Record
- Authors
- Tan, D.; et al.
- Year
- 2025
- Title
- Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.48550/arxiv.2510.04340
- arXiv
- arXiv:2510.04340
- Our note
- none yet
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4416292398 · DOI 10.48550/arxiv.2510.04340 · arXiv:2510.04340 - From the lookup
- doi, title (the pages' own wording is under "As cited" below)
- Id
tan-2025-inoculation-prompting-eliciting-traits-from-llms
Cited on
- Diluting Poisoned Fine-Tuning Data Can Strengthen Its Effect read status: not stated
As cited
The pages cite this work in one form.
-
Tan, D., et al. (2025). Inoculation Prompting: Eliciting Traits from LLMs During Training Can Suppress Them at Test-Time. arXiv:2510.04340.
BibLaTeX
@misc{tan-2025-inoculation-prompting-eliciting-traits-from-llms,
author = {Tan, D. and others},
title = {{Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time}},
date = {2025},
doi = {10.48550/arxiv.2510.04340},
eprint = {2510.04340},
eprinttype = {arxiv}
}