2 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.CL2026
WhisperRT -- Turning Whisper into a Causal Streaming Model
Tomer Krichli, Bhiksha Raj, Joseph Keshet
Automatic Speech Recognition (ASR) has seen remarkable progress, with models like OpenAI Whisper and NVIDIA Canary achieving state-of-the-art (SOTA) performance in offline transcri…