iiinova — where your digital self keeps evolving

HUJI NLP @nlphuji.bsky.social · 24/04/2025

That’s a wrap on our first Huji NLP Hackathon! Congrats to the winning team! @noy-sternlicht.bsky.social @nirmazor.bsky.social They explored gender bias in AI-generated movie scripts using the Bechdel Test — and yep, you can guess the results...

063

Reposted by HUJI NLP

Eliya Habba @eliyahabba.bsky.social · 17/03/2025

Care about LLM evaluation? 🤖 🤔 We bring you ️️🕊️ DOVE a massive (250M!) collection of LLMs outputs On different prompts, domains, tokens, models... Join our community effort to expand it with YOUR model predictions & become a co-author!

1113

Reposted by HUJI NLP

shaharl6000.bsky.social @shaharl6000.bsky.social · 11/03/2025

Can RAG performance get * worse * with more relevant documents?📄 We put the number of retrieved documents in RAG to the test! 💥Preprint💥: arxiv.org/abs/2503.04388 1/3

233

Reposted by HUJI NLP

Gabi Stanovsky @gabistanovsky.bsky.social · 03/02/2025

There's a lot of talk about regulating AI, but do regulators know the technology well enough? In our new paper, we survey major reg efforts & find they rely on benchmarking, which we know to be problematic. How did this happen & what can we do about it? arxiv.org/pdf/2501.15693

102

Reposted by HUJI NLP

Eitan Wagner @eitanwagner.bsky.social · 19/12/2024

- “I heard there’s a new paper about Theory of Mind in LLMs!” - “I know! There’s like hundreds of them!” … Could someone be driving in the wrong direction? Check out our new opinion paper. w/ @nitalon.bsky.social , @joebarnby.bsky.social and Omri Abend.

082

Reposted by HUJI NLP

asaf-yehudai.bsky.social @asaf-yehudai.bsky.social · 13/12/2024

New preprint! ✨ Interested in LLM-as-a-Judge? Want to get the best judge for ranking your system? our new work is just for you: "JuStRank: Benchmarking LLM Judges for System Ranking" 🕺💃 arxiv.org/abs/2412.09569

arxiv.org

JuStRank: Benchmarking LLM Judges for System Ranking

Given the rapid progress of generative AI, there is a pressing need to systematically compare and choose between the numerous models and configurations available. The scale and versatility of such eva...

195

Reposted by HUJI NLP

Esther Shizgal @esthershizgal.bsky.social · 21/11/2024

1/n First time in the sky ✈️ I had a great time presenting my work at @emnlpmeeting.bsky.social ’s Workshop on Narrative Understanding and reconnecting with friends and colleagues in Miami! 🌴 How do religious trajectories evolve in Holocaust testimony narratives?

162