Ramon Ruiz-Dolz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ramon Ruiz-Dolz has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- John Lawrence
University of Dundee
5 shared publications - Stella Heras
Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, 46022 València, Spain
5 shared publications - Ana García-Fornes
Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Politècnica de València, Valencia, Spain
4 shared publications - Chris Reed
Centre for Argument Technology University of Dundee DD1 4HN Dundee United Kingdom
4 shared publications - Jose Alemany
Universitat Politècnica de València
3 shared publications Ana García-Fornes
VRAIN Universitat Politècnica de València 46022 València Spain
2 shared publications
Latest Publications
- Open Access
- 10 September 2026
- Published by IOS Press
- p. 65-76
Can Large Language Models Identify Reasoning Patterns in Low-Resource Languages? A Case Study of Argumentation Schemes in Catalan
The identification of argumentation schemes seeks to uncover patterns of human reasoning in natural language, but it is a complex task, particularly in languages with limited resources, due to the scarcity of annotated data and the implicit nature of argumentative elements. In this paper, we present a study on argumentation scheme identification focusing on Catalan and English, in which we introduce the VivesDebate-7D-Schemes corpus, containing 282 annotated schemes from university debates. We compare three approaches: machine translation combined with a task-specific pre-trained model, translation combined with in-context learning based on large language models (LLMs), and in-context learning with LLMs compatible with Catalan. Our results on argumentation scheme family identification show that language-compatible LLMs outperform translation-based methods, highlighting the importance of preserving linguistic and pragmatic information. However, overall performance remains lower than that of task-specific models in languages with more resources. Furthermore, our corpus analysis reveals a strong bias towards specific schemes, showing the predominance of explanatory and consequence-based reasoning in debate contexts.
- 10 September 2026
- Published by IOS Press
- p. 65-76
Open AccessCan Large Language Models Identify Reasoning Patterns in Low-Resource Languages? A Case Study of Argumentation Schemes in Catalan
The identification of argumentation schemes seeks to uncover patterns of human reasoning in natural language, but it is a complex task, particularly in languages with limited resources, due to the scarcity of annotated data and the implicit nature of argumentative elements. In this paper, we present a study on argumentation scheme identification focusing on Catalan and English, in which we introduce the VivesDebate-7D-Schemes corpus, containing 282 annotated schemes from university debates. We compare three approaches: machine translation combined with a task-specific pre-trained model, translation combined with in-context learning based on large language models (LLMs), and in-context learning with LLMs compatible with Catalan. Our results on argumentation scheme family identification show that language-compatible LLMs outperform translation-based methods, highlighting the importance of preserving linguistic and pragmatic information. However, overall performance remains lower than that of task-specific models in languages with more resources. Furthermore, our corpus analysis reveals a strong bias towards specific schemes, showing the predominance of explanatory and consequence-based reasoning in debate contexts.
- Open Access
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.
Open AccessAn 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.
- 13 February 2025
- Published by Springer Nature in Autonomous Agents and Multi-Agent Systems
- Vol. 39 (1) , 1-59
An introduction to computational argumentation research from a human argumentation perspective
- 13 February 2025
- Published by Springer Nature in Autonomous Agents and Multi-Agent Systems
- Vol. 39 (1) , 1-59
An introduction to computational argumentation research from a human argumentation perspective
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 1945-1971
A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks
Haorui Yu, Ramon Ruiz-Dolz, Qiufeng Yi. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 1945-1971
Open AccessA Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks
Haorui Yu, Ramon Ruiz-Dolz, Qiufeng Yi. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 3717-3741
Natural Language Reasoning in Large Language Models: Analysis and Evaluation
Debela Gemechu, Ramon Ruiz-Dolz, Henrike Beyer, Chris Reed. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 3717-3741
Open AccessNatural Language Reasoning in Large Language Models: Analysis and Evaluation
Debela Gemechu, Ramon Ruiz-Dolz, Henrike Beyer, Chris Reed. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 30 October 2024
- Published by Elsevier in Data in Brief
- Vol. 57, 111087
NLAS-multi: A multilingual corpus of automatically generated Natural Language Argumentation Schemes
- 30 October 2024
- Published by Elsevier in Data in Brief
- Vol. 57, 111087
Open AccessNLAS-multi: A multilingual corpus of automatically generated Natural Language Argumentation Schemes
- Open Access
- 27 August 2024
- Published by IOS Press
- p. 253-264
Annotating and Mining Hypotheses in Argumentation
Generating and evaluating hypotheses about past, present, and future events is core to argumentation in many domains, such as forensic investigations, medical diagnostics, and scientific research. In this paper, we explore the role of hypothesis-making in argumentative dialogue. To do so, we introduce an annotated dataset of 502 hypotheses in the existing RIP corpus of collaborative problem-solving in murder mystery games, creating the RIP1 corpus. Propositions marked as hypotheses in RIP1 correlate systematically with argument structure (previously annotated according to Inference Anchoring Theory). We explore the interaction between arguments and hypotheses, showing hypotheses are often conclusions of arguments and differences between how hypotheses and assertions are treated in dialogue. Based on this quantitative analysis, we conduct preliminary computational experiments establishing a baseline for the automatic mining of hypotheses. Experimentation with a Support Vector Machine and a fine-tuned RoBERTa model shows initial performance on text span classification with an F1 score of 80.0, outperforming random and majority baselines, and providing a target for future improvement.
- 27 August 2024
- Published by IOS Press
- p. 253-264
Open AccessAnnotating and Mining Hypotheses in Argumentation
Generating and evaluating hypotheses about past, present, and future events is core to argumentation in many domains, such as forensic investigations, medical diagnostics, and scientific research. In this paper, we explore the role of hypothesis-making in argumentative dialogue. To do so, we introduce an annotated dataset of 502 hypotheses in the existing RIP corpus of collaborative problem-solving in murder mystery games, creating the RIP1 corpus. Propositions marked as hypotheses in RIP1 correlate systematically with argument structure (previously annotated according to Inference Anchoring Theory). We explore the interaction between arguments and hypotheses, showing hypotheses are often conclusions of arguments and differences between how hypotheses and assertions are treated in dialogue. Based on this quantitative analysis, we conduct preliminary computational experiments establishing a baseline for the automatic mining of hypotheses. Experimentation with a Support Vector Machine and a fine-tuned RoBERTa model shows initial performance on text span classification with an F1 score of 80.0, outperforming random and majority baselines, and providing a target for future improvement.
- Open Access
- 27 August 2024
- Published by IOS Press
- p. 61-72
An Argumentation Scheme-Based Framework for Automatic Reconstruction of Natural Language Enthymemes
An important open challenge in the area of computational argumentation is the automatic reconstruction of natural language enthymemes. Such argumentative figures are commonly used in natural language human discourse to improve the naturalness and efficiency of speech. They also represent a major challenge when developing computational argumentation systems that need to work with natural language data, since enthymemes bring irregularity to the representations proposed in classical models of argumentation. In this paper, we propose a new framework based on the theory of argumentation schemes aimed at automatically reconstructing natural language enthymemes. The proposed framework consists of a two-module pipeline: (i) scheme classification, and (ii) enthymeme reconstruction. We validate the proposed framework by comparing its performance to a baseline pipeline that does not take the argumentation scheme theory into account. We evaluate the framework by analysing the validity of the complete reconstructed arguments, establishing a new set of baselines that can be used as reference for future work in this direction.
- 27 August 2024
- Published by IOS Press
- p. 61-72
Open AccessAn Argumentation Scheme-Based Framework for Automatic Reconstruction of Natural Language Enthymemes
An important open challenge in the area of computational argumentation is the automatic reconstruction of natural language enthymemes. Such argumentative figures are commonly used in natural language human discourse to improve the naturalness and efficiency of speech. They also represent a major challenge when developing computational argumentation systems that need to work with natural language data, since enthymemes bring irregularity to the representations proposed in classical models of argumentation. In this paper, we propose a new framework based on the theory of argumentation schemes aimed at automatically reconstructing natural language enthymemes. The proposed framework consists of a two-module pipeline: (i) scheme classification, and (ii) enthymeme reconstruction. We validate the proposed framework by comparing its performance to a baseline pipeline that does not take the argumentation scheme theory into account. We evaluate the framework by analysing the validity of the complete reconstructed arguments, establishing a new set of baselines that can be used as reference for future work in this direction.
- Open Access
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.
Open AccessNLAS-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.
- Open Access
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.
Open AccessVivesDebate-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.