paper-with-me

Papers

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

2022-10-24 · Kenneth Li, Aspen K. Hopkins, David Bau, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg

Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics, or do they rely on internal representations of the process that generates the sequences they see? We investigate this question by applying a variant of the GPT model to the task of predicting legal moves in a simple board game, Othello. Although the network has no a priori knowledge of the game or its rules, we uncover evidence of an emergent nonlinear internal representation of the board state. Interventional experiments indicate this representation can be used to control the output of the network and create "latent saliency maps" that can help explain predictions in human terms.

📄 PDF Abstract BibTeX arXiv:2210.13382

Code (4)

likenneth/othello_world 공식 구현 pytorch
alxndrtl/othello_mamba pytorch
keyonvafa/world-model-evaluation pytorch
openmoss/language-model-saes jax

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Emergent World Beliefs: Exploring Transformers in Stochastic Games

2025-12-18 · Adam Kamel, Tanish Rastogi, Michael Ma, Kailash Ranganathan 외 arxiv

Transformer-based large language models (LLMs) have demonstrated strong reasoning abilities across diverse fields, from solving programming challenges to competing in strategy-intensive games such as chess. Prior work ha…

Asking without Telling: Exploring Latent Ontologies in Contextual Representations

2020-04-29 · EMNLP 2020 11 · Julian Michael, Jan A. Botha, Ian Tenney

The success of pretrained contextual encoders, such as ELMo and BERT, has brought a great deal of interest in what these models learn: do they, without explicit supervision, learn to encode meaningful notions of linguist…

Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning

2025-12-23 · Seijin Kobayashi, Yanick Schimpf, Maximilian Schlegel, Angelika Steger 외 arxiv

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. During RL, these models explore by generat…

Hierarchical Reinforcement Learning

Emergent Linear Representations in World Models of Self-Supervised Sequence Models

2023-09-02 · Neel Nanda, Andrew Lee, Martin Wattenberg

How do sequence models represent their decision-making process? Prior work suggests that Othello-playing neural network learned nonlinear models of the board state (Li et al., 2023). In this work, we provide evidence of …

Decision Making

The emergence of numerical representations in communicating artificial agents

2026-02-11 · Daniela Mihai, Lucas Weber, Francesca Franzon arxiv

Human languages provide efficient systems for expressing numerosities, but whether the sheer pressure to communicate is enough for numerical representations to arise in artificial agents, and whether the emergent codes r…