retrieved documents (usually the first ranked) constitute the so called pool, and their relevance is evaluated by human assessors; the document list is then used to compute effectiveness metrics and rank the participant systems. Private Web Search companies also run their in-house evaluation exercises; although the details are mostly unknown, and the aims are somehow different, the overall approach shares several issues with the test collection approach. The aim of this work is to: (i) develop and improve some state-of-the-art work on the evaluation of IR effectiveness while saving resources, and (ii) propose a novel, more principled and engineered, overall approach to test collection based effectiveness evaluation. [...]

cs.IR↗
arXiv2020

The COVID-19 Infodemic: Can the Crowd Judge Recent Misinformation Objectively?

Misinformation is an ever increasing problem that is difficult to solve for the research community and has a negative impact on the society at large. Very recently, the problem has been addressed with a crowdsourcing-based approach to scale up labeling efforts: to assess the truthfulness of a statement, instead of relying on a few experts, a crowd of (non-expert) judges is exploited. We follow the same approach to study whether crowdsourcing is an effective and reliable method to assess statements truthfulness during a pandemic. We specifically target statements related to the COVID-19 health emergency, that is still ongoing at the time of the study and has arguably caused an increase of the amount of misinformation that is spreading online (a phenomenon for which the term "infodemic" has been used). By doing so, we are able to address (mis)information that is both related to a sensitive and personal issue like health and very recent as compared to when the judgment is done: two issues that have not been analyzed in related work. In our experiment, crowd workers are asked to assess the truthfulness of statements, as well as to provide evidence for the assessments as a URL and a text justification. Besides showing that the crowd is able to accurately judge the truthfulness of the statements, we also report results on many different aspects, including: agreement among workers, the effect of different aggregation functions, of scales transformations, and of workers background / bias. We also analyze workers behavior, in terms of queries submitted, URLs found / selected, text justifications, and other behavioral data like clicks and mouse actions collected by means of an ad hoc logger.

cs.IR↗
arXiv2020

Can The Crowd Identify Misinformation Objectively? The Effects of Judgment Scale and Assessor's Background

Truthfulness judgments are a fundamental step in the process of fighting misinformation, as they are crucial to train and evaluate classifiers that automatically distinguish true and false statements. Usually such judgments are made by experts, like journalists for political statements or medical doctors for medical statements. In this paper, we follow a different approach and rely on (non-expert) crowd workers. This of course leads to the following research question: Can crowdsourcing be reliably used to assess the truthfulness of information and to create large-scale labeled collections for information credibility systems? To address this issue, we present the results of an extensive study based on crowdsourcing: we collect thousands of truthfulness assessments over two datasets, and we compare expert judgments with crowd judgments, expressed on scales with various granularity levels. We also measure the political bias and the cognitive background of the workers, and quantify their effect on the reliability of the data provided by the crowd.

cs.IR↗