causation

Tag

Cards List
#causation

For What Reason? Interpreting Models' Encoding of Causation and Antithesis

arXiv cs.CL ↗ · 2026-07-22 Cached

This paper investigates how instruction-tuned Transformer models (LLaMA and Mistral) encode the discourse relations of causation and antithesis using interpretability techniques on next-token prediction.

0 favorites 0 likes
← Back to home

Submit Feedback