Signals 4 · free daily AI digest

World Modeling in Transformers

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

Abstract

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

Read on arXiv →

#11 most recent of 200 cs.CL papers we have recorded · ↑ newer: Per-Aetiology Contrastive Severity Embeddings with Phonological Pseudo · ↓ older: CIBuzzBench: A Benchmark for Cross-Lingual Understanding of Chinese In
Cite this page: World Modeling in Transformers: the #11 most recent of 200 cs.CL papers we have recorded (as of 2026-09-18). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/world-modeling-in-transformers.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions