Image de couverture de livre

Exploring Compositional Generalization (in COGS/ReCOGS_pos) by Transformers using Restricted Access Sequence Processing (RASP)

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Bruns, William
Format:	Preprint
Publié:	2025
Sujets:	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

ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation
par: Wu, Zhengxuan, et autres
Publié: (2023)

Discovering Interpretable Algorithms by Decompiling Transformers to RASP
par: Huang, Xinting, et autres
Publié: (2026)

Knee-Deep in C-RASP: A Transformer Depth Hierarchy
par: Yang, Andy, et autres
Publié: (2025)

Exploring Continual Learning of Compositional Generalization in NLI
par: Fu, Xiyan, et autres
Publié: (2024)

Analyzing the Inner Workings of Transformers in Compositional Generalization
par: Kumon, Ryoma, et autres
Publié: (2025)

Re-Representation in Sentential Relation Extraction with Sequence Routing Algorithm
par: Bahrami, Ramazan Ali, et autres
Publié: (2025)

ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization
par: Chen, Guoxin, et autres
Publié: (2025)

ReMamba: Equip Mamba with Effective Long-Sequence Modeling
par: Yuan, Danlong, et autres
Publié: (2024)

The Impact of Depth on Compositional Generalization in Transformer Language Models
par: Petty, Jackson, et autres
Publié: (2023)

Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
par: Mondorf, Philipp, et autres
Publié: (2024)

LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models
par: Zhou, Zihan, et autres
Publié: (2024)

Transforming Chatbot Text: A Sequence-to-Sequence Approach
par: Reddy, Natesh, et autres
Publié: (2025)

ADEQA: A Question Answer based approach for joint ADE-Suspect Extraction using Sequence-To-Sequence Transformers
par: Arannil, Vinayak, et autres
Publié: (2024)

Analysing The Impact of Sequence Composition on Language Model Pre-Training
par: Zhao, Yu, et autres
Publié: (2024)

GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection
par: Deng, Zhijie, et autres
Publié: (2025)

Automatic Differential Diagnosis using Transformer-Based Multi-Label Sequence Classification
par: Sadi, Abu Adnan, et autres
Publié: (2024)

Advancements in Natural Language Processing: Exploring Transformer-Based Architectures for Text Understanding
par: Wu, Tianhao, et autres
Publié: (2025)

Transformers with Selective Access to Early Representations
par: Gunasekaran, Skye, et autres
Publié: (2026)

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers
par: Zhang, Zhongwang, et autres
Publié: (2025)

Aligning Brain Activity with Advanced Transformer Models: Exploring the Role of Punctuation in Semantic Processing
par: Lamprou, Zenon, et autres
Publié: (2025)

Equipping Transformer with Random-Access Reading for Long-Context Understanding
par: Yang, Chenghao, et autres
Publié: (2024)

Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers
par: Ebrahimi, MohammadReza, et autres
Publié: (2024)

NLP4PBM: A Systematic Review on Process Extraction using Natural Language Processing with Rule-based, Machine and Deep Learning Methods
par: Van Woensel, William, et autres
Publié: (2024)

ReARTeR: Retrieval-Augmented Reasoning with Trustworthy Process Rewarding
par: Sun, Zhongxiang, et autres
Publié: (2025)

SequenceLayers: Sequence Processing and Streaming Neural Networks Made Easy
par: Skerry-Ryan, RJ, et autres
Publié: (2025)

E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation
par: Zhong, Qihuang, et autres
Publié: (2022)

FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation
par: Kiruluta, Andrew, et autres
Publié: (2025)

Exploring Compositional Generalization of Multimodal LLMs for Medical Imaging
par: Cai, Zhenyang, et autres
Publié: (2024)

Hate Content Detection via Novel Pre-Processing Sequencing and Ensemble Methods
par: Chhabra, Anusha, et autres
Publié: (2024)

PrahokBART: A Pre-trained Sequence-to-Sequence Model for Khmer Natural Language Generation
par: Kaing, Hour, et autres
Publié: (2025)

Simulating Weighted Automata over Sequences and Trees with Transformers
par: Rizvi, Michael, et autres
Publié: (2024)

ReCode: Reinforcing Code Generation with Reasoning-Process Rewards
par: Fan, Lishui, et autres
Publié: (2025)

Long-range Modeling and Processing of Multimodal Event Sequences
par: Li, Jichu, et autres
Publié: (2026)

Learning Extrapolative Sequence Transformations from Markov Chains
par: Hager, Sophia, et autres
Publié: (2025)

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers
par: Dai, Xinnan, et autres
Publié: (2025)

Exploring the Limitations of Large Language Models in Compositional Relation Reasoning
par: Zhao, Jinman, et autres
Publié: (2024)

Dissociating Decodability and Causal Use in Bracket-Sequence Transformers
par: Sharma, Aryan, et autres
Publié: (2026)

HyReC: Exploring Hybrid-based Retriever for Chinese
par: Wang, Zunran, et autres
Publié: (2025)

Product vs. Process: Exploring EFL Students' Editing of AI-Generated Text for Expository Writing
par: Woo, David James, et autres
Publié: (2025)

Exploring Generative Process Reward Modeling for Semi-Structured Data: A Case Study of Table Question Answering
par: Tang, Lei, et autres
Publié: (2025)