3 papers
cs.CL2025
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…
cs.CL2025
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…
cs.CV2025
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…