We are joined by Aman Madaan and Shuyan Zhou. They are both PhD students at the Language Technology Institute at Carnegie Mellon University. They join us to discuss their latest published paper, PAL: Program-aided Language Models.
Aman and Shuyan started by sharing how the application of LLMs has evolved. They talked about the performance of LLMs on arithmetic tasks in contrast to coding tasks. Aman introduced their PAL model and how it helps LLMs improve at arithmetic tasks. He shared examples of the tasks PAL was tested on. Shuyan discussed how PAL’s performance was evaluated using Big Bench hard tasks.
They discussed the kind of mistakes LLMs tend to make and how the PAL’s model circumvents these limitations. They also discussed how these developments in LLMS can improve kids learning.
Rounding up, Aman discussed the CoCoGen project, a project that enables NLP tasks to be converted to graphs. Shuyan and Aman shared their next research steps.
Follow Shuyan on Twitter @shuyanzhxyc. Follow Aman on @aman_madaan.
Behavioral Genetics
Signal in the Noise
Pose Tracking
Modeling Group Behavior
Advances in Data Loggers
What You Know About Intelligence is Wrong (fixed)
Animal Decision Making
Octopus Cognition
Optimal Foraging
Memory in Chess
OpenWorm
What the Antlion Knows
AI Roundtable
Uncontrollable AI Risks
I LLM and You Can Too
Q&A with Kyle
LLMs for Data Analysis
AI Platforms
Deploying LLMs
A Survey Assessing Github Copilot
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
Black Wolf Feed (Chapo Premium Feed Bootleg)
Bannon`s War Room