Paper recorded by Signals 4 on 2026-09-18 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-18 on arXiv · recorded by Signals 4 on 2026-09-21
Category: cs.CL · 自然语言处理 · first seen 2026-09-21
Behavioral failures can make a transformer appear to lack a world model even when it has learned faithful representations of its environment. We demonstrate this in TaxiGPT, a transformer trained on random walks through Manhattan whose failures have been interpreted as evidence of an incoherent internal map. Through mechanistic analysis and causal interventions, we show that the model represents i