From Semantics to Symbols: A Two-Stage Framework for Deconstructing LLM Reasoning into Concepts and Rules

Mar 25

Written By Centaur Info

https://neurips.cc/virtual/2025/loc/san-diego/125206

Admin for site, used by JW

MC3G: Model Agnostic Causally Constrained Counterfactual Generation

Interpretable Imitation Learning via Generative Adversarial STL Inference and Control