Papers by Ramon Ruiz-Dolz

8 papers
Mining Complex Patterns of Argumentative Reasoning in Natural Language Dialogue (2025.acl-long)

Copied to clipboard

Challenge: Argumentation scheme mining is the task of automatically identifying reasoning mechanisms behind argument inferences.
Approach: They propose to create a corpus of 441 arguments annotated with 24 argumentation schemes and leverage the capabilities of LLMs and Transformer-based models to validate their applicability in real-world scenarios.
Outcome: The proposed corpus of arguments is pre-trained on a large corpus containing textbook-like argumentation schemes and validates their applicability in real-world scenarios.
VivesDebate-Speech: A Corpus of Spoken Argumentation to Leverage Audio Features for Argument Mining (2023.emnlp-main)

Copied to clipboard

Challenge: a corpus of spoken argumentation is used to leverage audio features for argument mining tasks . a vast majority of arguments-based natural language processing resources only take text features into account .
Approach: They describe a corpus of spoken argumentation created to leverage audio features for argument mining tasks.
Outcome: The proposed corpus of spoken argumentation improves when integrating audio features into the argument mining pipeline.
Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for analyzing argumentative debates are insufficient to understand complex tasks.
Approach: They propose a hybrid method to automatically predict the winning stance in argumentative debates using arguments from argumentation theory and semantics.
Outcome: The proposed method is based on an unexplored new instance of the automatic analysis of natural language arguments.
A Structured Framework for Evaluating and Enhancing Interpretive Capabilities of Multimodal LLMs in Culturally Situated Tasks (2025.findings-emnlp)

Copied to clipboard

Challenge: Using a zero-shot classification model, we extracted multi-dimensional evaluative features from human expert critiques and used them to evaluate selected VLMs such as Llama, Qwen, or Gemini.
Approach: They constructed a quantitative framework for Chinese painting critique by extracting multi-dimensional evaluative features from human expert critiques using a zero-shot classification model.
Outcome: The framework was constructed by extracting features from human critiques using a zero-shot classification model.
Natural Language Reasoning in Large Language Models: Analysis and Evaluation (2025.findings-acl)

Copied to clipboard

Challenge: Argumentative reasoning presents unique challenges due to its reliance on context, implicit assumptions, and value judgments.
Approach: They propose a large-scale evaluation of LLMs' unconstrained natural language reasoning capabilities . they formalise a new strategy designed to evaluate argumentative reasoning in LLM .
Outcome: The proposed model performs better on a range of reasoning tasks than other models.
Looking at the Unseen: Effective Sampling of Non-Related Propositions for Argument Mining (2025.coling-main)

Copied to clipboard

Challenge: Argument mining is the task of automatically identifying argumentative structures in natural language documents.
Approach: They propose to use context and semantic similarity to sample non-related propositions . argument mining is the task of automatically identifying argumentative structures in natural language documents .
Outcome: The proposed sampling strategies improve the performance of argument mining tasks.
The Open Argument Mining Framework (2025.acl-demo)

Copied to clipboard

Challenge: Argument Mining (AM) has been a key area of research for many years, but it is still a challenging field.
Approach: the oAMF provides an open-source, modular platform that unifies diverse AM methods.
Outcome: the oAMF is an open-source, modular, and scalable platform that unifies diverse AM methods.
Learning Strategies for Robust Argument Mining: An Analysis of Variations in Language and Domain (2024.lrec-main)

Copied to clipboard

Challenge: Argument mining is a complex process that requires a large amount of resources and time.
Approach: They propose to analyze arguments in three different languages and domains to understand their robustness to natural language variations.
Outcome: The proposed systems are more robust to natural language variations than existing arguments mining systems.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations