Chain and Causal Attention for Efficient Entity Tracking - Archive ouverte HAL
Conference Papers Year : 2024

Chain and Causal Attention for Efficient Entity Tracking

Abstract

This paper investigates the limitations of transformers for entity-tracking tasks in large language models. We identify a theoretical constraint, showing that transformers require at least $\log_2 (n+1)$ layers to handle entity tracking with $n$ state changes. To address this issue, we propose an efficient and frugal enhancement to the standard attention mechanism, enabling it to manage long-term dependencies more efficiently. By considering attention as an adjacency matrix, our model can track entity states with a single layer. Empirical results demonstrate significant improvements in entity tracking datasets while keeping competitive performance on standard natural language modeling. Our modified attention allows us to achieve the same performance with drastically fewer layers. Additionally, our enhanced mechanism reveals structured internal representations of attention. Extensive experiments on both toy and complex datasets validate our approach. Our contributions include theoretical insights, an improved attention mechanism, and empirical validation.

Dates and versions

hal-04731420 , version 1 (10-10-2024)

Licence

Identifiers

Cite

Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen. Chain and Causal Attention for Efficient Entity Tracking. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics, Nov 2024, Miami, United States. ⟨hal-04731420⟩
18 View
0 Download

Altmetric

Share

More