9 papers
Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs
Nagham Omar, Mahmoud Jabarin, Maya Rozenshtein +3
Generalization in large language models (LLMs) is the ability to produce consistent and semantically stable outputs when the same input is expressed in different ways. Existing wor…
AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion
Gal Wertheizer, Rom Himelstein, Tomer Peretz +1
Adversarial attacks optimized on a single open-weight LLM can transfer to and jailbreak architecturally different models, allowing an attacker with white-box access to one model to…
Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing
Dvir Alsheich, Adar Peleg, Ben Hagag +3
The rapid integration of Large Language Models (LLMs) has driven the evolution of Multi-Agent Systems (MAS), where specialized agents collaborate to execute complex workflows. Effe…
Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models
Eliron Rahimi, Elad Hirshel, Rom Himelstein +3
Diffusion language models (DLMs) have recently emerged as a competitive alternative to autoregressive (AR) models, offering parallel decoding, competitive generation quality, and i…
You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations
Amit LeVi, Raz Lapid, Rom Himelstein +3
Many LLM applications require only narrow capabilities, yet standard post-training quantization (PTQ) methods allocate precision without considering the target task. This can waste…
Silenced Biases: The Dark Side LLMs Learned to Refuse
Rom Himelstein, Amit LeVi, Brit Youngmann +2
Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause sign…
Silent Tokens, Loud Effects: Padding in LLMs
Rom Himelstein, Amit LeVi, Yonatan Belinkov +1
Padding tokens are widely used in large language models (LLMs) to equalize sequence lengths during batched inference. While they should be fully masked, implementation errors can c…
Leveraging NTPs for Efficient Hallucination Detection in VLMs
Ofir Azachi, Kfir Eliyahu, Eyal El Ani +4
Hallucinations of vision-language models (VLMs), which are misalignments between visual content and generated text, undermine the reliability of VLMs. One common approach for detec…
Jailbreak Attack Initializations as Extractors of Compliance Directions
Amit Levi, Rom Himelstein, Yaniv Nemcovsky +2
Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation space. Recent works show that initiali…