565 citations · 734 across the 71 of their papers we have counts for
81 papers
LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs
Guy Bar-Shalom, Mor Geva, Fabrizio Frasca +1
Large language models exhibit misbehaviors that hinder deployment in high-stakes settings. One approach to monitor such failures is to use an external LLM as a monitor, but this is…
Pretraining Latent Information Feedback Transformers with Teacher Supervision
Dor Tirosh, Ido Amos, Mor Geva
Transformer language models (LMs) are feed-forward: deep-layer representations are never fed back to shallower layers, and the only pathway for information to flow downward across…
The Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization
Benoit Dherin, Michael Munn, Xavier Gonzalvo +14
Context tokens in a transformer-based language model can be absorbed into the model's weights as a multiplicative operator. We study this operator in the setting of safety instruct…
Capacity, Responsiveness and Alignment: What Makes a Latent Structure Actionable
Or Shafran, Mor Geva
Localizing latent structures in the activation space of language models (LMs) is central to understanding and controlling their behavior. Yet, localized structures can differ subst…
LMs as Task-Specific Knowledge Bases: An Interpretability Analysis
Amit Elhelo, Amir Globerson, Mor Geva
Language models (LMs) capture large amounts of factual knowledge applicable to a wide range of tasks, motivating the view of their parameters as a knowledge base. An important prop…
Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings
Clara Haya Suslik, Or Shafran, Mor Geva
As language models are increasingly deployed in real-world applications, the ability to erase specific knowledge from them becomes critical for safety and compliance. Prominent met…