Shahar Katz
Publication record assembled from the DBLP archive of ranked conferences.
Papers indexed
7
Venues
5
Active years
2023–2026
Best venue rank
A*
Where they publish
Papers
7 indexed papers, newest first.
| Year | Venue | Title | Authors |
|---|---|---|---|
| 2026 | AAAI | AlignTree: Efficient Defense Against LLM Jailbreak Attacks. | Gil Goren, Shahar Katz, Lior Wolf |
| 2026 | ACL | TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors. | Ido Andrew Atad, Itamar Zimerman, Shahar Katz, Lior Wolf |
| 2026 | EACL | Safeguarding Language Models via Self-Destruct Trapdoor. | Shahar Katz, Bar Alon, Ariel Shaulov, Lior Wolf, Mahmood Sharif |
| 2025 | ACL | Segment-Based Attention Masking for GPTs. | Shahar Katz, Liran Ringel, Yaniv Romano, Lior Wolf |
| 2025 | NAACL | Reversed Attention: On The Gradient Descent Of Attention Layers In GPT. | Shahar Katz, Lior Wolf |
| 2024 | EMNLP | Backward Lens: Projecting Language Model Gradients into the Vocabulary Space. | Shahar Katz, Yonatan Belinkov, Mor Geva, Lior Wolf |
| 2023 | EMNLP | VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers. | Shahar Katz, Yonatan Belinkov |