Information retrieval axioms are formalized constraints that retrieval systems should ideally satisfy (e.g., to rank documents higher that contain the query terms more often). In this paper, we propose new axioms that focus on the scenario of argument retrieval: retrieval for queries that need arguments in the results. Our underlying axiomatic idea is that in such scenarios, documents should be prioritized with argumentative units that are similar to the query. We test our new axioms in re-ranking experiments on the data of the Touché ~2020 and~2021 shared task on argument retrieval for controversial questions, and show that the new axioms can improve the effectiveness of Touché's strong DirichletLM baseline model and even of the top-performing system from Touché ~2021, a system already specifically optimized for argument retrieval. Finally, we also propose a new method for visualizing the relationships between axioms based on their effects in re-ranking settings.

While human values play a crucial role in making arguments persuasive, we currently lack the necessary extensive datasets to develop methods for analyzing the values underlying these arguments on a large scale. To address this gap, we present the Touché23-ValueEval dataset, an expansion of the Webis-ArgValues-22 dataset. We collected and annotated an additional 4780 new arguments, doubling the dataset’s size to 9324 arguments. These arguments were sourced from six diverse sources, covering religious texts, community discussions, free-text arguments, newspaper editorials, and political debates. Each argument is annotated by three crowdworkers for 54 human values, following the methodology established in the original dataset. The Touché23-ValueEval dataset was utilized in the SemEval 2023 Task 4. ValueEval: Identification of Human Values behind Arguments, where an ensemble of transformer models demonstrated state-of-the-art performance. Furthermore, our experiments show that a fine-tuned large language model, Llama-2-7B, achieves comparable results.

Abstract dialectical frameworks (ADFs) are one of the most powerful generalizations of classical Dung-style argumentation frameworks (AFs). The additional expressive power comes with an increase in computational complexity, namely one level up in the polynomial hierarchy in comparison to their AF counterparts. However, there is one important subclass, so-called bipolar ADFs (BADFs) which are as complex as classical AFs while offering strictly more modeling capacities. This property makes BADFs very attractive from a knowledge representation point of view and is the main reason why this class has received much attention recently. The semantics of ADFs rely on the Gamma-operator which takes as an input a three-valued interpretation and returns a new one. However, in order to obtain the output the original definition requires to consider any two-valued completion of a given three-valued interpretation. In this paper we formally prove that in case of BADFs we may bypass the computationally intensive procedure via applying Kleene's three-valued logic K. We therefore introduce the so-called bipolar disjunctive normal form which is simply a disjunctive normal form where any used atom possesses either a positive or a negative polarity. We then show that: First, this normal form is expressive enough to represent any BADF and secondly, the computation can be done via Kleene's K instead of dealing with two-valued completions. Inspired by the main correspondence result we present some first experiments showing the computational benefit of using Kleene.

We approach aspect-based argument mining as a supervised machine learning task to classify arguments into semantically coherent groups referring to the same defined aspect categories. As an exemplary use case, we introduce the Argument Aspect Corpus - Nuclear Energy that separates arguments about the topic of nuclear energy into nine major aspects. Since the collection of training data for further aspects and topics is costly, we investigate the potential for current transformer-based few-shot learning approaches to accurately classify argument aspects. The best approach is applied to a British newspaper corpus covering the debate on nuclear energy over the past 21 years. Our evaluation shows that a stable prediction of shares of argument aspects in this debate is feasible with 50 to 100 training samples per aspect. Moreover, we see signals for a clear shift in the public discourse in favor of nuclear energy in recent years. This revelation of changing patterns of pro and contra arguments related to certain aspects over time demonstrates the potential of supervised argument aspect detection for tracking issue-specific media discourses.