Avenging Polanyi's Revenge: Exploiting the Approximate Omniscience of LLMs in Planning without Deluding Yourself In the Process
Jul 28, 2023
Speakers
Subbarao Kambhampati
Speaker · 0 followers
About
LLMs are on track to reverse what seemed like an inexorable shift of AI from explicit to tacit knowledge tasks. Trained as they are on everything ever written on the web, LLMs exhibit "approximate omniscience"--they can provide answers to all sorts of queries, with nary a guarantee. This could herald a new era for knowledge-based AI systems--with LLMs taking the role of (blowhard?) experts. But first, we have to stop confusing the impressive form of the generated knowledge for correct content, and resist the temptation to ascribe reasoning powers to approximate retrieval by these n-gram models on steroids. We have to focus instead on LLM-Modulo techniques that complement the unfettered idea generation of LLMs with careful vetting by model-based AI systems. In this talk, I will reify this vision and attendant caveats in the context of the role of LLMs in planning tasks.LLMs are on track to reverse what seemed like an inexorable shift of AI from explicit to tacit knowledge tasks. Trained as they are on everything ever written on the web, LLMs exhibit "approximate omniscience"--they can provide answers to all sorts of queries, with nary a guarantee. This could herald a new era for knowledge-based AI systems--with LLMs taking the role of (blowhard?) experts. But first, we have to stop confusing the impressive form of the generated knowledge for correct content, a…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition
Watch later
Yucheng Lu, …
“AI For Good” Isn’t Good Enough: A Call for Human-Centered AI
Watch later
Implicit Jacobian Regularization Weighted with Impurity of Probability Output
Watch later
Sungyoon Lee, …