1

Democratizing Advanced Attribution Analyses of Generative Language Models with the Inseq Toolkit

Inseq 1 is a recent toolkit providing an intuitive and optimized interface to conduct feature attribution analyses of generative language models. In this work, we present the latest improvements to the library, including efforts to simplify the …

Evaluating the Robustness of Adverse Drug Event Classification Models Using Templates

An adverse drug effect (ADE) is any harmful event resulting from medical drug treatment. Despite their importance, ADEs are often under-reported in official channels. Some research has therefore turned to detecting discussions of ADEs in social …

Symmetric Dot-Product Attention for Efficient Training of BERT Language Models

Initially introduced as a machine translation model, the Transformer architecture has now become the foundation for modern deep learning architecture, with applications in a wide range of fields, from computer vision to natural language processing. …

Towards ML-supported Triage Prediction in Real-World Emergency Room Scenarios

XAI for Better Exploitation of Text in Medical Decision Support

QoEXplainer: Mediating Explainable Quality of Experience Models with Large Language Models

In this paper, we present QoEXplainer, a QoE dashboard for supporting humans in understanding the internals of an explainable, data-driven Quality of Experience model. This tool leverages Large Language Models and the concept of Mediators to convey …

DFKI-NLP at SemEval-2024 Task 2: Towards Robust LLMs Using Data Perturbations and MinMax Training

The NLI4CT task at SemEval-2024 emphasizes the development of robust models for Natural Language Inference on Clinical Trial Reports (CTRs) using large language models (LLMs). This edition introduces interventions specifically targeting the …

The Role of Explainability in Collaborative Human-AI Disinformation Detection

Manual verification has become very challenging based on the increasing volume of information shared online and the role of generative Artificial Intelligence (AI). Thus, AI systems are used to identify disinformation and deep fakes online. Previous …

LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations

Interpretability tools that offer explanations in the form of a dialogue have demonstrated their efficacy in enhancing users' understanding (Slack et al., 2023; Shen et al., 2023), as one-off explanations may fall short in providing sufficient …

Retrieval-Augmented Knowledge Integration into Language Models: A Survey