TRAILS - Trustworthy and Inclusive Machines

Leonhard Hennig
August 1, 2024
Go to Project Site
Bias Evaluation Large Language Models
Leonhard Hennig
Leonhard Hennig
Senior Researcher

Posts

One paper to be presented at LREC 2026

One paper from DFKI-NLP authors has been accepted for publication at LREC 2026, the 2026 Language Resources and Evaluation Conference. The conference is will take place in Palma de Mallorca, Spain, from May 11th to May 16th, 2026. The paper presents a biomedical relation extraction dataset that has also been annotated for epistemic commitment (factuality) of the relations. On this dataset, we evaluate LLM-based methods for the joint detection of relations and epistemic commitment.

May 11, 2026 1 min read
Project

Publications

Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems
Conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) have garnered considerable …
PDF Cite Project Project
PolBiX: Detecting LLMs' Political Bias in Fact-Checking through X-phemisms
Large Language Models are increasingly used in applications requiring objective assessment, which could be compromised by political …
PDF Cite Code Project
PolBiX: Detecting LLMs' Political Bias in Fact-Checking through X-phemisms
Reverse Probing: Evaluating Knowledge Transfer via Finetuned Task Embeddings for Coreference Resolution
In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of …
PDF Cite Project
Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
Natural language explanations (NLEs) are vital for elucidating the reasoning behind large language model (LLM) decisions. Many …
PDF Cite Project
CoXQL: A Dataset for Parsing Explanation Requests in Conversational XAI Systems
Conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) have garnered significant …
PDF Cite Code Dataset Project
Enhancing Editorial Tasks: A Case Study on Rewriting Customer Help Page Contents Using Large Language Models
In this paper, we investigate the use of large language models (LLMs) to enhance the editorial process of rewriting customer help …
PDF Cite Dataset Project
German Voter Personas can Radicalize LLM Chatbots via the Echo Chamber Effect
We investigate the impact of LLMs on political discourse with a particular focus on the influence of generated personas on model …
PDF Cite Code Dataset Project DOI
DFKI-MLST at DialAM-2024 Shared Task: System Description
This paper presents the dfki-mlst submission for the DialAM shared task (Ruiz-Dolz et al., 2024) on identification of argumentative and …
PDF Cite Code Project
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 …
PDF Cite Code Project
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 …
PDF Cite Code Project