Papers by Maja Stahl
A School Student Essay Corpus for Analyzing Interactions of Argumentative Structure and Quality (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing arguments mining corpus with ground-truth quality annotations is lacking . authors propose baseline approaches to argument mining and essay scoring . |
| Approach: | They propose to use argumentative structure to support argumentative writing . they use an annotated german corpus to analyze interactions between the two tasks . |
| Outcome: | The proposed methods can be used to support argumentative writing . they analyze interactions between argumentative structure and quality annotations . |
Reference-guided Style-Consistent Content Transfer (2024.lrec-main)
Copied to clipboard
| Challenge: | Text style transfer involves changing the style of a text while preserving its original style. |
| Approach: | They propose a task of style-consistent content transfer which involves modifying a text’s content based on a provided reference statement while preserving its original style. |
| Outcome: | The proposed approach meets three important conditions: reference faithfulness, style adherence, and coherence. |
Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Comparing human-like edits to LLMs, we observe a mismatch in editing strategies. |
| Approach: | They propose a reinforcement learning approach that teaches LLMs human-like editing to improve the appropriateness of arguments. |
| Outcome: | The proposed approach outperforms baselines and the state of the art in human-like editing, with multi-round editing achieving appropriateness close to full rewriting. |
ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been trained to follow instructions for many NLP tasks, including several tasks from computational argumentation (CA), the computational analysis and synthesis of natural language arguments. |
| Approach: | They propose a specialized instruction fine-tuning for the domain of computational argumentation (CA) they synthesized 52k CA-related instructions and used them to train a CA-specialized instruction-following LLM. |
| Outcome: | The proposed benchmarks show that the LLMs can tackle unseen and seen tasks while maintaining generalization capabilities. |
Mind the Gap: Automated Corpus Creation for Enthymeme Detection and Reconstruction in Learner Arguments (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Argumentative writing is an essential skill that can be challenging to acquire. |
| Approach: | They propose two new tasks to identify gaps in arguments and fill such gaps by deleting ADUs from argumentative text. |
| Outcome: | The proposed methods reduce argument quality and produce arguments that are natural to those written by learners. |