Discover · purdue.edu

Abulhair Saparov, Can/Will LLMs Learn to Reason?

CERIAS Weekly Security Seminar - Purdue University purdue.edu

Reasoning—the process of drawing conclusions from prior knowledge—is a hallmark of intelligence. Large language models, and more recently, large reasoning models have demonstrated impressive results on many reasoning-intensive benchmarks. Careful studies over the past few years have revealed that LLMs may exhibit some reasoning behavior, and larger models tend to do better on reasoning tasks. However, even the largest current models still struggle on various kinds of reasoning problems. In this talk, we will try to address the question: Are the observed reasoning limitations of LLMs fundamental in nature? Or will they be resolved by further increasing the size and data of these…

Length
52:36
More ways to use this
Open on another device
Scan this QR code to open the same public page

Scan to open this page. Your saved notes and account access are not included.

Download QR code

Open the page link

Keep going

Each of these is read from what this estate already kept: the feed a piece came through, the publisher behind it, the credits and topics the publisher printed. None of it is a recommendation, an identity or a record kept anywhere else.

More like this

Also from CERIAS Weekly Security Seminar - Purdue University

  1. Gary McGraw, No Security Meter for AI[email protected] purdue.edu
  2. Melissa Dark, The Nature of Cybersecurity Knowledge[email protected] purdue.edu
  3. Brad Sollar, Trust Without a Connection: Layered Security for Disconnected Mission Compute[email protected] purdue.edu
  4. JohnGabriel Nguyen-Truong, The Way We Travel the World Is at Risk: GPS Origins, Recent Disruptions, and Alternative Paths to Resilient Positioning[email protected] purdue.edu
  5. Sandhya Aneja, From Data to Decisions: AI-Powered Optimization in Modern Communication Networks[email protected] purdue.edu
  6. Eugene Spafford, AI: Cybersecurity Panacea or Existential Threat?[email protected] purdue.edu