Superpose Task-specific Features for Model Merging (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for model merging are limited by resource demands . recent studies validate the linear representation hypothesis .
Approach: They propose a method that superposes task-specific features from individual models into a merged model.
Outcome: The proposed method outperforms existing methods on multiple benchmarks and models.

Similar Papers

To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Merging (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to model merging ignore the fundamental roles of neurons, connectivity and activation.
Approach: They propose a framework that relies on neuronal mechanisms to mitigate task interference . they decomposed task-specific representations into two complementary subspaces . their results offer new insights into mitigating task interference and improving knowledge fusion .
Outcome: The proposed framework reduces task interference within neurons and improves knowledge fusion.
NeuronMerge: Merging Models via Functional Neuron Groups (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies show that task arithmetic improves performance by combining model parameters with output features.
Approach: They propose a neuron-based task arithmetic merging method that improves model linearity . they group neurons by function and propose combining them with existing models .
Outcome: The proposed method improves performance across tasks and scales.
PRIME: Ultra-Low-Rank Principal–Residual Model Merging (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for model merging have been limited by task-specific performance and task-related tasks.
Approach: They propose an ultra-low-rank principal-residual model merging framework that decomposes task vector merging into two stages.
Outcome: Experiments on eight natural language processing tasks show that PRIME outperforms existing models while preserving the task-specific capabilities of the original models.
Training-free LLM Merging for Multi-task Learning (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing tasks.
Approach: They propose a training-free method for unifying different specialized LLMs into a single model using model-wise and layer-wise pruning and scaling.
Outcome: The proposed method outperforms existing merging techniques and surpasses models fine-tuned on combined datasets in most scenarios.
DivMerge: A divergence-based model merging method for multi-tasking (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods for multitask learning struggle with interference between tasks, especially as the number of tasks grows.
Approach: They propose a reference-free method that minimizes the divergence between models' outputs and those of the merged model, automatically balancing task importance.
Outcome: The proposed method outperforms existing methods on classification and generative tasks and remains robust when scaling to more tasks.
LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging (2025.findings-emnlp)

Copied to clipboard

Challenge: a framework for model merging is proposed without additional training . task vectors from fine-tuned models exhibit a limited number of dominant singular values .
Approach: They propose a framework for model merging based on low-rank estimation of task vectors without access to the base model.
Outcome: The proposed framework improves models without additional training without additional inputs.
Unraveling Feature Extraction Mechanisms in Neural Networks (2023.emnlp-main)

Copied to clipboard

Challenge: Neural networks have become indispensable across a variety of natural language processing tasks.
Approach: They propose a theoretical approach based on Neural Tangent Kernels to investigate neural networks' internal mechanisms.
Outcome: The proposed approach can be applied to analyze language modeling tasks . it shows that the choice of activation function can affect feature extraction .
Exploiting Deep Representations for Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: Neural machine translation models typically implement encoder and decoder as multiple layers, but only the top layers are leveraged in the subsequent process, which misses the opportunity to exploit useful information embedded in other layers.
Approach: They propose to expose all of these signals with layer aggregation and multi-layer attention mechanisms and introduce an auxiliary regularization term to encourage different layers to capture diverse information.
Outcome: The proposed approach exposes all of these signals with layer aggregation and multi-layer attention mechanisms on widely-used translation datasets.
Will it Merge? On The Causes of Model Mergeability (2026.findings-acl)

Copied to clipboard

Challenge: Model merging has emerged as a promising technique for combining fine-tuned models into a single expert model without retraining.
Approach: They propose a model merging technique that preserves weak model knowledge . they define mergeability as a property of model updates that captures how well they retain trained knowledge when merged with other model updates.
Outcome: The proposed method preserves weak knowledge in the base model.
Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond (2024.findings-acl)

Copied to clipboard

Challenge: Existing task embedding methods rely on fine-tuned, task-specific language models, which hinders their adaptability to prompt-guided Large Language Models (LLMs).
Approach: They propose a framework for unified task embedding that harmonizes task embeds from various models within a single vector space.
Outcome: The proposed framework harmonizes task embeddings from various models within a single vector space.

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