Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model

• URL: http://arxiv.org/abs/2404.10306v4
• Date: Mon, 3 Jun 2024 10:42:36 GMT
• Title: Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model
• Authors: Hengyuan Zhang, Yanru Wu, Dawei Li, Sak Yang, Rui Zhao, Yong Jiang, Fei Tan,
• Abstract summary: Aligned Large Language Models (LLMs) showcase remarkable versatility, capable of handling diverse real-world tasks. Fine-tuning with extra data, a common practice to gain speciality, often leads to catastrophic forgetting of previously acquired versatility. We propose CoFiTune, a coarse to fine framework in an attempt to strike the balance between speciality and versatility.
• Score: 25.54822836846494
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aligned Large Language Models (LLMs) showcase remarkable versatility, capable of handling diverse real-world tasks. Meanwhile, aligned LLMs are also expected to exhibit speciality, excelling in specific applications. However, fine-tuning with extra data, a common practice to gain speciality, often leads to catastrophic forgetting (CF) of previously acquired versatility, hindering the model's performance across diverse tasks. In response to this challenge, we propose CoFiTune, a coarse to fine framework in an attempt to strike the balance between speciality and versatility. At the coarse-grained level, an empirical tree-search algorithm is utilized to pinpoint and update specific modules that are crucial for speciality, while keeping other parameters frozen; at the fine-grained level, a soft-masking mechanism regulates the update to the LLMs, mitigating the CF issue without harming speciality. In an overall evaluation of both speciality and versatility, CoFiTune consistently outperforms baseline methods across diverse tasks and model scales. Compared to the full-parameter SFT, CoFiTune leads to about 14% versatility improvement and marginal speciality loss on a 13B model. Lastly, based on further analysis, we provide a speculative insight into the information forwarding process in LLMs, which helps explain the effectiveness of the proposed method. The code is available at https://github.com/rattlesnakey/CoFiTune.

Related papers

• Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution [37.437830302067326]
  Sparsity Evolution Fine-Tuning (SEFT) is a novel method designed specifically for sparse large language models (LLMs)<n>SEFT dynamically evolves the sparse topology of pruned models during fine-tuning, while preserving the overall sparsity throughout the process.<n>Our experiments on various LLMs demonstrate that SEFT achieves stronger performance while offering superior memory and time efficiency compared to existing baselines.
  arXiv  Detail & Related papers  (2025-05-29T22:17:43Z)
• CoLA: Collaborative Low-Rank Adaptation [3.421904493396495]
  Fine-tuning a pre-trained model for specific tasks achieves strong performance; however, it is computationally expensive and inefficient.<n>LoRA, in particular, has proven effective, but its application to multi-task scenarios is limited by interference between tasks.<n>We propose CoLA, a more flexible LoRA architecture and three collaborative strategies to enhance performance by better utilizing the quantitative relationships between $A$ and $B$.
  arXiv  Detail & Related papers  (2025-05-21T12:46:42Z)
• Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization [66.10528870853324]
  Fusing and balancing multi-modal inputs from novel sensors for dense prediction tasks is critically important.<n>One major limitation is the tendency of multi-modal frameworks to over-rely on easily learnable modalities.<n>We propose a plug-and-play regularization term based on functional entropy, which introduces no additional parameters.
  arXiv  Detail & Related papers  (2025-05-10T12:58:15Z)
• Boosting Large Language Models with Mask Fine-Tuning [60.56962908455601]
  We introduce Mask Fine-Tuning (MFT) to show that properly breaking the integrity of the model can surprisingly lead to improved performance. Experiments show that MFT gains a consistent performance boost across various domains and backbones.
  arXiv  Detail & Related papers  (2025-03-27T20:17:57Z)
• UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality [52.49062565901046]
  Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone for aligning large language models with human values.<n>Existing approaches struggle to capture the multi-dimensional, distributional nuances of human preferences.<n>We introduce Utility-Conditioned Multi-Objective Alignment (UC-MOA), a novel framework that overcomes these limitations.
  arXiv  Detail & Related papers  (2025-03-10T09:52:42Z)
• How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization [15.434072331989878]
  Large Language Models (LLMs) exhibit strong general language capabilities. Fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired during pretraining. We propose a novel approach to compute the element-wise importance of model parameters crucial for preserving general knowledge during fine-tuning.
  arXiv  Detail & Related papers  (2025-01-23T13:54:53Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications. Ensuring their alignment with the diverse preferences of individual users has become a critical challenge. We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Unified Parameter-Efficient Unlearning for LLMs [25.195126838721492]
  Large Language Models (LLMs) have revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks. This raises significant privacy and security concerns, as models may inadvertently retain and disseminate sensitive or undesirable information. We introduce a novel instance-wise unlearning framework, LLMEraser, which systematically categorizes unlearning tasks and applies precise adjustments using influence functions.
  arXiv  Detail & Related papers  (2024-11-30T07:21:02Z)
• Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning [104.27224674122313]
  Fine-tuning MLLM has become a common practice to improve performance on specific downstream tasks. To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions.
  arXiv  Detail & Related papers  (2024-11-17T01:16:37Z)
• Is Multiple Object Tracking a Matter of Specialization? [33.59920084936913]
  Training end-to-end transformer-based trackers in heterogeneous scenarios poses significant challenges. We introduce. The Scenario-specific Tracking Architecture (PASTA), a novel framework that combines. Efficient Fine-Tuning (PEFT) and Modular Deep Learning.
  arXiv  Detail & Related papers  (2024-11-01T13:03:58Z)
• The Perfect Blend: Redefining RLHF with Mixture of Judges [68.58426626501883]
  Reinforcement learning from human feedback (RLHF) has become the leading approach for fine-tuning large language models (LLM) Applying RLHF for MTL currently requires careful tuning of the weights for reward model and data combinations. We introduce a novel post-training paradigm which we called Constrained Generative Policy Optimization (CGPO)
  arXiv  Detail & Related papers  (2024-09-30T15:06:53Z)
• LLM-enhanced Reranking in Recommender Systems [49.969932092129305]
  Reranking is a critical component in recommender systems, playing an essential role in refining the output of recommendation algorithms. We introduce a comprehensive reranking framework, designed to seamlessly integrate various reranking criteria. A customizable input mechanism is also integrated, enabling the tuning of the language model's focus to meet specific reranking needs.
  arXiv  Detail & Related papers  (2024-06-18T09:29:18Z)
• Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models [45.51085356985464]
  Large language models (LLMs) are typically fine-tuned on diverse and extensive datasets sourced from various origins. MoS learns to optimize data usage automatically during the fine-tuning process. MoSpec harnesses the utilities of various datasets for a specific purpose.
  arXiv  Detail & Related papers  (2024-06-13T05:01:28Z)
• Intuition-aware Mixture-of-Rank-1-Experts for Parameter Efficient Finetuning [50.73666458313015]
  Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications. MoE has been emerged as a promising solution with its sparse architecture for effective task decoupling. Intuition-MoR1E achieves superior efficiency and 2.15% overall accuracy improvement across 14 public datasets.
  arXiv  Detail & Related papers  (2024-04-13T12:14:58Z)
• Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks [5.536630285985836]
  We introduce parameter-efficient sparsity crafting (PESC) PESC crafts dense models into sparse models using the mixture-of-experts (MoE) architecture. Our best sparse model outperforms other sparse and dense models and exhibits superior general capabilities compared to GP3.5.
  arXiv  Detail & Related papers  (2024-01-05T09:58:09Z)
• Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts [74.40198929049959]
  Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks. generalist LMMs often suffer from performance degradation when tuned over a large collection of tasks. We propose Omni-SMoLA, an architecture that uses the Soft MoE approach to mix many multimodal low rank experts.
  arXiv  Detail & Related papers  (2023-12-01T23:04:27Z)
• MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning [28.12788291168137]
  We present a multi-task fine-tuning framework, MFTcoder, that enables simultaneous and parallel fine-tuning on multiple tasks. Experiments have conclusively demonstrated that our multi-task fine-tuning approach outperforms both individual fine-tuning on single tasks and fine-tuning on a mixed ensemble of tasks.
  arXiv  Detail & Related papers  (2023-11-04T02:22:40Z)
• When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications [57.342772288710044]
  We propose a novel parameter efficient fine-tuning framework for multi-task medical applications, dubbed as MOELoRA. For unifying MOE and LoRA, we devise multiple experts as the trainable parameters, where each expert consists of a pair of low-rank matrices to retain the small size of trainable parameters. We conduct experiments on a multi-task medical dataset, indicating MOELoRA outperforms the existing parameter efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2023-10-21T17:18:09Z)
• SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models [28.764782216513037]
  Federated Learning (FL) can benefit from distributed and private data of the FL edge clients for fine-tuning. We propose a method called SLoRA, which overcomes the key limitations of LoRA in high heterogeneous data scenarios. Our experimental results demonstrate that SLoRA achieves performance comparable to full fine-tuning.
  arXiv  Detail & Related papers  (2023-08-12T10:33:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.