Author

Itai Allouche

h-index 1 View on Semantic Scholar

We have 2 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning May 2026

Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time

This work finds that hallucinations often arise when the model relies less on perceptual inputs, and that changing this reliance affects its predictions, and proposes a training-free framework that shifts relevance toward perceptual tokens by optimizing key-value representations during decoding, without modifying model...

Itai Allouche, Joseph Keshet · arXiv.org · 1 citation

#natural language process... Preprint Aug 2026

Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance

Empirical evaluations show that two LRP-guided decoding methods that steer generation toward trajectories more relevant to cue tokens promote safer responses, supporting cue-token attribution's role in compliance failures.

Or Biton, Tomer Krichli, Itai Allouche et al. · 1 citation