activity
20242026
collaborators

6 papers

cs.LG2026

TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors

Ido Andrew Atad, Itamar Zimerman, Shahar Katz +1

Attention matrices are fundamental to transformer research, supporting a broad range of applications including interpretability, visualization, manipulation, and distillation. Yet,…

cs.LG2025

AlignTree: Efficient Defense Against LLM Jailbreak Attacks

Gil Goren, Shahar Katz, Lior Wolf

Large Language Models (LLMs) are vulnerable to adversarial attacks that bypass safety guidelines and generate harmful content. Mitigating these vulnerabilities requires defense mec…

cs.LG2025

Execution Guided Line-by-Line Code Generation

Boaz Lavon, Shahar Katz, Lior Wolf

We present a novel approach to neural code generation that incorporates real-time execution signals into the language model generation process. While large language models (LLMs) h…

cs.CL2025

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models

Ameen Ali, Shahar Katz, Lior Wolf +1

Large language models (LLMs) often develop learned mechanisms specialized to specific datasets, such as reliance on domain-specific correlations, which yield high-confidence predic…

cs.CL2024

Segment-Based Attention Masking for GPTs

Shahar Katz, Liran Ringel, Yaniv Romano +1

Modern Language Models (LMs) owe much of their success to masked causal attention, the backbone of Generative Pre-Trained Transformer (GPT) models. Although GPTs can process the en…

cs.CL2024

Reversed Attention: On The Gradient Descent Of Attention Layers In GPT

Shahar Katz, Lior Wolf

The success of Transformer-based Language Models (LMs) stems from their attention mechanism. While this mechanism has been extensively studied in explainability research, particula…