mlsanityData to 14 Oct 2026

ListOps: A Diagnostic Dataset for Latent Tree Learning

arXiv 1804.06028 ↗First posted 17 Apr 2018cs.CLcited by 129

Not on the map. Why?

Abstract (arXiv)

Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence classification, they do not learn grammars that conform to any plausible semantic or syntactic formalism (Williams et al., 2018a). Studying the parsing ability of such models in natural language can be challenging due to the inherent complexities of natural language, like having several valid parses for a single sentence. In this paper we introduce ListOps, a toy dataset created to study the parsing ability of latent tree models. ListOps sequences are in the style of prefix arithmetic. The dataset is designed to have a single correct parsing strategy that a system needs to learn to succeed at the task. We show that the current leading latent tree models are unable to learn to parse and succeed at ListOps. These models achieve accuracies worse than purely sequential RNNs.

Key facts. Cited by 129 papers in the map (data through 14 Oct 2026). First posted on arXiv 17 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 28; 2022: 19; 2023: 23; 2024: 30; 2025: 19; 2026: 10.

129 papers.

Sort:

By area:

  1. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  2. 2021Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attentioncited by 471
  3. 2021Random Feature Attentioncited by 354
  4. 2022cosFormer: Rethinking Softmax in Attentioncited by 213
  5. 2022Mega: Moving Average Equipped Gated Attentioncited by 179
  6. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  7. 2021Scatterbrain: Unifying Sparse and Low-rank Attention Approximationcited by 130
  8. 2021SOFT: Softmax-free Transformer with Linear Complexitycited by 128
  9. 2021Long-Short Transformer: Efficient Transformers for Language and Visioncited by 102
  10. 2021Luna: Linear Unified Nested Attentioncited by 96
  11. 2021Going Beyond Linear Transformers with Recurrent Fast Weight Programmerscited by 89
  12. 2021A Practical Survey on Faster and Lighter Transformerscited by 73
38 more
  1. 2022Flowformer: Linearizing Transformers with Conservation Flowscited by 69
  2. 2021Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr"om Methodcited by 63
  3. 2021The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalizationcited by 62
  4. 2021Memory-efficient Transformers via Top-k Attentioncited by 60
  5. 2024Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Lengthcited by 46
  6. 2021Relative Positional Encoding for Transformers with Linear Complexitycited by 37
  7. 2022Efficient Long Sequence Modeling via State Space Augmented Transformercited by 37
  8. 2024How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpadcited by 36
  9. 2023Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priorscited by 34
  10. 2023SwitchHead: Accelerating Transformers with Mixture-of-Experts Attentioncited by 34
  11. 2025PolaFormer: Polarity-aware Linear Attention for Vision Transformerscited by 32
  12. 2021Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systemscited by 31
  13. 2022Linear Complexity Randomized Self-attention Mechanismcited by 31
  14. 2023Bridging Discrete and Backpropagation: Straight-Through and Beyondcited by 31
  15. 2023Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representationcited by 29
  16. 2021Improving Transformers with Probabilistic Attention Keyscited by 28
  17. 2021FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attentioncited by 26
  18. 2023Online learning of long-range dependenciescited by 25
  19. 2023Sparse Modular Activation for Efficient Sequence Modelingcited by 20
  20. 2022BayesFormer: Transformer with Uncertainty Estimationcited by 19
  21. 2023Learning Long Sequences in Spiking Neural Networkscited by 19
  22. 2024State-Free Inference of State-Space Models: The Transfer Function Approachcited by 18
  23. 2021You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Samplingcited by 17
  24. 2021Learning Hierarchical Structures with Differentiable Nondeterministic Stackscited by 16
  25. 2021Modeling Hierarchical Structures with Continuous Recursive Neural Networkscited by 15
  26. 2023MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superpositioncited by 14
  27. 2024Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformerscited by 11
  28. 2024A Theory for Length Generalization in Learning to Reasoncited by 11
  29. 2024From Generalization Analysis to Optimization Designs for State Space Modelscited by 11
  30. 2021Dynamic Token Normalization Improves Vision Transformerscited by 10
  31. 2022A Call for Clarity in Beam Search: How It Works and When It Stopscited by 10
  32. 2023From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformerscited by 10
  33. 2024Layer-Adaptive State Pruning for Deep State Space Modelscited by 10
  34. 2024Token Statistics Transformer: Linear-Time Attention via Variational Rate Reductioncited by 10
  35. 2022Softmax-free Linear Transformerscited by 9
  36. 2024Benchmarking GPT-4 on Algorithmic Problems: A Systematic Evaluation of Prompting Strategiescited by 9
  37. 2022Training Discrete Deep Generative Models via Gapped Straight-Through Estimatorcited by 8
  38. 2024IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUscited by 8

50 most cited of 129 All 129 (JSON)