3 papers
cs.AI2026
Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance
Or Biton, Tomer Krichli, Itai Allouche +1
Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably leading to alignment failures. T…
cs.LG2026
Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time
Itai Allouche, Joseph Keshet
Multimodal large language models (MLLMs) have revolutionized the landscape of AI, demonstrating impressive capabilities in tackling complex vision and audio-language tasks. However…
cs.CL2026
How Does a Deep Neural Network Look at Lexical Stress in English Words?
Itai Allouche, Itay Asael, Rotem Rousso +5
Despite their success in speech processing, neural networks often operate as black boxes, prompting the question: what informs their decisions, and how can we interpret them? This…