Analyzing the Inner Workings of Transformers in Compositional Generalization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies on compositional generalization abilities of neural models have focused on benchmarks, but the results do not reflect the underlying competence of the model. |
| Approach: | They propose to find an existing subnetwork that contributes to the generalization performance and perform causal analyses on how the model utilizes syntactic features. |
| Outcome: | The proposed model relies on syntactic features but the subnetwork with better generalization performance relies mainly on a non-compositional algorithm . |
Similar Papers
Making Transformers Solve Compositional Tasks (2022.acl-long)
Copied to clipboard
| Challenge: | Several studies have reported the inability of Transformer models to generalize compositionally . a key aspect of natural language is the ability to learn basic primitives . |
| Approach: | They propose to use Transformers to generalize compositionally in a large range of tasks . they find that Transformers generalize significantly better than previous models . |
| Outcome: | The proposed models generalize compositionally significantly better than previous models . a set of 12 datasets shows that the proposed models can be improved . |
When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarks (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent benchmarks like ReaSCAN use navigation tasks grounded in a grid world to assess whether neural models exhibit compositional behaviour. |
| Approach: | They propose a transformer-based model that outperforms specialized architectures on ReaSCAN and a modified version of gSCAN to test their performance. |
| Outcome: | The proposed model outperforms specialized architectures on ReaSCAN and gSCAN on a grid world and can generalize to deeper input structures. |
The Impact of Depth on Compositional Generalization in Transformer Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | In this paper, we test the hypothesis that deeper transformers generalize more compositionally. |
| Approach: | They propose to add layers to transformers to generalize more compositionally . they propose to fine-tune the models so that the total number of parameters is constant . |
| Outcome: | The proposed model generalizes more compositionally than shallower models, but returns diminish . the proposed model can be made shallower without sacrificing performance . |
Improving Compositional Generalization in Classification Tasks via Structure Annotations (2021.acl-short)
Copied to clipboard
| Challenge: | Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. |
| Approach: | They propose to convert a natural language sequence-to-sequence dataset into a classification dataset that requires compositional generalization. |
| Outcome: | The proposed model can generalize compositionally by providing hints on the structure of the input. |
Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers (2025.tacl-1)
Copied to clipboard
Kabir Ahuja, Vidhisha Balachandran, Madhur Panwar, Tianxing He, Noah A. Smith, Navin Goyal, Yulia Tsvetkov
| Challenge: | Inductive biases in transformers can cause hierarchical generalization without explicitly encoding structural bias. |
| Approach: | They investigate sources of inductive bias in transformer models and their training that could cause such preference for hierarchical generalization. |
| Outcome: | The proposed model can generalize to novel syntactic forms without explicit bias . the proposed model is able to generalize on a dataset with a hierarchical grammar . |
Inducing Transformer’s Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing neural models lack systematic compositionality in learning symbolic structures . existing models lack this ability in learning symbols, despite being able to understand complex structures. |
| Approach: | They propose to use auxiliary sequence prediction tasks to train a Transformer model to understand compositional symbolic structures of input data. |
| Outcome: | The proposed model improves on the SCAN compositionality challenge, with only 418 (5%) training instances, and achieves 97.8% accuracy on the MCD1 split. |
Data Factors for Better Compositional Generalization (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent diagnostic datasets on compositional generalization expose severe problems . state-of-the-art models trained on larger and more general datasets show better generalization ability . |
| Approach: | They conduct an empirical analysis by training Transformer models on a variety of training sets with different data factors including dataset scale, pattern complexity, example difficulty, etc. |
| Outcome: | The proposed model training on larger datasets improves on compositional generalization tasks. |
Towards Understanding the Relationship between In-context Learning and Compositional Generalization (2024.lrec-main)
Copied to clipboard
| Challenge: | In-context learning is an inductive bias for compositional generalization, but many deep neural architectures struggle with this ability. |
| Approach: | They propose to force a causal Transformer to in-context learn to promote compositional generalization by using earlier examples to generalize to later ones. |
| Outcome: | The proposed model can solve 'ordinary' learning problems by utilizing earlier examples to generalize to later ones, i.e., in-context learning. |
The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that basic configurations can improve the performance of neural networks on systematic generalization. |
| Approach: | They propose to revisit basic configurations to improve the performance of Transformers on systematic generalization by revisiting scaling of embeddings, early stopping, relative positional embeddment, and Universal Transformer variants. |
| Outcome: | The proposed models improve accuracy from 50% to 85% on the PCFG productivity split and from 35% to 81% on COGS. |
Consistency Regularization Training for Compositional Generalization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing neural models have difficulty generalizing to unseen combinations of seen components. |
| Approach: | They propose to improve the capability of Transformer on compositional generalization by consistency regularization training without modifying model architectures. |
| Outcome: | The proposed model performs well on semantic parsing and machine translation benchmarks. |