◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Francisco Eiras

13 papers hereh-index 9357 citations22 works total

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

author position
  • first author6
  • middle author5

Across the 11 of 13 papers where every author was matched, so the position is known.

fields
  • cs.LG6
  • cs.RO4
  • cs.CV2
  • cs.CL1
same name
  • Francisco Eiras — 3 papers

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
20182024
collaborators
Showing 2024Show all

3 papers · 1 filter

cs.CL2024

Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models

Francisco Eiras, Aleksandar Petrov, Philip H. S. Torr +2

Recent research shows that fine-tuning on benign instruction-following data can inadvertently undo the safety alignment process and increase a model's propensity to comply with har…

cs.LG2024

Risks and Opportunities of Open-Source Generative AI

Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +22

Applications of Generative AI (Gen AI) are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic chan…

cs.LG2024

Near to Mid-term Risks and Opportunities of Open-Source Generative AI

Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +21

In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for thes…

◍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.