◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Drake Thomas

3 papers hereh-index 3128 citations4 works total

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

author position
  • middle author3

Across the 3 of 3 papers where every author was matched, so the position is known.

fields
  • cs.AI2
  • cs.LG1

identity via Semantic Scholar / OpenAlex

most citedAuditing language models for hidden objectives

3 citations · 3 across the 2 of their papers we have counts for

collaborators

3 papers

cs.AI2025

Natural Emergent Misalignment from Reward Hacking in Production RL

Monte MacDiarmid, Benjamin Wright, Jonathan Uesato +19

We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, im…

cs.AI2025★ 3 cited

Auditing language models for hidden objectives

Samuel Marks, Johannes Treutlein, Trenton Bricken +32

We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objecti…

cs.LG2024

Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification

Thomas Kwa, Drake Thomas, Adrià Garriga-Alonso

When applying reinforcement learning from human feedback (RLHF), the reward is learned from data and, therefore, always has some error. It is common to mitigate this by regularizin…

◍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.