◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Thomas Kwa

2 papers hereh-index 221 citations2 works total

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

author position
  • first author1
  • middle author1

Across the 2 of 2 papers where every author was matched, so the position is known.

fields
  • cs.LG2
same name
  • Thomas Kwa — 5 papers, h 4

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

collaborators

2 papers

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…

cs.LG2024

InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques

Rohan Gupta, Iván Arcuschin, Thomas Kwa +1

Mechanistic interpretability methods aim to identify the algorithm a neural network implements, but it is difficult to validate such methods when the true algorithm is unknown. Thi…

◍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.