activity
20182026
most citedPerspectives on Large Language Models for Relevance Judgment

170 citations · 252 across the 33 of their papers we have counts for

collaborators
Showing cs.CLShow all

35 papers · 1 filter

cs.CL2026

Generating Constructive Feedback on Stories via Reinforcement Learning

Maja Stahl, Timon Ziegenbein, Henning Wachsmuth

Constructive feedback is crucial for creative writers to refine their storytelling abilities. Since receiving feedback from human experts is often costly and time-intensive, large…

cs.CL2026

Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation

Leandra Fichtel, Janek Prange, Henning Wachsmuth

To effectively enable people to understand new topics, explanations should be tailored to their backgrounds and abilities. Prompting alone has been shown to be insufficient for cre…

cs.CL2026

ArgBench: Benchmarking LLMs on Computational Argumentation Tasks

Yamen Ajjour, Carlotta Quensel, Nedim Lipka +1

Argumentation skills are an essential toolkit for large language models (LLMs). These skills are crucial in various use cases, including self-reflection, debating collaboratively f…

cs.CL2026

Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning

Timon Ziegenbein, Maja Stahl, Henning Wachsmuth

Editing human-written text has become a standard use case of large language models (LLMs), for example, to make one's arguments more appropriate for a discussion. Comparing human t…

cs.CL2025★ 2 cited

Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design

Elena Musi, Nadin Kokciyan, Khalid Al-Khatib +10

In this position paper, we advocate for the development of conversational technology that is inherently designed to support and facilitate argumentative processes. We argue that, a…

cs.CL2025

ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation

Maja Stahl, Timon Ziegenbein, Joonsuk Park +1

Training large language models (LLMs) to follow instructions has significantly enhanced their ability to tackle unseen tasks. However, despite their strong generalization capabilit…