Challenge: Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices.
Approach: They propose two methods that share parameters across attention heads to reduce memory usage and reduce performance drop by using coarse-grained weight sharing rules.
Outcome: The proposed methods reuse pre-trained weights without retraining and then share, denoted as PostShare.

Similar Papers

Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)

Copied to clipboard

Challenge: Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers.
Approach: They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights.
Outcome: The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers.
Does Self-Attention Need Separate Weights in Transformers? (2025.naacl-industry)

Copied to clipboard

Challenge: Experimental results show a 66.53% reduction in parameter size within the attention block and competitive accuracy improvements of 3.55% and 0.89% over symmetric and pairwise attention-based models, respectively.
Approach: They propose a simplified approach where a single weight matrix is used for Keys, Queries, and Values instead of separate matrices for each.
Outcome: The proposed approach outperforms the BERT baseline on GLUE tasks even outperforming the standard BERT model in handling noisy and out-of-domain data.
IAM: Efficient Inference through Attention Mapping between Different-scale LLMs (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are a challenge due to their internal reasoning processes.
Approach: They propose an algorithm that can optimize attention matrices by performing attention mapping between small and large LLMs.
Outcome: The proposed framework can reduce KV cache usage by 22.1% and accelerate prefill by 15% without sacrificing performance.
SharVeT: Similarity-aware Parameter Sharing with Vector-based Tuning for Efficient LLM Compression (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for parameter sharing rely on naive grouping and fail to correct sharing-induced discrepancies.
Approach: They propose a parameter sharing framework that performs similarity-based grouping to ensure accurate sharing and allocates parameters adaptively to preserve diversity within each group.
Outcome: The proposed framework outperforms existing methods, achieving 32.1% lower perplexity and 23.3% higher few-shot reasoning accuracy.
Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing pre-trained language models have produced performance gains in various tasks but come with large computational requirements.
Approach: They propose an alternative module that uses only a single shared projection matrix and multiple head embeddings (MHE) they demonstrate that MHE attention is substantially more memory efficient compared to alternative attention mechanisms.
Outcome: The proposed model is more memory efficient compared to the current model while achieving high retention ratio on several downstream tasks.
A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference (2025.naacl-short)

Copied to clipboard

Challenge: Recent studies have shown that sharing key-value (KV) cache across layers is effective in efficient inference of large language models.
Approach: They propose a unified framework that covers several recent methods and their novel variants to investigate cross-layer KV sharing.
Outcome: The proposed framework achieves higher throughput and better performance when reducing the size of the key-value cache by 2 while maintaining competitive performance.
LongHeads: Multi-Head Attention is Secretly a Long Context Processor (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models struggle to process lengthy inputs due to limited length generalization and attention’s quadratic computational demands.
Approach: They propose a training-free framework that allows each head to attend to important context chunks instead of allowing each head a full sentence .
Outcome: The proposed framework unlocks multi-head attention's untapped potential by allowing each head to attend to important context chunks instead of the full sentence.
ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Prior research has focused on optimizing general-purpose large language models to downstream tasks . however, these approaches inherently introduce data dependency, which hinders generalization and reusability.
Approach: They propose an algorithm that localizes the most task-sensitive attention heads and prunes by restricting attention training updates to these heads, thereby reducing alignment costs.
Outcome: The proposed algorithm achieves 2% performance improvement over baselines on three tasks while localizing the most task-sensitive attention heads.
Probing and Boosting Large Language Models Capabilities via Attention Heads (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to identifying capabilities rely on external signals with limited structural grounding . emergence of specific capabilities remains poorly understood .
Approach: They propose a lightweight approach that links LLM capabilities to internal components by identifying correspondences at the level of attention heads.
Outcome: The proposed approach improves accuracy on MMLU and BBH by 1 to 1.5 points over gradient-based method and 5 to 6 points over other intermediate-state baselines.
Efficient Sparse Attention needs Adaptive Token Release (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks, however, their ‘large’ scale introduces significant computational and storage challenges, particularly in managing the key-value states of the transformer, which limits their wider applicability.
Approach: They propose to release resources from caches and rebuild key-value states by a lightweight controller module to approximate an ideal top-K sparse attention.
Outcome: The proposed method achieves a significant throughput improvement of 221.8% over full attention and a model with 7 billion tokens.

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