paper-with-me

Papers

An All-MLP Sequence Modeling Architecture That Excels at Copying

2024-06-23 · Chenwei Cui, Zehao Yan, Gedeon Muhawenayo, Hannah Kerner

Recent work demonstrated Transformers' ability to efficiently copy strings of exponential sizes, distinguishing them from other architectures. We present the Causal Relation Network (CausalRN), an all-MLP sequence modeling architecture that can match Transformers on the copying task. Extending Relation Networks (RNs), we implemented key innovations to support autoregressive sequence modeling while maintaining computational feasibility. We discovered that exponentially-activated RNs are reducible to linear time complexity, and pre-activation normalization induces an infinitely growing memory pool, similar to a KV cache. In ablation study, we found both exponential activation and pre-activation normalization are indispensable for Transformer-level copying. Our findings provide new insights into what actually constitutes strong in-context retrieval.

📄 PDF Abstract BibTeX arXiv:2406.16168

Code (1)

kerner-lab/causal-relation-networks 공식 구현 pytorch

Tasks

AllRelationRelation NetworkRetrieval

Similar Papers 제목 키워드 기반

Repeat After Me: Transformers are Better than State Space Models at Copying

2024-02-01 · Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach

Transformers are the dominant architecture for sequence modeling, but there is growing interest in models that use a fixed-size latent state that does not depend on the sequence length, which we refer to as "generalized …

State Space Models

Sequential Copying Networks

2018-07-06 · Qingyu Zhou, Nan Yang, Furu Wei, Ming Zhou

Copying mechanism shows effectiveness in sequence-to-sequence based neural network models for text generation tasks, such as abstractive sentence summarization and question generation. However, existing works on modeling…

DecoderQuestion GenerationQuestion-GenerationSentence+2

Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D

2026-07-17 · Haodong Wen, Yiran Zhang, Yingfa Chen, Kaifeng Lyu arxiv

While large language models (LLMs) can solve advanced reasoning problems in seconds, we show that even frontier models fail to perform a much simpler operation: exactly copying an input string that lies well within their…

Incorporating Copying Mechanism in Sequence-to-Sequence Learning

2016-03-21 · ACL 2016 8 · Jiatao Gu, Zhengdong Lu, Hang Li, Victor O. K. Li

We address an important problem in sequence-to-sequence (Seq2Seq) learning referred to as copying, in which certain segments in the input sequence are selectively replicated in the output sequence. A similar phenomenon i…

DecoderText Summarization

Generating Medical Reports from Patient-Doctor Conversations Using Sequence-to-Sequence Models

2020-07-01 · WS 2020 7 · Seppo Enarvi, Marilisa Amoia, Miguel Del-Agua Teba, Brian Delaney 외

We discuss automatic creation of medical reports from ASR-generated patient-doctor conversational transcripts using an end-to-end neural summarization approach. We explore both recurrent neural network (RNN) and Transfor…

Machine TranslationTranslation