2 citations · 5 across the 13 of their papers we have counts for
14 papers
Bayesian Fine-tuning Yields Language Models that are as Bayesian as their Beliefs Allow
Polina Tsvilodub, Andreas Waldis, Linlu Qiu +2
Language models (LMs) are increasingly used for tasks that require reasoning about hidden variables from a few observations, for which Bayesian inference is the normatively correct…
AIMO Interpretability Challenge
Michal Štefánik, Philipp Mondorf, Andreas Waldis +15
We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the models' interna…
Instructions Shape Production of Language, not Processing
Andreas Waldis, Leshem Choshen, Yufang Hou +1
Instructions trigger a production-centered mechanism in language models. Through a cognitively inspired lens that separates language processing and production, we reveal this mecha…
A Pipeline to Assess Merging Methods via Behavior and Internals
Yutaro Sigrist, Andreas Waldis
Merging methods combine the weights of multiple language models (LMs) to leverage their capacities, such as for domain adaptation. While existing studies investigate merged models…
Aligned Probing: Relating Toxic Behavior and Model Internals
Andreas Waldis, Vagrant Gautam, Anne Lauscher +2
We introduce aligned probing, a novel interpretability framework that aligns the behavior of language models (LMs), based on their outputs, and their internal representations (inte…
The Lou Dataset -- Exploring the Impact of Gender-Fair Language in German Text Classification
Andreas Waldis, Joel Birrer, Anne Lauscher +1
Gender-fair language, an evolving German linguistic variation, fosters inclusion by addressing all genders or using neutral forms. Nevertheless, there is a significant lack of reso…
Overview of PerpectiveArg2024: The First Shared Task on Perspective Argument Retrieval
Neele Falk, Andreas Waldis, Iryna Gurevych
Argument retrieval is the task of finding relevant arguments for a given query. While existing approaches rely solely on the semantic alignment of queries and arguments, this first…
Holmes: A Benchmark to Assess the Linguistic Competence of Language Models
Andreas Waldis, Yotam Perlitz, Leshem Choshen +2
We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence - their unconscious understanding of linguistic phenomena. Specifically, we use…
ScamSpot: Fighting Financial Fraud in Instagram Comments
Stefan Erben, Andreas Waldis
The long-standing problem of spam and fraudulent messages in the comment sections of Instagram pages in the financial sector claims new victims every day. Instagram's current spam…
Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalization
Andreas Waldis, Yufang Hou, Iryna Gurevych
Pre-trained language models (LMs) perform well in In-Topic setups, where training and testing data come from the same topics. However, they face challenges in Cross-Topic scenarios…
How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Study
Andreas Waldis, Yufang Hou, Iryna Gurevych
The advent of pre-trained Language Models (LMs) has markedly advanced natural language processing, but their efficacy in out-of-distribution (OOD) scenarios remains a significant c…
Contextual information integration for stance detection via cross-attention
Tilman Beck, Andreas Waldis, Iryna Gurevych
Stance detection deals with identifying an author's stance towards a target. Most existing stance detection models are limited because they do not consider relevant contextual info…
Diversity Over Size: On the Effect of Sample and Topic Sizes for Topic-Dependent Argument Mining Datasets
Benjamin Schiller, Johannes Daxenberger, Andreas Waldis +1
The task of Argument Mining, that is extracting and classifying argument components for a specific topic from large document sources, is an inherently difficult task for machine le…
Nested and Balanced Entity Recognition using Multi-Task Learning
Andreas Waldis, Luca Mazzola
Entity Recognition (ER) within a text is a fundamental exercise in Natural Language Processing, enabling further depending tasks such as Knowledge Extraction, Text Summarisation, o…