activity
20242026
collaborators

8 papers

cs.CL2026

From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks

Ayan Datta, Mounika Marreddy, Alexander Mehler +2

Large language models (LLMs) exhibit failures on elementary symbolic tasks such as character counting in a word, despite excelling on complex benchmarks. Although this limitation h…

cs.CL2026

Explanation Generation for Contradiction Reconciliation with LLMs

Jason Chan, Zhixue Zhao, Robert Gaizauskas

Existing NLP work commonly treats contradictions as errors to be resolved by choosing which statements to accept or discard. Yet a key aspect of human reasoning in social interacti…

cs.CL2025

Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation

Yinjie Cheng, Paul Youssef, Christin Seifert +2

Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting L…

cs.CL2025

Tracing and Reversing Edits in LLMs

Paul Youssef, Zhixue Zhao, Christin Seifert +1

Knowledge editing methods (KEs) are a cost-effective way to update the factual content of large language models (LLMs), but they pose a dual-use risk. While KEs are beneficial for…

cs.CL2025

Position: Editing Large Language Models Poses Serious Safety Risks

Paul Youssef, Zhixue Zhao, Daniel Braun +2

Large Language Models (LLMs) contain large amounts of facts about the world. These facts can become outdated over time, which has led to the development of knowledge editing method…

cs.CL2024

How to Make LLMs Forget: On Reversing In-Context Knowledge Edits

Paul Youssef, Zhixue Zhao, Jörg Schlötterer +1

In-context knowledge editing (IKE) enables efficient modification of large language model (LLM) outputs without parameter changes and at zero-cost. However, it can be misused to ma…