paper-with-me

Papers

Contextual Position Encoding: Learning to Count What's Important

2024-05-29 · Olga Golovneva, Tianlu Wang, Jason Weston, Sainbayar Sukhbaatar

The attention mechanism is a critical component of Large Language Models (LLMs) that allows tokens in a sequence to interact with each other, but is order-invariant. Incorporating position encoding (PE) makes it possible to address by position, such as attending to the i-th token. However, current PE methods use token counts to derive position, and thus cannot generalize to higher levels of abstraction, such as attending to the i-th sentence. In this paper, we propose a new position encoding method, Contextual Position Encoding (CoPE), that allows positions to be conditioned on context by incrementing position only on certain tokens determined by the model. This allows more general position addressing such as attending to the $i$-th particular word, noun, or sentence. We show that CoPE can solve the selective copy, counting and Flip-Flop tasks where popular position embeddings fail, and improves perplexity on language modeling and coding tasks.

📄 PDF Abstract BibTeX arXiv:2405.18719

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingPositionSentence

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
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…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Position Information in Transformers: An Overview

2021-02-22 · CL (ACL) 2022 9 · Philipp Dufter, Martin Schmitt, Hinrich Schütze

Transformers are arguably the main workhorse in recent Natural Language Processing research. By definition a Transformer is invariant with respect to reordering of the input. However, language is inherently sequential an…

ClusteringPosition

Measuring What AI Systems Might Do: Towards A Measurement Science in AI

2026-02-10 · Konstantinos Voudouris, Mirko Thalmann, Alex Kipnis, José Hernández-Orallo 외 arxiv

Scientists, policy-makers, business leaders, and members of the public care about what modern artificial intelligence systems are disposed to do. Yet terms such as capabilities, propensities, skills, values, and abilitie…

Positional encoding is not the same as context: A study on positional encoding for sequential recommendation

2024-05-16 · Alejo Lopez-Avila, Jinhua Du, Abbas Shimary, Ze Li

The rapid growth of streaming media and e-commerce has driven advancements in recommendation systems, particularly Sequential Recommendation Systems (SRS). These systems employ users' interaction histories to predict fut…

Recommendation SystemsSequential Recommendation

Energy-Gated Attention and Wavelet Positional Encoding: Complementary Inductive Biases for Transformer Attention

2026-05-25 · Athanasios Zeris arxiv

Standard transformer attention computes pairwise token similarity but treats all tokens as equally salient and all positions as equally local, regardless of the informational structure of the input. We identify two compl…

What Are the Invariant Occlusive Components of Image Patches? A Probabilistic Generative Approach

2013-12-01 · NeurIPS 2013 12 · Zhenwen Dai, Georgios Exarchakis, Jörg Lücke

We study optimal image encoding based on a generative approach with non-linear feature combinations and explicit position encoding. By far most approaches to unsupervised learning learning of visual features, such as spa…

Position