Similarity-Distance-Magnitude Activations (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for interpreting neural network-based language models (LMs) are limited to approximately conditional quantities.
Approach: They introduce a similarity-distance-magnitude activation function and an SDM estimator to control class- and prediction-conditional accuracy among selective classifications.
Outcome: The proposed estimator is more robust to covariate shifts and out-of-distribution inputs while remaining informative over in-difference data.

Similar Papers

ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Activation sparsity is a promising paradigm for accelerating model inference . few large language models achieve high activation spar and comparable performance .
Approach: They propose a method to achieve activation sparsity and acceleration in large language models . they introduce ReLU activation and adopt progressive sparse regularization .
Outcome: The proposed method achieves high activation sparsity and comparable model performance.
IMPACT: Importance-Aware Activation Space Reconstruction (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) achieve strong performance across domains but remain difficult to deploy in resource-constrained environments due to their massive size.
Approach: They propose an importance-aware activation reconstruction framework that links compression to its effect on model performance.
Outcome: Experiments show that IMPACT reduces model size by 55.4% while maintaining accuracy comparable to or better than state-of-the-art models.
Activation Scaling for Steering and Interpreting Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: a successful intervention should flip the correct with the wrong token, while remaining sparse.
Approach: They propose to use activation scaling to flip the correct with the wrong token . they use gradient-based optimization to learn and evaluate a specific kind of efficient intervention .
Outcome: The proposed method performs comparable with steering vectors but is much less minimal.
Sparse Attention with Linear Units (2021.emnlp-main)

Copied to clipboard

Challenge: Recent studies have suggested that sparse attention mechanisms can be made more interpretable by replacing the softmax activation with its sparser variants.
Approach: They propose a method to replace softmax activation with a ReLU to achieve sparsity in attention by layer normalization with either a specialized initialization or an additional gating function.
Outcome: The proposed model is easy to implement and more efficient than previously proposed sparse attention mechanisms.
CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation (2025.emnlp-main)

Copied to clipboard

Challenge: Large foundation models have become huge, but they consume computational resources in pretraining.
Approach: They propose to replace full-size layers with compute-efficient auto-encoders that enforce low-rank activations throughout training.
Outcome: The proposed method reduces the computing cost by 2pmbtimes and improves training throughput by 1.86pmtime.
Self-Adjust Softmax (2025.emnlp-main)

Copied to clipboard

Challenge: Usually, tokens with larger attention scores are important for the final prediction.
Approach: They propose to modify softmax(z) to z softmax and its normalized variant to improve the Transformer attention mechanism by making minor adjustments to the softmax function.
Outcome: The proposed model provides enhanced gradient properties compared to the vanilla softmax function.
Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019) (D19-61)

Copied to clipboard

Challenge: EMNLP-IJCNLP 2019 Workshop on Deep Learning Approaches for Low-Resource Natural Language Processing takes place in Hong Kong, China .
Approach: EMNLP-IJCNLP 2019 Workshop on Deep Learning Approaches for Low-Resource Natural Language Processing takes place in Hong Kong, China . call for papers for this second workshop met with a strong response .
Outcome: the EMNLP-IJCNLP 2019 workshop on deep learning approaches for low-resource natural language processing takes place in Hong Kong, China.
Unveiling Multimodal Processing: Exploring Activation Patterns in Multimodal LLMs for Interpretability and Efficiency (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in multimodal large language models have remained opaque.
Approach: They propose a method to convert dense MLLMs into fine-grained Mixture-of-Experts architectures.
Outcome: The proposed method outperforms random expert pruning and sparse activation and model pruning.
Self-Supervised Document Similarity Ranking via Contextualized Language Models and Hierarchical Inference (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches to document-to-document similarity ranking are limited to relatively short documents or lack similarity labels.
Approach: They propose a self-supervised method for document similarity ranking that can be applied to documents of arbitrary length.
Outcome: The proposed model outperforms existing methods on large documents datasets.
Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to convert pretrained dense models to MoEs are limited to ReLU-based models with natural sparsity.
Approach: They propose a G-MoEfication approach for arbitrary dense models where activation sparsity assumptions no longer hold.
Outcome: The proposed method reduces the inference cost associated with dense models by sparsely activating experts.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations