SPE Attention: Making Attention Equivariant to Semantic-Preserving Permutation for Code Processing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to train code processing models to capture symmetry of code . semantic-preserving permutations are not found in natural languages . |
| Approach: | They propose a mechanism that captures a unique symmetry of code, called the SPE attention . they propose symmetry graphs that are then combined to create a symmetry mask . |
| Outcome: | The proposed model can be used to analyze code summarization and error detection tasks. |
Similar Papers
Symmetric Dot-Product Attention for Efficient Training of BERT Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Transformer-based models are stretched to enormous sizes, requiring increasingly larger training datasets and unsustainable amount of compute resources. |
| Approach: | They propose an alternative compatibility function for the Transformer-based attention mechanism that exploits an overlap in the learned representation of the traditional scaled dot-product attention mechanism. |
| Outcome: | The proposed model achieves 79.36 on the GLUE benchmark against 78.74 for the traditional implementation and reduces the number of trainable parameters by 6%. |
Chain and Causal Attention for Efficient Entity Tracking (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to handle entity tracking require at least log2 (n+1) layers to handle n state changes. |
| Approach: | They propose an efficient enhancement to the standard attention mechanism to handle long-term dependencies with a single layer. |
| Outcome: | The proposed model can handle entity tracking with n state changes with a single layer. |
SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that code retrievers exhibit a strong bias towards well-documented code . |
| Approach: | They propose a framework that augments textual information with semantic information to mask specific features while preserving code functionality. |
| Outcome: | The proposed framework enhances textual information and reduces bias by augmenting code or structural knowledge with semantic information. |
Attention Understands Semantic Relations (2022.lrec-1)
Copied to clipboard
| Challenge: | Present-day monopoly of foundation language models in most tasks forces researchers and practitioners to rely on popular large models without genuinely understanding the models' behaviour. |
| Approach: | They propose a probing pipeline to study the representedness of semantic relations in transformer language models and propose 'attention mechanisms' that focus on syntactic relational information and semantic one. |
| Outcome: | The proposed pipeline shows that attention scores are expressive as output activations on this task, despite their lesser ability to represent surface cues. |
EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention (2026.acl-long)
Copied to clipboard
Yifan Zhang, Chen Huang, Yueke Zhang, Jiahao Zhang, Toby Jia-Jun Li, Collin McMillan, Kevin Leach, Yu Huang
| Challenge: | Code Language Models learn attention based on statistical input-output token correlations. |
| Approach: | They propose a model-agnostic technique to align CodeLLM attention with human visual attention without architectural changes. |
| Outcome: | The proposed model outperforms baselines in three languages, with gains of over 30 CodeBLEU points in translation and up to 22 BERTScore points in summarization. |
Syntax-Based Attention Masking for Neural Machine Translation (2021.naacl-srw)
Copied to clipboard
| Challenge: | Existing approaches to extend transformers to source-side trees are linearized into sequences, but they are limited by positional encodings. |
| Approach: | They propose a method for extending transformers to source-side trees by using masks based on tree positions . they define a number of masks that limit self-attention based upon relationships among tree nodes . |
| Outcome: | The proposed method improves on translations from English to germany and English to english and germany by +2.1 BLEU. |
Selective Prefix Tuning for Pre-trained Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained models are time-consuming and memory-inefficient. |
| Approach: | They propose a method that inserts learnable vectors into each Transformer layer . they propose SL to encourage diversity in prefix tokens . |
| Outcome: | Extensive experiments validate the effectiveness of Prefix Tuning in sentence and token classification tasks. |
Data-Informed Global Sparseness in Attention Mechanisms for Deep Neural Networks (2024.lrec-main)
Copied to clipboard
| Challenge: | Attention pruning techniques have been developed to identify and exploit sparseness . previous work has taken pioneering steps to discover and explain the sparsity in attention patterns . |
| Approach: | They propose a framework that observes attention patterns in a fixed dataset and generates a global sparseness mask. |
| Outcome: | The proposed approach saves 90% of computations and maintains quality of results. |
Permutation Invariant Strategy Using Transformer Encoders for Table Understanding (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for encoding text in tables require additional training and require additional pretraining. |
| Approach: | They propose a novel encoding strategy that preserves the critical property of permutation invariance across rows or columns. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on three table interpretation tasks: column type annotation, relation extraction, and entity linking. |
Sparsifying Transformer Models with Trainable Representation Pooling (2022.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to sparsify attention in the Transformer model are based on quadratic memory complexity and a lack of information for each word. |
| Approach: | They propose a method to sparsify attention in a Transformer model by learning to select the most-informative token representations during the training process. |
| Outcome: | The proposed model performs better than the current SOTA model while being 1.8 faster during training, 4.5 faster inference and 13 more efficient in the decoder. |