◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Kshitij Sachan

3 papers hereh-index 4941 citations7 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.AI1
  • cs.CR1
  • cs.LG1

identity via Semantic Scholar / OpenAlex

most citedSleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

39 citations · 39 across the 1 of their papers we have counts for

collaborators

3 papers

cs.AI2024

Debating with More Persuasive LLMs Leads to More Truthful Answers

Akbir Khan, John Hughes, Dan Valentine +7

Common methods for aligning large language models (LLMs) with desired behaviour heavily rely on human-labelled data. However, as models grow increasingly sophisticated, they will s…

cs.CR2024★ 39 cited

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Evan Hubinger, Carson Denison, Jesse Mu +36

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when giv…

cs.LG2023

AI Control: Improving Safety Despite Intentional Subversion

Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan +1

As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researcher…

◍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.