Papers by Andreas Waldis
ScamSpot: Fighting Financial Fraud in Instagram Comments (2024.eacl-demo)
Copied to clipboard
| Challenge: | Existing research on spam and scams on Instagram is limited to theoretical concepts and only a recall of 11.51%. |
| Approach: | They propose a system that includes a browser extension, a fine-tuned BERT model and a REST API to solve the problem of spam and fraudulent messages in the comment sections of Instagram pages. |
| Outcome: | The proposed system includes a browser extension, a fine-tuned BERT model and a REST API. |
The Lou Dataset - Exploring the Impact of Gender-Fair Language in German Text Classification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Gender-fair language fosters inclusion by addressing all genders or using neutral forms. |
| Approach: | They present a dataset that provides high-quality reformulations for German text classification . they find substantial label flips, reduced prediction certainty, and altered attention patterns . |
| Outcome: | The proposed dataset provides high-quality reformulations for German text classification . it finds label flips, reduced prediction certainty, and significantly altered attention patterns . |
Diversity Over Size: On the Effect of Sample and Topic Sizes for Topic-Dependent Argument Mining Datasets (2024.emnlp-main)
Copied to clipboard
| Challenge: | Topic-dependent argument mining is a task that requires expert knowledge to recognize retrieved arguments. |
| Approach: | They investigate the effect of TDAM dataset composition on model performance by using carefully composed training samples and reducing the training sample size by almost 90%. |
| Outcome: | The proposed model can achieve 95% of the maximum performance on three different datasets. |
Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization (2024.findings-eacl)
Copied to clipboard
| Challenge: | Pre-trained language models perform well in In-Topic setups, but face challenges in Cross-Topical setups where testing data is derived from distinct topics. |
| Approach: | They propose a probing-based approach to analyze pre-trained language models in a Cross-Topic setup to better understand the reasons behind generalization gaps. |
| Outcome: | The proposed approach improves on pre-trained language models in In-Topic setups and Cross-Topical scenarios. |
Aligned Probing: Relating Toxic Behavior and Model Internals (2026.tacl-1)
Copied to clipboard
| Challenge: | Language models (LMs) may produce toxic text that contains hate speech, insults, or vulgarity, even when prompted with innocuous text. |
| Approach: | They propose an interpretability framework that aligns the behavior of language models based on their outputs and internal representations. |
| Outcome: | The proposed framework bridges behavioral and internal perspectives for toxicity for the first time. |
Composing Structure-Aware Batches for Pairwise Sentence Classification (2022.findings-acl)
Copied to clipboard
| Challenge: | Identifying the relation between two sentences requires datasets with pairwise annotations. |
| Approach: | They propose three batch composition strategies to incorporate such information and measure their performance over 14 heterogeneous pairwise sentence classification tasks. |
| Outcome: | The proposed methods show that the pre-trained language model can benefit from having such structural information in a low-resource setting. |
Robust Integration of Contextual Information for Cross-Target Stance Detection (2023.starsem-1)
Copied to clipboard
| Challenge: | Existing stance detection models do not take into account relevant contextual information which allows for inferring the stance correctly. |
| Approach: | They propose an approach to integrate contextual information as text into pretrained language models by prompting large language models. |
| Outcome: | The proposed approach outperforms baselines on a large and diverse stance detection benchmark in a cross-target setup, i.e. for targets unseen during training. |