Veniamin Veselovsky
@veniamin.bsky.social
phd student in cs at princeton
Excited to finally share work from this summer!
We propose using structured negotiation games to evaluate language models.
LMs are being used to create *dynamic* agents but benchmarks have remained *static*. Structured negotiation games solve this!
We propose using structured negotiation games to evaluate language models.
LMs are being used to create *dynamic* agents but benchmarks have remained *static*. Structured negotiation games solve this!
January 10, 2024 at 3:11 PM
Excited to finally share work from this summer!
We propose using structured negotiation games to evaluate language models.
LMs are being used to create *dynamic* agents but benchmarks have remained *static*. Structured negotiation games solve this!
We propose using structured negotiation games to evaluate language models.
LMs are being used to create *dynamic* agents but benchmarks have remained *static*. Structured negotiation games solve this!