# Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance

arXiv: https://arxiv.org/abs/2508.21741 · HTML: https://mlsanity.com/paper/2508.21741/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 78 references that are in the map.
- First posted on arXiv 29 Aug 2025.

## Builds on (most cited first, 30 of 43)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks](https://mlsanity.com/paper/1711.02257/) (2017)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning](https://mlsanity.com/paper/1412.6614/) (2014)
- [Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning](https://mlsanity.com/paper/2010.15875/) (2020)
- [Arcee's MergeKit: A Toolkit for Merging Large Language Models](https://mlsanity.com/paper/2403.13257/) (2024)
- [ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning](https://mlsanity.com/paper/2111.10952/) (2021)
- [Continual Learning for Large Language Models: A Survey](https://mlsanity.com/paper/2402.01364/) (2024)

## Built on by (most cited first, 13 of 13)

- [Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling](https://mlsanity.com/paper/2509.25361/) (2025)
- [StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching](https://mlsanity.com/paper/2509.02033/) (2025)
- [Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models](https://mlsanity.com/paper/2604.10079/) (2026)
- [DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF](https://mlsanity.com/paper/2511.19097/) (2025)
- [Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty](https://mlsanity.com/paper/2604.10072/) (2026)
- [DPI: Exploiting Parameter Heterogeneity for Interference-Free Fine-Tuning](https://mlsanity.com/paper/2601.17777/) (2026)
- [Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answering](https://mlsanity.com/paper/2601.01195/) (2026)
- [Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning](https://mlsanity.com/paper/2604.14010/) (2026)
- [Tiny Brains, Giant Impact: Uncovering the Keystone Neurons of LLM with Just a Few Prompts](https://mlsanity.com/paper/2605.24846/) (2026)
- [Tag-Enriched Multi-Attention with Large Language Models for Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2510.09224/) (2025)
- [Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering](https://mlsanity.com/paper/2602.19569/) (2026)
- [Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization](https://mlsanity.com/paper/2604.17051/) (2026)
- [Multi-Granularity Reasoning for Natural Language Inference](https://mlsanity.com/paper/2606.05181/) (2026)

## Abstract (arXiv)

Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the ``seesaw phenomenon'', where indiscriminate parameter updates yield progress on certain tasks at the expense of others. To address this challenge, we propose a novel Core Parameter Isolation Fine-Tuning (CPI-FT) framework. Specifically, we first independently fine-tune the LLM on each task to identify its core parameter regions by quantifying parameter update magnitudes. Tasks with similar core regions are then grouped based on region overlap, forming clusters for joint modeling. We further introduce a parameter fusion technique: for each task, core parameters from its individually fine-tuned model are directly transplanted into a unified backbone, while non-core parameters from different tasks are smoothly integrated via Spherical Linear Interpolation (SLERP), mitigating destructive interference. A lightweight, pipelined SFT training phase using mixed-task data is subsequently employed, while freezing core regions from prior tasks to prevent catastrophic forgetting. Extensive experiments on multiple public benchmarks demonstrate that our approach significantly alleviates task interference and forgetting, consistently outperforming vanilla multi-task and multi-stage fine-tuning baselines.