◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Mrinank Sharma

17 papers hereh-index 122.1k citations21 works total

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

author position
  • first author4
  • middle author8
  • last author5

Across the 17 of 17 papers where every author was matched, so the position is known.

fields
  • cs.CL6
  • cs.CR4
  • cs.LG3
  • cs.AI2
  • cs.CY1
  • stat.ML1
same name
  • Mrinank Sharma — 1 paper, h 12
  • Mrinank Sharma — 1 paper, h 2

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

activity
20192026
most citedSleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

39 citations · 52 across the 14 of their papers we have counts for

collaborators
Showing cs.CRShow all

3 papers · 1 filter

cs.CR2026

Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs

Jackson Kaunismaa, Avery Griffin, John Hughes +3

Model developers implement safeguards in frontier models to prevent misuse, for example, by employing classifiers to filter dangerous outputs. In this work, we demonstrate that eve…

cs.CR2026

Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks

Hoagy Cunningham, Jerry Wei, Zihan Wang +26

We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and refusal rates compared to prev…

cs.CR2024

PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning

Tingchen Fu, Mrinank Sharma, Philip Torr +3

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBenc…

◍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.