Image de couverture de livre

How Do Transformers Learn Variable Binding in Symbolic Programs?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Yiwei, Geiger, Atticus, Millière, Raphaël
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

How Causal Abstraction Underpins Computational Explanation
par: Geiger, Atticus, et autres
Publié: (2025)

A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates
par: Millière, Raphaël, et autres
Publié: (2024)

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space
par: Bigelow, Eric, et autres
Publié: (2026)

HyperSteer: Activation Steering at Scale with Hypernetworks
par: Sun, Jiuding, et autres
Publié: (2025)

Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
par: Boppana, Siddharth, et autres
Publié: (2026)

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
par: Wu, Zhengxuan, et autres
Publié: (2024)

ReFT: Representation Finetuning for Language Models
par: Wu, Zhengxuan, et autres
Publié: (2024)

Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small
par: Chaudhary, Maheep, et autres
Publié: (2024)

HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks
par: Sun, Jiuding, et autres
Publié: (2025)

How do Language Models Bind Entities in Context?
par: Feng, Jiahai, et autres
Publié: (2023)

Do pretrained Transformers Learn In-Context by Gradient Descent?
par: Shen, Lingfeng, et autres
Publié: (2023)

Constructing Interpretable Features from Compositional Neuron Groups
par: Shafran, Or, et autres
Publié: (2025)

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
par: Wu, Zhengxuan, et autres
Publié: (2025)

Symbolic Learning Enables Self-Evolving Agents
par: Zhou, Wangchunshu, et autres
Publié: (2024)

Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
par: Csordás, Róbert, et autres
Publié: (2024)

(How) Do Language Models Track State?
par: Li, Belinda Z., et autres
Publié: (2025)

Do Efficient Transformers Really Save Computation?
par: Yang, Kai, et autres
Publié: (2024)

Prism: Symbolic Superoptimization of Tensor Programs
par: Wu, Mengdi, et autres
Publié: (2026)

Fair In-Context Learning via Latent Concept Variables
par: Bhaila, Karuna, et autres
Publié: (2024)

Symbolic Prompt Program Search: A Structure-Aware Approach to Efficient Compile-Time Prompt Optimization
par: Schnabel, Tobias, et autres
Publié: (2024)

Do Large Language Models Know How Much They Know?
par: Prato, Gabriele, et autres
Publié: (2025)

How Likely Do LLMs with CoT Mimic Human Reasoning?
par: Bao, Guangsheng, et autres
Publié: (2024)

Combining Causal Models for More Accurate Abstractions of Neural Networks
par: Pîslar, Theodora-Mara, et autres
Publié: (2025)

LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
par: Zheng, Zihan, et autres
Publié: (2025)

Cultural Binding Heads in Language Models
par: Floro, Avrile, et autres
Publié: (2026)

How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
par: Cui, Yingqian, et autres
Publié: (2026)

A Meta-Learning Perspective on Transformers for Causal Language Modeling
par: Wu, Xinbo, et autres
Publié: (2023)

Preference Learning Algorithms Do Not Learn Preference Rankings
par: Chen, Angelica, et autres
Publié: (2024)

BertaQA: How Much Do Language Models Know About Local Culture?
par: Etxaniz, Julen, et autres
Publié: (2024)

MMSR: Symbolic Regression is a Multi-Modal Information Fusion Task
par: Li, Yanjie, et autres
Publié: (2024)

One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
par: Khan, Zaid, et autres
Publié: (2025)

In-Context Occam's Razor: How Transformers Prefer Simpler Hypotheses on the Fly
par: Deora, Puneesh, et autres
Publié: (2025)

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
par: Jaipersaud, Brandon, et autres
Publié: (2025)

Towards Verifiable Text Generation with Symbolic References
par: Hennigen, Lucas Torroba, et autres
Publié: (2023)

Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics
par: Zur, Amir, et autres
Publié: (2025)

Can Large Language Models Understand Symbolic Graphics Programs?
par: Qiu, Zeju, et autres
Publié: (2024)

SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs
par: Liu, Ben, et autres
Publié: (2025)

Transformers Struggle to Learn to Search
par: Saparov, Abulhair, et autres
Publié: (2024)

Do Large Language Models Show Biases in Causal Learning?
par: Carro, Maria Victoria, et autres
Publié: (2024)

Why Larger Language Models Do In-context Learning Differently?
par: Shi, Zhenmei, et autres
Publié: (2024)