5 papers
Output Vector Editing for Memorization Mitigation in Large Language Models
Ahmad Dawar Hakimi, Kaiwei Lei, Isabelle Augenstein +1
Large language models memorize and reproduce sequences from their training data, creating privacy, copyright, and security risks. Existing neuron-level mitigation methods equate ed…
Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learning for Hostility Detection
Ahmad Dawar Hakimi, Lea Hirlimann, Isabelle Augenstein +1
Instruction-tuned LLMs can annotate thousands of instances at low cost. This raises two questions for active learning (AL): can LLM labels replace human labels within the AL loop,…
BlackboxNLP-2025 MIB Shared Task: Exploring Ensemble Strategies for Circuit Localization Methods
Philipp Mondorf, Mingyang Wang, Sebastian Gerstner +6
The Circuit Localization track of the Mechanistic Interpretability Benchmark (MIB) evaluates methods for localizing circuits within large language models (LLMs), i.e., subnetworks…
On Relation-Specific Neurons in Large Language Models
Yihong Liu, Runsheng Chen, Lea Hirlimann +6
In large language models (LLMs), certain \emph{neurons} can store distinct pieces of knowledge learned during pretraining. While factual knowledge typically appears as a combinatio…
Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models
Ahmad Dawar Hakimi, Ali Modarressi, Philipp Wicke +1
Understanding how large language models (LLMs) acquire and store factual knowledge is crucial for enhancing their interpretability and reliability. In this work, we analyze the evo…