2 citations · 4 across the 13 of their papers we have counts for
14 papers
Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations
Antonin Poché, Fanny Jourdan, Nils Feldhus +6
Simulatability is an evaluation protocol for explanations that quantifies their usefulness by how well they help a user predict a task model's outputs. Since human evaluation is co…
Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge
Nils Feldhus, Tanja Baeumel, Elena Golimblevskaia +10
LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when its output format changes (e.g.,…
Gendered Prompting and LLM Code Review: How Gender Cues in the Prompt Shape Code Quality and Evaluation
Lynn Janzen, Üveys Eroglu, Dorothea Kolossa +4
LLMs are increasingly embedded in programming workflows, from code generation to automated code review. Yet, how gendered communication styles interact with LLM-assisted programmin…
Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
Qianli Wang, Nils Feldhus, Pepa Atanasova +4
Quantization is widely used to accelerate inference and streamline the deployment of large language models (LLMs), yet its effects on self-explanations (SEs) remain unexplored. SEs…
Parallel Universes, Parallel Languages: A Comprehensive Study on LLM-based Multilingual Counterfactual Example Generation
Qianli Wang, Van Bach Nguyen, Yihong Liu +6
Counterfactuals refer to minimally edited inputs that cause a model's prediction to change, serving as a promising approach to explaining the model's behavior. Large language model…
Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems
Qianli Wang, Tatiana Anikina, Nils Feldhus +6
Conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) have garnered considerable attention for their ability to enhance user co…
Truth or Twist? Optimal Model Selection for Reliable Label Flipping Evaluation in LLM-based Counterfactuals
Qianli Wang, Van Bach Nguyen, Nils Feldhus +4
Counterfactual examples are widely employed to enhance the performance and robustness of large language models (LLMs) through counterfactual data augmentation (CDA). However, the s…
Through a Compressed Lens: Investigating The Impact of Quantization on Factual Knowledge Recall
Qianli Wang, Mingyang Wang, Nils Feldhus +5
Quantization methods are widely used to accelerate inference and streamline the deployment of large language models (LLMs). Although quantization's effects on various LLM capabilit…
Towards Automated Fact-Checking of Real-World Claims: Exploring Task Formulation and Assessment with LLMs
Premtim Sahitaj, Iffat Maab, Junichi Yamagishi +3
Fact-checking is necessary to address the increasing volume of misinformation. Traditional fact-checking relies on manual analysis to verify claims, but it is slow and resource-int…
FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
Qianli Wang, Nils Feldhus, Simon Ostermann +3
Counterfactual examples are widely used in natural language processing (NLP) as valuable data to improve models, and in explainable artificial intelligence (XAI) to understand mode…
Anchored Alignment for Self-Explanations Enhancement
Luis Felipe Villa-Arenas, Ata Nizamoglu, Qianli Wang +2
In this work, we introduce a methodology for alignment designed to enhance the ability of large language models (LLMs) to articulate their reasoning (self-explanation) even in the…
Cross-Refine: Improving Natural Language Explanation Generation by Learning in Tandem
Qianli Wang, Tatiana Anikina, Nils Feldhus +3
Natural language explanations (NLEs) are vital for elucidating the reasoning behind large language model (LLM) decisions. Many techniques have been developed to generate NLEs using…
Protect and Extend -- Using GANs for Synthetic Data Generation of Time-Series Medical Records
Navid Ashrafi, Vera Schmitt, Robert P. Spang +2
Preservation of private user data is of paramount importance for high Quality of Experience (QoE) and acceptability, particularly with services treating sensitive data, such as IT-…
A Feature Extraction based Model for Hate Speech Identification
Salar Mohtaj, Vera Schmitt, Sebastian Möller
The detection of hate speech online has become an important task, as offensive language such as hurtful, obscene and insulting content can harm marginalized people or groups. This…