ResMerge improves merging of RL expert LLMs via a stable residual consensus backbone plus gated head correction, outperforming task-vector and spectral baselines in capability preservation.
arXiv preprint arXiv:2311.03099 , doi =
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 10roles
baseline 1polarities
baseline 1representative citing papers
SAEs used for layer selection with raw task vectors outperform subspace projection and raise math reasoning accuracy on Gemma-3-4B-IT.
CapTrack shows post-training causes drift beyond facts, with instruction fine-tuning producing stronger behavioral changes than preference optimization across model families.
DG-Hard uses Donoho-Gavish hard thresholding on the fine-tuning weight delta to separate task-aligned signal from noise-like residual, recovering damaged capabilities while preserving target-task gains.
BAR trains independent domain experts via separate mid-training, SFT, and RL pipelines then composes them with a MoE router to match monolithic retraining performance at lower cost and without catastrophic forgetting.
Weight Patching localizes capabilities to specific parameter modules in LLMs by replacing weights from a behavior-specialized model into a base model and validating recovery via a vector-anchor interface, revealing a hierarchy of source, routing, and execution components.
HeteroFusion fuses heterogeneous LLMs via topology-based alignment and conflict-aware denoising, outperforming merging and ensemble baselines in cross-family and multi-source settings.
A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.
Data flow space model merging is formalized as a mixed binary-continuous black-box optimization problem, where a structured approach respecting variable dependencies achieves 6.7% higher accuracy and 51.4% smaller search space than unstructured methods on real language models.
SoTU merges sparse orthogonal delta parameters learned across streaming tasks to fuse knowledge and mitigate forgetting in pre-trained model continual learning.
citing papers explorer
-
ResMerge: Residual-based Spectral Merging of Large Language Models
ResMerge improves merging of RL expert LLMs via a stable residual consensus backbone plus gated head correction, outperforming task-vector and spectral baselines in capability preservation.
-
Interpretability-Guided Layer Selection over Subspace Projection: SAEs as Stethoscopes, Not Scalpels, for Raw Task Vector Model Editing
SAEs used for layer selection with raw task vectors outperform subspace projection and raise math reasoning accuracy on Gemma-3-4B-IT.
-
CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
CapTrack shows post-training causes drift beyond facts, with instruction fine-tuning producing stronger behavioral changes than preference optimization across model families.
-
Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining
DG-Hard uses Donoho-Gavish hard thresholding on the fine-tuning weight delta to separate task-aligned signal from noise-like residual, recovering damaged capabilities while preserving target-task gains.
-
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts
BAR trains independent domain experts via separate mid-training, SFT, and RL pipelines then composes them with a MoE router to match monolithic retraining performance at lower cost and without catastrophic forgetting.
-
Weight Patching: Toward Source-Level Mechanistic Localization in LLMs
Weight Patching localizes capabilities to specific parameter modules in LLMs by replacing weights from a behavior-specialized model into a base model and validating recovery via a vector-anchor interface, revealing a hierarchy of source, routing, and execution components.
-
Can Heterogeneous Language Models Be Fused?
HeteroFusion fuses heterogeneous LLMs via topology-based alignment and conflict-aware denoising, outperforming merging and ensemble baselines in cross-family and multi-source settings.
-
Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting
A plug-and-play KL regularizer that masks the target token and renormalizes probabilities to improve the learning-forgetting trade-off in LoRA adaptation of LLMs.
-
Black-Box Optimization of Mixed Binary-Continuous Variables: Challenges and Opportunities in Evolutionary Model Merging
Data flow space model merging is formalized as a mixed binary-continuous black-box optimization problem, where a structured approach respecting variable dependencies achieves 6.7% higher accuracy and 51.4% smaller search space than unstructured methods on real language models.
-
Sparse Orthogonal Parameters Tuning for Continual Learning
SoTU merges sparse orthogonal delta parameters learned across streaming tasks to fuse knowledge and mitigate forgetting in pre-trained model continual learning.