iiinova — where your digital self keeps evolving

DARK lab

@ucldark.com

UCL Deciding, Acting, and Reasoning with Knowledge (DARK) Lab at UCL led by @rockt.ai, @egrefen.bsky.social, @jparkerholder.bsky.social, and Roberta Raileanu. ucldark.com

Posts Replies Media

Reposted by DARK lab

Tim Rocktäschel @handle.invalid · 25/11/2024

@ucl-dark.bsky.social entered the stage! Thanks @lauraruis.bsky.social :)

0182

DARK lab @ucldark.com · 25/11/2024

Check out Tim's start pack for Open-Endedness on Bluesky!

010

Reposted by DARK lab

Laura @lauraruis.bsky.social · 20/11/2024

How do LLMs learn to reason from data? Are they ~retrieving the answers from parametric knowledge🦜? In our new preprint, we look at the pretraining data and find evidence against this: Procedural knowledge in pretraining drives LLM reasoning ⚙️🔢 🧵⬇️

36850139

Reposted by DARK lab

Tim Rocktäschel @handle.invalid · 22/11/2024

The LLM parrot analogy is dead. Fantastic work by UCL DARK's @lauraruis.bsky.social on rigorously investigating whether LLMs learn reasoning from procedural knowledge during pretraining.

0504

Reposted by DARK lab

Tim Rocktäschel @handle.invalid · 22/11/2024

Excited to announce "BALROG: a Benchmark for Agentic LLM and VLM Reasoning On Games" led b UCL DARK's @dpaglieri.bsky.social! Douwe Kiela plot below is maybe the scariest for AI progress — LLM benchmarks are saturating at an accelerating rate. BALROG to the rescue. This will keep us busy for years.

312415