Cover Image

Complexity of Symbolic Representation in Working Memory of Transformer Correlates with the Complexity of a Task

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sagirova, Alsu, Burtsev, Mikhail
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
by: Sagirova, Alsu, et al.
Published: (2025)

Learning Elementary Cellular Automata with Transformers
by: Burtsev, Mikhail
Published: (2024)

Associative Recurrent Memory Transformer
by: Rodkin, Ivan, et al.
Published: (2024)

Symbolic Working Memory Enhances Language Models for Complex Rule Application
by: Wang, Siyuan, et al.
Published: (2024)

Scaling Transformer to 1M tokens and beyond with RMT
by: Bulatov, Aydar, et al.
Published: (2023)

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity
by: Kuratov, Yuri, et al.
Published: (2025)

In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss
by: Kuratov, Yuri, et al.
Published: (2024)

Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
by: Liao, Huanxuan, et al.
Published: (2024)

Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models
by: Chepurova, Alla, et al.
Published: (2025)

Limitations of Normalization in Attention Mechanism
by: Mudarisov, Timur, et al.
Published: (2025)

Divide et Impera: Multi-Transformer Architectures for Complex NLP-Tasks
by: Helland, Solveig, et al.
Published: (2023)

TaskComplexity: A Dataset for Task Complexity Classification with In-Context Learning, FLAN-T5 and GPT-4o Benchmarks
by: Rasheed, Areeg Fahad, et al.
Published: (2024)

Correlation Does Not Imply Compensation: Complexity and Irregularity in the Lexicon
by: Doucette, Amanda, et al.
Published: (2024)

Type and Complexity Signals in Multilingual Question Representations
by: Kokot, Robin, et al.
Published: (2025)

BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
by: Kuratov, Yuri, et al.
Published: (2024)

Synaptic Theory of Chunking in Working Memory
by: Zhong, Weishun, et al.
Published: (2024)

SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets
by: Wang, Ziwei, et al.
Published: (2025)

A Survey on Complex Tasks for Goal-Directed Interactive Agents
by: Hartmann, Mareike, et al.
Published: (2024)

LLM for Complex Reasoning Task: An Exploratory Study in Fermi Problems
by: Liu, Zishuo, et al.
Published: (2025)

Czech Dataset for Complex Aspect-Based Sentiment Analysis Tasks
by: Šmíd, Jakub, et al.
Published: (2025)

ComplexityNet: Increasing LLM Inference Efficiency by Learning Task Complexity
by: Bae, Henry, et al.
Published: (2023)

HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
by: Zhou, Chulun, et al.
Published: (2025)

BAR: A Backward Reasoning based Agent for Complex Minecraft Tasks
by: Du, Weihong, et al.
Published: (2025)

Deliberate Planning in Language Models with Symbolic Representation
by: Xiong, Siheng, et al.
Published: (2025)

Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction
by: Sainsbury, Chris, et al.
Published: (2026)

Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation
by: Liang, Chen, et al.
Published: (2024)

TOD-ProcBench: Benchmarking Complex Instruction-Following in Task-Oriented Dialogues
by: Ghazarian, Sarik, et al.
Published: (2025)

Characterizing Knowledge Graph Tasks in LLM Benchmarks Using Cognitive Complexity Frameworks
by: Todorovikj, Sara, et al.
Published: (2025)

LegalRikai: Open Benchmark -- Benchmark for Complex Japanese Corporate Legal Tasks
by: Fujita, Shogo, et al.
Published: (2025)

MMESGBench: Pioneering Multimodal Understanding and Complex Reasoning Benchmark for ESG Tasks
by: Zhang, Lei, et al.
Published: (2025)

Reasoning Topology Matters: Network-of-Thought for Complex Reasoning Tasks
by: Huang, Fan
Published: (2026)

ComplexFormer: Disruptively Advancing Transformer Inference Ability via Head-Specific Complex Vector Attention
by: Shao, Jintian, et al.
Published: (2025)

Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs
by: Zhang, Xiang, et al.
Published: (2025)

Think Before You Act: Decision Transformers with Working Memory
by: Kang, Jikun, et al.
Published: (2023)

Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks
by: Wang, Yihan, et al.
Published: (2025)

A Fine-Tuning Approach for T5 Using Knowledge Graphs to Address Complex Tasks
by: Liao, Xiaoxuan, et al.
Published: (2025)

D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use
by: Xu, Bowen, et al.
Published: (2026)

From Symbolic Tasks to Code Generation: Diversification Yields Better Task Performers
by: Zhang, Dylan, et al.
Published: (2024)

Improving Factuality with Explicit Working Memory
by: Chen, Mingda, et al.
Published: (2024)

Transformers for Complex Query Answering over Knowledge Hypergraphs
by: Tsang, Hong Ting, et al.
Published: (2025)