AIConfPaper
← Search

Henning Wachsmuth

26 accepted papers

2025

Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection

Maximilian Spliethöver, Tim Knebler, Fabian Fumagalli, Maximilian Muschalik, Barbara Hammer, Eyke Hüllermeier +1
NAACL 2025long

Recent advances on instruction fine-tuning have led to the development of various prompting techniques for large language models, such as explicit reasoning steps. However, the success of techniques depends on various parameters, such as the task, language model, and context provided. Finding an eff…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2025

ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation

Maja Stahl, Timon Ziegenbein, Joonsuk Park, Henning Wachsmuth
ACL 2025finding

Training large language models (LLMs) to follow instructions has significantly enhanced their ability to tackle unseen tasks. However, despite their strong generalization capabilities, instruction-following LLMs encounter difficulties when dealing with tasks that require domain knowledge. This work…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Towards a Perspectivist Turn in Argument Quality Assessment

Julia Romberg, Maximilian Maurer, Henning Wachsmuth, Gabriella Lapesa
NAACL 2025long

The assessment of argument quality depends on well-established logical, rhetorical, and dialectical properties that are unavoidably subjective: multiple valid assessments may exist, there is no unequivocal ground truth. This aligns with recent paths in machine learning, which embrace the co-existenc…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

A School Student Essay Corpus for Analyzing Interactions of Argumentative Structure and Quality

Maja Stahl, Nadine Michel, Sebastian Kilsbach, Julian Schmidtke, Sara Rezat, Henning Wachsmuth
NAACL 2024long

Learning argumentative writing is challenging. Besides writing fundamentals such as syntax and grammar, learners must select and arrange argument components meaningfully to create high-quality essays. To support argumentative writing computationally, one step is to mine the argumentative structure.…

Cited by 3Source ↗PDF ↗code ↗Scholar ↗
2024

Analyzing the Use of Metaphors in News Editorials for Political Framing

Meghdut Sengupta, Roxanne El Baff, Milad Alshomary, Henning Wachsmuth
NAACL 2024long

Metaphorical language is a pivotal element inthe realm of political framing. Existing workfrom linguistics and the social sciences providescompelling evidence regarding the distinctivenessof conceptual framing for politicalideology perspectives. However, the nature andutilization of metaphors and th…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Argument Quality Assessment in the Age of Instruction-Following Large Language Models

Henning Wachsmuth, Gabriella Lapesa, Elena Cabrio, Anne Lauscher, Joonsuk Park, Eva Maria Vecchi +2
COLING 2024main

The computational treatment of arguments on controversial issues has been subject to extensive NLP research, due to its envisioned impact on opinion formation, decision making, writing education, and the like. A critical task in any such application is the assessment of an argument’s quality - but i…

Cited by 12Source ↗PDF ↗Scholar ↗
2024

Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness

Maximilian Spliethöver, Sai Nikhil Menon, Henning Wachsmuth
ACL 2024findings

Dialects introduce syntactic and lexical variations in language that occur in regional or social groups. Most NLP methods are not sensitive to such variations. This may lead to unfair behavior of the methods, conveying negative bias towards dialect speakers. While previous work has studied dialect-r…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

Improving Argument Effectiveness Across Ideologies using Instruction-tuned Large Language Models

Roxanne El Baff, Khalid Al Khatib, Milad Alshomary, Kai Konen, Benno Stein, Henning Wachsmuth
EMNLP 2024finding

Different political ideologies (e.g., liberal and conservative Americans) hold different worldviews, which leads to opposing stances on different issues (e.g., gun control) and, thereby, fostering societal polarization. Arguments are a means of bringing the perspectives of people with different ideo…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedback

Timon Ziegenbein, Gabriella Skitalinskaya, Alireza Bayat Makou, Henning Wachsmuth
ACL 2024long

Ensuring that online discussions are civil and productive is a major challenge for social media platforms. Such platforms usually rely both on users and on automated detection tools to flag inappropriate arguments of other users, which moderators then review. However, this kind of post-hoc moderatio…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2024

Modeling the Quality of Dialogical Explanations

Milad Alshomary, Felix Lange, Meisam Booshehri, Meghdut Sengupta, Philipp Cimiano, Henning Wachsmuth
COLING 2024main

Explanations are pervasive in our lives. Mostly, they occur in dialogical form where an explainer discusses a concept or phenomenon of interest with an explainee. Leaving the explainee with a clear understanding is not straightforward due to the knowledge gap between the two participants. Previous r…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2024

Reference-guided Style-Consistent Content Transfer

Wei-Fan Chen, Milad Alshomary, Maja Stahl, Khalid Al Khatib, Benno Stein, Henning Wachsmuth
COLING 2024main

In this paper, we introduce the task of style-consistent content transfer, which concerns modifying a text’s content based on a provided reference statement while preserving its original style. We approach the task by employing multi-task learning to ensure that the modified text meets three importa…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

The Touché23-ValueEval Dataset for Identifying Human Values behind Arguments

Nailia Mirzakhmedova, Johannes Kiesel, Milad Alshomary, Maximilian Heinrich, Nicolas Handke, Xiaoni Cai +8
COLING 2024main

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…

Cited by 39Source ↗PDF ↗code ↗Scholar ↗
2023

Mind the Gap: Automated Corpus Creation for Enthymeme Detection and Reconstruction in Learner Arguments

Maja Stahl, Nick Düsterhus, Mei-Hua Chen, Henning Wachsmuth
EMNLP 2023long findings

Writing strong arguments can be challenging for learners. It requires to select and arrange multiple argumentative discourse units (ADUs) in a logical and coherent way as well as to decide which ADUs to leave implicit, so called enthymemes. However, when important ADUs are missing, readers might not…

Cited by 0Source ↗code ↗Scholar ↗
2023

Modeling Appropriate Language in Argumentation

Timon Ziegenbein, Shahbaz Syed, Felix Lange, Martin Potthast, Henning Wachsmuth
ACL 2023long

Online discussion moderators must make ad-hoc decisions about whether the contributions of discussion participants are appropriate or should be removed to maintain civility. Existing research on offensive language and the resulting tools cover only one aspect among many involved in such decisions. T…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2023

Modeling Highlighting of Metaphors in Multitask Contrastive Learning Paradigms

Meghdut Sengupta, Milad Alshomary, Ingrid Scharlau, Henning Wachsmuth
EMNLP 2023long findings

Metaphorical language, such as ``spending time together'', projects meaning from a source domain (here, $\textit{money}$) to a target domain ($\textit{time}$). Thereby, it highlights certain aspects of the target domain, such as the $\textit{effort}$ behind the time investment. Highlighting aspects…

Cited by 0Source ↗Scholar ↗
2023

To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support

Gabriella Skitalinskaya, Henning Wachsmuth
ACL 2023long

Optimizing the phrasing of argumentative text is crucial in higher education and professional development. However, assessing whether and how the different claims in a text should be revised is a hard task, especially for novice writers. In this work, we explore the main challenges to identifying ar…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2022

Identifying the Human Values behind Arguments

Johannes Kiesel, Milad Alshomary, Nicolas Handke, Xiaoni Cai, Henning Wachsmuth, Benno Stein
ACL 2022long

This paper studies the (often implicit) human values behind natural language arguments, such as to have freedom of thought or to be broadminded. Values are commonly accepted answers to why some option is desirable in the ethical sense and are thus essential both in real-world argumentation and theor…

Cited by 96Source ↗PDF ↗code ↗Scholar ↗
2022

No Word Embedding Model Is Perfect: Evaluating the Representation Accuracy for Social Bias in the Media

Maximilian Spliethöver, Maximilian Keiff, Henning Wachsmuth
EMNLP 2022finding

News articles both shape and reflect public opinion across the political spectrum. Analyzing them for social bias can thus provide valuable insights, such as prevailing stereotypes in society and the media, which are often adopted by NLP models trained on respective data. Recent work has relied on w…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2022

The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments

Milad Alshomary, Roxanne El Baff, Timon Gurcke, Henning Wachsmuth
ACL 2022long

An audience’s prior beliefs and morals are strong indicators of how likely they will be affected by a given argument. Utilizing such knowledge can help focus on shared values to bring disagreeing parties towards agreement. In argumentation technology, however, this is barely exploited so far. This p…

Cited by 37Source ↗PDF ↗code ↗Scholar ↗
2022

“Mama Always Had a Way of Explaining Things So I Could Understand”: A Dialogue Corpus for Learning to Construct Explanations

Henning Wachsmuth, Milad Alshomary
COLING 2022main

As AI is more and more pervasive in everyday life, humans have an increasing demand to understand its behavior and decisions. Most research on explainable AI builds on the premise that there is one ideal explanation to be found. In fact, however, everyday explanations are co-constructed in a dialogu…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2021

Bias Silhouette Analysis: Towards Assessing the Quality of Bias Metrics for Word Embedding Models

Maximilian Spliethöver, Henning Wachsmuth
IJCAI 2021poster

Word embedding models reflect bias towards genders, ethnicities, and other social groups present in the underlying training data. Metrics such as ECT, RNSB, and WEAT quantify bias in these models based on predefined word lists representing social groups and bias-conveying concepts. How suitable thes…

Cited by 6Source ↗PDF ↗code ↗Scholar ↗
2021

Controlled Neural Sentence-Level Reframing of News Articles

Wei-Fan Chen, Khalid Al Khatib, Benno Stein, Henning Wachsmuth
EMNLP 2021finding

Framing a news article means to portray the reported event from a specific perspective, e.g., from an economic or a health perspective. Reframing means to change this perspective. Depending on the audience or the submessage, reframing can become necessary to achieve the desired effect on the readers…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2021

Employing Argumentation Knowledge Graphs for Neural Argument Generation

Khalid Al Khatib, Lukas Trautner, Henning Wachsmuth, Yufang Hou, Benno Stein
ACL 2021long

Generating high-quality arguments, while being challenging, may benefit a wide range of downstream applications, such as writing assistants and argument search engines. Motivated by the effectiveness of utilizing knowledge graphs for supporting general text generation tasks, this paper investigates…

Cited by 32Source ↗PDF ↗code ↗Scholar ↗
2021

Syntopical Graphs for Computational Argumentation Tasks

Joe Barrow, Rajiv Jain, Nedim Lipka, Franck Dernoncourt, Vlad Morariu, Varun Manjunatha +3
ACL 2021long

Approaches to computational argumentation tasks such as stance detection and aspect detection have largely focused on the text of independent claims, losing out on potentially valuable context provided by the rest of the collection. We introduce a general approach to these tasks motivated by syntopi…

Cited by 5Source ↗PDF ↗Scholar ↗