SOLICITATION NOTICE
A -- Bias Effects and Notable Generative AI Limitations (BENGAL) Targeted Super Seedling Research Topics
- Notice Date
- 11/20/2023 2:08:21 PM
- Notice Type
- Combined Synopsis/Solicitation
- NAICS
- 541715
— Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)
- Contracting Office
- IARPA CONTRACTING OFFICE Washington DC 20511 USA
- ZIP Code
- 20511
- Solicitation Number
- IARPA-BAA-24-03
- Response Due
- 1/19/2024 1:00:00 PM
- Archive Date
- 02/19/2024
- Point of Contact
- Dr. Timothy McKinnon, Program Manager, Liana Todman, Phone: 703-275-2195
- E-Mail Address
-
dni-bengal-proposers-day@iarpa.gov, dni-IARPA-BAA-24-03@iarpa.gov
(dni-bengal-proposers-day@iarpa.gov, dni-IARPA-BAA-24-03@iarpa.gov)
- Description
- 11/20/23 - Amendment 001:��The BAA is amended to revise the submission window for white papers to December 1, 2023 12:00PM EST through December 5, 2023 12:00PM EST and to add the requirement for a Quad Chart attachment to the proposal, see attached Amendment 001. ________________________________________ Original posting: White Papers (abstracts) Due Date: December 5, 2023 12:00 PM EST (Offerors are strongly encouraged to submit white papers before submitting a proposal). The submission window for white papers will open on November 27, 2023 12:00PM EST and close on December 5, 2023 12:00PM EST. The Intelligence Advanced Research Projects Activity (IARPA) invests in high-risk/highpayoff research programs that have the potential to provide our nation with an overwhelming intelligence advantage. IARPA seeks to develop new capabilities to enable the safe adoption and use of generative AI technologies to greatly enhance the effectiveness and efficiency of the Intelligence Community (IC). The goal of the BENGAL targeted super seedling is to understand LLM threat modes, quantify them and to find novel methods to correct threats and vulnerabilities or to work resiliently with imperfect models. IARPA seeks to develop and incorporate novel technologies to efficiently probe large language models to detect and characterize LLM threat modes and vulnerabilities. Performers will focus on one or more of the topic domains below, clearly articulate a taxonomy of threat modes within their domain of interest and develop technologies to serve as an analog to �virus scan� software.
- Web Link
-
SAM.gov Permalink
(https://sam.gov/opp/d4e3fc49d8774a2d8c163b7f29bdfdc8/view)
- Place of Performance
- Address: Washington, DC 20511, USA
- Zip Code: 20511
- Country: USA
- Zip Code: 20511
- Record
- SN06889774-F 20231122/231120230046 (samdaily.us)
- Source
-
SAM.gov Link to This Notice
(may not be valid after Archive Date)
| FSG Index | This Issue's Index | Today's SAM Daily Index Page |