collaborators

6 papers

cs.CL2026

Tokenizing Crosslingual Homographs

Rotem Brillant, Yuval Pinter

Multilingual language models rely on shared subword vocabularies to represent multiple languages within a limited number of token units. While such sharing is often useful, it can…

cs.CL2026

Inside the LLM Word Factory

Benzi Busigin, Yuval Pinter

Transformer language models process input provided as subword fragments, but natural language semantics usually rely on word-level concepts. Detokenization is the process where mod…

cs.CL2026

Which Pieces Does Unigram Tokenization Really Need?

Sander Land, Yuval Pinter

The Unigram tokenization algorithm offers a probabilistic alternative to the greedy heuristics of Byte-Pair Encoding. Despite its theoretical elegance, its implementation in practi…

cs.CL2026

CharBench: Evaluating the Role of Tokenization in Character-Level Tasks

Omri Uzan, Yuval Pinter

Tasks that require character-level reasoning, such as counting or locating characters within words, remain challenging for contemporary language models. A common conjecture is that…

cs.CL2026

Hebrew Diacritics Restoration using Visual Representation

Yair Elboher, Yuval Pinter

Diacritics restoration in Hebrew is a fundamental task for ensuring accurate word pronunciation and disambiguating textual meaning. Despite the language's high degree of ambiguity…

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…