Papers by Thomas Huber
TruthSplit: Revealing Conditional Validity in Arguments Through Multi-Worldview Comparative Reasoning (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing argumentation tools analyze properties of the argument, but leave perspective-specific background knowledge implicit. |
| Approach: | They propose a system that analyzes arguments from multiple perspectives using a perspective-dependent analysis approach. |
| Outcome: | The proposed system analyzes arguments from multiple perspectives and generates interpretations, value conflicts and assumption gaps. |
LLMs meet Bloom’s Taxonomy: A Cognitive View on Large Language Model Evaluations (2025.coling-main)
Copied to clipboard
| Challenge: | Existing evaluation approaches for Large Language Models lack a structured approach that reflects the underlying cognitive abilities required for solving the tasks. |
| Approach: | They propose a hierarchical approach to evaluation of Large Language Models that leverages Bloom’s Taxonomy to identify how well they cover the levels of Bloom’ s taxonomies. |
| Outcome: | The proposed evaluation frameworks cover the Bloom’s Taxonomy, a hierarchical framework for categorizing cognitive skills, on the most widely used benchmarks. |
Let’s discuss! Quality Dimensions and Annotated Datasets for Computational Argument Quality Assessment (2024.emnlp-main)
Copied to clipboard
| Challenge: | Argumentation is a key competence and an important cultural technique in democratic societies. |
| Approach: | They propose to create domain-specific datasets and methods to assess argument quality. |
| Outcome: | The proposed methods address gaps in the literature and aid future research in the domain. |
CLEAR: A Comprehensive Linguistic Evaluation of Argument Rewriting by Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Argument Improvement (ArgImp) is a text rewriting task that requires LLMs to shorten texts while increasing word length and merging sentences. |
| Approach: | They propose to use a pipeline to evaluate LLMs' behavior in a text rewriting setting . they use four linguistic levels to examine the qualities of argumentative texts . |
| Outcome: | The proposed evaluation pipeline compares LLMs on argumentative texts and their improvement on a broad set of argumentation corpora. |