Conference-Paper

Standard vs. Modular Sampling: Best Practices for Reliable LLM Unlearning

RAG-enhanced Llms for Interactive Explainability in Clinical Decision Support Systems

Evaluating Online Moderation via LLM-powered Counterfactual Simulations

Abstract Online Social Networks (OSNs) widely adopt content moderation to mitigate the spread of abusive and toxic discourse. Nonetheless, the real effectiveness of moderation …

Enhancing Debunking Effectiveness through LLM-based Personality Adaptation

Emotion Recognition in Multimodal Social Data

Abstract Emotion recognition on social media is often approached in unimodal or single-label settings, despite the multimodal nature of online communication. This paper presents a …

Design Pattern-Based Code Refactoring with Llms

Perspectives in Play: A Multi-Perspective Approach for More Inclusive NLP Systems

Investigating Time-Scales in Deep Echo State Networks for Natural Language Processing

ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models

Embracing Diversity: A Multi-Perspective Approach with Soft Labels

Abstract In subjective tasks like stance detection, diverse human perspectives are often simplified into a single ground truth through label aggregation i.e. majority voting, …