◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Jacob Drori

4 papers

No researched profile yet.

papers

Publications (4)

cs.LG2025

Towards a unified and verified understanding of group-operation networks

Wilson Wu, Louis Jaburi, Jacob Drori +1

A recent line of work in mechanistic interpretability has focused on reverse-engineering the computation performed by neural networks trained on the binary operation of finite grou…

cs.LG2026

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…

cs.AI2026

Recontextualization Mitigates Specification Gaming without Modifying the Specification

Ariana Azarbal, Victor Gillioz, Vladimir Ivanov +6

Developers often struggle to specify correct training labels and rewards. Perhaps they don't need to. We propose recontextualization, which reduces how often language models "game"…

cs.LG2025

Output Supervision Can Obfuscate the Chain of Thought

Jacob Drori, Luke Marks, Bryce Woodworth +2

OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep C…

◍wovepaper

A living map of arXiv — papers, researchers, institutions.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Sign in
  • Library
  • Chat
Data
  • arXiv.org
  • Latest RSS
Metadata from arXiv.org · Not affiliated with arXiv