arXiv subjects

Ramon Ruiz-Dolz

Publications and source records attributed to Ramon Ruiz-Dolz.

11 recordsLinked to original sources

arXiv2026

When Composition Doesn't Add Up: Humans Identifying Defects in AI-Generated Images

*Chulin Zhao and Ruoqi Hu contributed equally to this work. State-of-the-art text-to-image (T2I) models exhibit pronounced and systematic defects when prompts involve intricate compositional factors such as multiple entities and multiple attributes. In this paper, we investigate how humans identify such defects. Specifically, we manually select 651 reference images from the four categories of people, hand, object, and scene that exhibit complex compositional characteristics, from which prompts emphasizing compositional factors are derived by manually editing ChatGPT-generated prompts. We then feed the prompts into three selected T2I models to generate AI images and conduct a comprehensive subjective study to identify their defects. For each image, 29 participants provide multi-label assessments specifying defect types and locations. The study yields the compositional AI-generated image defect (CO-AID) dataset, including reference images, prompts, AI-generated images, and information on defect locations and types. Experimental results show that training a deep model on CO-AID can both predict defects in AI-generated images and optimize AI image generation, demonstrating its usability and effectiveness. The database and supplementary materials are available at: https://github.com/Future-IQA/CO-AID .

cs.CV↗

arXiv2026

Security and Privacy in Agentic AI: Grand Challenges and Future Directions

We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading international experts from academia, industry, and government to engage in focused discussions and collaborative exercises on the emerging risks associated with the growing agency of AI.

cs.CR↗

arXiv2026

Show Me How You Reason and I'll Tell You Who You Are: Reasoning Graphs for Robust LLM Authorship Attribution

Given the current trend to employ large language models (LLMs) in almost any imaginable context, LLM-generated text detection and authorship attribution have become a pressing issue. Prior work has primarily focused on surface-level linguistic features, an approach shown to be susceptible to paraphrasing and other obfuscation techniques. In this paper, we go beyond the linguistic surface, extracting and analysing reasoning structures in LLM-generated texts with the goal of capturing more complex signals of LLM authorship. We propose a graph neural network approach that leverages reasoning graphs extracted by an argument mining pipeline, demonstrating improved robustness and generalisation over a traditional Longformer baseline. Our approach outperforms the baseline by up to 27 percentage points under the obfuscation attacks such as paraphrasing and backtranslation, and 19 percentage points when evaluated on the texts generated by the unseen model versions, simulating real-world conditions in which new LLM versions are continuously released.

cs.CL↗

arXiv2026

A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks

This study aims to test and evaluate the capabilities and characteristics of current mainstream Visual Language Models (VLMs) in generating critiques for traditional Chinese painting. To achieve this, we first developed a quantitative framework for Chinese painting critique. This framework was constructed by extracting multi-dimensional evaluative features covering evaluative stance, feature focus, and commentary quality from human expert critiques using a zero-shot classification model. Based on these features, several representative critic personas were defined and quantified. This framework was then employed to evaluate selected VLMs such as Llama, Qwen, or Gemini. The experimental design involved persona-guided prompting to assess the VLM's ability to generate critiques from diverse perspectives. Our findings reveal the current performance levels, strengths, and areas for improvement of VLMs in the domain of art critique, offering insights into their potential and limitations in complex semantic understanding and content generation tasks. The code used for our experiments can be publicly accessed at: https://github.com/yha9806/VULCA-EMNLP2025.

cs.CL↗

arXiv2025

An Explainable Framework for Misinformation Identification via Critical Question Answering

Natural language misinformation detection approaches have been, to date, largely dependent on sequence classification methods, producing opaque systems in which the reasons behind classification as misinformation are unclear. While an effort has been made in the area of automated fact-checking to propose explainable approaches to the problem, this is not the case for automated reason-checking systems. In this paper, we propose a new explainable framework for both factual and rational misinformation detection based on the theory of Argumentation Schemes and Critical Questions. For that purpose, we create and release NLAS-CQ, the first corpus combining 3,566 textbook-like natural language argumentation scheme instances and 4,687 corresponding answers to critical questions related to these arguments. On the basis of this corpus, we implement and validate our new framework which combines classification with question answering to analyse arguments in search of misinformation, and provides the explanations in form of critical questions to the human user.

cs.CL↗

arXiv2024

NLAS-multi: A Multilingual Corpus of Automatically Generated Natural Language Argumentation Schemes

Some of the major limitations identified in the areas of argument mining, argument generation, and natural language argument analysis are related to the complexity of annotating argumentatively rich data, the limited size of these corpora, and the constraints that represent the different languages and domains in which these data is annotated. To address these limitations, in this paper we present the following contributions: (i) an effective methodology for the automatic generation of natural language arguments in different topics and languages, (ii) the largest publicly available corpus of natural language argumentation schemes, and (iii) a set of solid baselines and fine-tuned models for the automatic identification of argumentation schemes.

cs.CL↗

arXiv2024

Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks

The lack of annotated data on professional argumentation and complete argumentative debates has led to the oversimplification and the inability of approaching more complex natural language processing tasks. Such is the case of the automatic debate evaluation. In this paper, we propose an original hybrid method to automatically evaluate argumentative debates. For that purpose, we combine concepts from argumentation theory such as argumentation frameworks and semantics, with Transformer-based architectures and neural graph networks. Furthermore, we obtain promising results that lay the basis on an unexplored new instance of the automatic analysis of natural language arguments.

cs.CL↗

arXiv2024

VivesDebate-Speech: A Corpus of Spoken Argumentation to Leverage Audio Features for Argument Mining

In this paper, we describe VivesDebate-Speech, a corpus of spoken argumentation created to leverage audio features for argument mining tasks. The creation of this corpus represents an important contribution to the intersection of speech processing and argument mining communities, and one of the most complete publicly available resources in this topic. Moreover, we have performed a set of first-of-their-kind experiments which show an improvement when integrating audio features into the argument mining pipeline. The provided results can be used as a baseline for future research.

cs.CL↗

arXiv2022

Toward the Prevention of Privacy Threats: How Can We Persuade Our Social Network Platform Users?

Complex decision-making problems such as the privacy policy selection when sharing content in online social networks can significantly benefit from artificial intelligence systems. With the use of Computational Argumentation, it is possible to persuade human users to modify their initial decisions to avoid potential privacy threats and violations. In this paper, we present a study performed over 186 teenage users aimed at analysing their behaviour when we try to persuade them to modify the publication of sensitive content in Online Social Networks (OSN) with different arguments. The results of the study revealed that the personality traits and the social interaction data (e.g., number of comments, friends, and likes) of our participants were significantly correlated with the persuasive power of the arguments. Therefore, these sets of features can be used to model OSN users, and to estimate the persuasive power of different arguments when used in human-computer interactions. The findings presented in this paper are helpful for personalising decision support systems aimed at educating and preventing privacy violations in OSNs using arguments.

cs.SI↗

arXiv2022

A Cascade Model for Argument Mining in Japanese Political Discussions: the QA Lab-PoliInfo-3 Case Study

The rVRAIN team tackled the Budget Argument Mining (BAM) task, consisting of a combination of classification and information retrieval sub-tasks. For the argument classification (AC), the team achieved its best performing results with a five-class BERT-based cascade model complemented with some handcrafted rules. The rules were used to determine if the expression was monetary or not. Then, each monetary expression was classified as a premise or as a conclusion in the first level of the cascade model. Finally, each premise was classified into the three premise classes, and each conclusion into the two conclusion classes. For the information retrieval (i.e., relation ID detection or RID), our best results were achieved by a combination of a BERT-based binary classifier, and the cosine similarity of pairs consisting of the monetary expression and budget dense embeddings.

cs.CL↗

arXiv2021

Transformer-Based Models for Automatic Identification of Argument Relations: A Cross-Domain Evaluation

Argument Mining is defined as the task of automatically identifying and extracting argumentative components (e.g., premises, claims, etc.) and detecting the existing relations among them (i.e., support, attack, rephrase, no relation). One of the main issues when approaching this problem is the lack of data, and the size of the publicly available corpora. In this work, we use the recently annotated US2016 debate corpus. US2016 is the largest existing argument annotated corpus, which allows exploring the benefits of the most recent advances in Natural Language Processing in a complex domain like Argument (relation) Mining. We present an exhaustive analysis of the behavior of transformer-based models (i.e., BERT, XLNET, RoBERTa, DistilBERT and ALBERT) when predicting argument relations. Finally, we evaluate the models in five different domains, with the objective of finding the less domain dependent model. We obtain a macro F1-score of 0.70 with the US2016 evaluation corpus, and a macro F1-score of 0.61 with the Moral Maze cross-domain corpus.

cs.CL↗