News for hackers. Stuff that matters.
Re:Weird GPT-4 behavior for the specific string “ davidjl” by visarga on Friday June 09, 2023 @03:02AM (#36254313)
This recent paper investigates the limits of symbolic operations in LLMs and found that they learn a weaker ability than actual reasoning - linearized subgraph matching.

> "Faith and Fate: Limits of Transformers on Compositionality" - We investigate the limits of these models across three representative compositional tasks -- multi-digit multiplication, logic grid puzzles, and a classic dynamic programming problem. These tasks require breaking problems down into sub-steps and synthesizing these steps into a precise answer. We formulate compositional tasks as computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures. Our empirical findings suggest that Transformers solve compositional tasks by reducing multi-step compositional reasoning into linearized subgraph matching, without necessarily developing systematic problem-solving skills.

https://arxiv.org/abs/2305.18654

There are no comments on this comment yet.