◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Guy Kaplan

The Hebrew University of Jerusalem

4 papers hereh-index 255 citations5 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author3
  • middle author1

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.CL4
affiliations
  • The Hebrew University of Jerusalem
Homepage

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.CL2026

Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic

Yuval Reif, Guy Kaplan, Roy Schwartz

Large language models (LLMs) often encode word-form variation (e.g., walk vs. walked) as linear directions in the embedding space. However, standard tokenization algorithms treat s…

cs.CL2026

Why Fine-Tuning Encourages Hallucinations and How to Fix It

Guy Kaplan, Zorik Gekhman, Zhen Zhu +5

Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through supervised fine-tuning…

cs.CL2026

Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models

Guy Kaplan, Michael Toker, Yuval Reif +2

Text-to-image generation models suffer from alignment problems, where generated images fail to accurately capture the objects and relations in the text prompt. Prior work has focus…

cs.CL2025

From Tokens to Words: On the Inner Lexicon of LLMs

Guy Kaplan, Matanel Oren, Yuval Reif +1

Natural language is composed of words, but modern large language models (LLMs) process sub-words as input. A natural question raised by this discrepancy is whether LLMs encode word…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.