Publications

2025

1. 

   Precise In-Parameter Concept Erasure in Large Language Models

   Yoav Gur-Arieh, Clara Suslik, Yihuai Hong, Fazl Barez, and Mor Geva

   2025

   Abs Bib PDF Code

   Large language models (LLMs) often acquire knowledge during pretraining that is undesirable in downstream deployments, e.g., sensitive information or copyrighted content. Existing approaches for removing such knowledge rely on fine-tuning, training low-rank adapters or fact-level editing, but these are either too coarse, too shallow, or ineffective. In this work, we propose PISCES (Precise In-parameter Suppression for Concept EraSure), a novel framework for precisely erasing entire concepts from model parameters by directly editing directions that encode them in parameter space. PISCES uses a disentangler model to decompose MLP vectors into interpretable features, identifies those associated with a target concept using automated interpretability techniques, and removes them from model parameters. Experiments on Gemma 2 and Llama 3.1 over various concepts show that PISCES achieves modest gains in efficacy over leading erasure methods, reducing accuracy on the target concept to as low as 7.7%, while dramatically improving erasure specificity (by up to 31%) and robustness (by up to 38%). Overall, these results demonstrate that feature-based in-parameter editing enables a more precise and reliable approach for removing conceptual knowledge in language models.

   @misc{gurarieh2025preciseinparameterconcepterasure,
     title = {Precise In-Parameter Concept Erasure in Large Language Models},
     author = {Gur-Arieh, Yoav and Suslik, Clara and Hong, Yihuai and Barez, Fazl and Geva, Mor},
     year = {2025},
     eprint = {2505.22586},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
     url = {https://arxiv.org/abs/2505.22586},
   }

2. ACL

   

   Enhancing Automated Interpretability with Output-Centric Feature Descriptions

   Yoav Gur-Arieh, Roy Mayan, Chen Agassy, Atticus Geiger, and Mor Geva

   In The 63rd Annual Meeting of the Association for Computational Linguistics, 2025

   Abs Bib HTML PDF Code

   Automated interpretability pipelines generate natural language descriptions for the concepts represented by features in large language models (LLMs), such as plants or the first word in a sentence. These descriptions are derived using inputs that activate the feature, which may be a dimension or a direction in the model’s representation space. However, identifying activating inputs is costly, and the mechanistic role of a feature in model behavior is determined both by how inputs cause a feature to activate and by how feature activation affects outputs. Using steering evaluations, we reveal that current pipelines provide descriptions that fail to capture the causal effect of the feature on outputs. To fix this, we propose efficient, output-centric methods for automatically generating feature descriptions. These methods use the tokens weighted higher after feature stimulation or the highest weight tokens after applying the vocabulary "unembedding" head directly to the feature. Our output-centric descriptions better capture the causal effect of a feature on model outputs than input-centric descriptions, but combining the two leads to the best performance on both input and output evaluations. Lastly, we show that output-centric descriptions can be used to find inputs that activate features previously thought to be "dead".

   @inproceedings{gurarieh2025enhancing,
     title = {Enhancing Automated Interpretability with Output-Centric Feature Descriptions},
     author = {Gur-Arieh, Yoav and Mayan, Roy and Agassy, Chen and Geiger, Atticus and Geva, Mor},
     year = {2025},
     booktitle = {The 63rd Annual Meeting of the Association for Computational Linguistics},
     url = {https://arxiv.org/abs/2501.08319},
   }