UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function

• URL: http://arxiv.org/abs/2410.21438v1
• Date: Mon, 28 Oct 2024 18:34:25 GMT
• Title: UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function
• Authors: Zhichao Wang, Bin Bi, Zixu Zhu, Xiangbo Mao, Jun Wang, Shiyu Wang,
• Abstract summary: We introduce Unified Fine-Tuning (UFT), which integrates SFT and alignment into a single training stage. Our experimental results demonstrate that UFT outperforms SFT on instruction-tuning data alone. When combining instruction-tuning data with alignment data, UFT effectively prevents catastrophic forgetting.
• Score: 18.54945183526789
• License:
• Abstract: By pretraining on trillions of tokens, an LLM gains the capability of text generation. However, to enhance its utility and reduce potential harm, SFT and alignment are applied sequentially to the pretrained model. Due to the differing nature and objective functions of SFT and alignment, catastrophic forgetting has become a significant issue. To address this, we introduce Unified Fine-Tuning (UFT), which integrates SFT and alignment into a single training stage using the same objective and loss functions through an implicit reward function. Our experimental results demonstrate that UFT outperforms SFT on instruction-tuning data alone. Moreover, when combining instruction-tuning data with alignment data, UFT effectively prevents catastrophic forgetting across these two stages and shows a clear advantage over sequentially applying SFT and alignment. This is evident in the significant improvements observed in the \textbf{ifeval} task for instruction-following and the \textbf{truthful-qa} task for factuality. The proposed general fine-tuning framework UFT establishes an effective and efficient pretraining-UFT paradigm for LLM training.

Related papers

• Natural Language Fine-Tuning [13.143016409660484]
  We introduce Natural Language Fine-Tuning (NLFT), which utilizes natural language for fine-tuning for the first time. Since linguistic information is effectively utilized in NLFT, our proposed method significantly reduces training costs. It markedly enhances training efficiency, comprehensively outperforming reinforcement fine-tuning algorithms in accuracy, time-saving, and resource conservation.
  arXiv  Detail & Related papers  (2024-12-29T07:02:45Z)
• Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models [12.500777267361102]
  We introduce a novel textbfpreference-textbforiented supervised textbffine-textbftuning approach, namely PoFT. The intuition is to boost SFT by imposing a particular preference: textitfavoring the target model over aligned LLMs on the same SFT data. PoFT achieves stable and consistent improvements over the SFT baselines across different training datasets and base models.
  arXiv  Detail & Related papers  (2024-12-17T12:49:14Z)
• Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves [123.07450481623124]
  We propose Skip Tuning as a novel paradigm for adapting vision-language models to downstream tasks. Unlike existing PT or adapter-based methods, Skip Tuning applies Layer-wise Skipping (LSkip) and Class-wise Skipping (CSkip) upon the FT baseline without introducing extra context vectors or adapter modules.
  arXiv  Detail & Related papers  (2024-12-16T07:33:23Z)
• PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning [17.73193523921637]
  Large language models (LLMs) have shown remarkable abilities in diverse natural language processing (NLP) tasks. LLMs generally undergo supervised fine-tuning (SFT) followed by preference alignment to be usable in downstream applications. This paper introduces PAFT, a new PArallel training paradigm for effective LLM Fine-Tuning.
  arXiv  Detail & Related papers  (2024-06-25T20:11:37Z)
• Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process [26.196705232699884]
  We introduce Intuitive Fine-Tuning (IFT) to integrate SFT and Preference Optimization into a single process. IFT performs comparably or even superiorly to sequential recipes of SFT and some typical Preference Optimization methods. An explainable Frozen Lake game further validates the effectiveness of IFT for getting competitive policy.
  arXiv  Detail & Related papers  (2024-05-20T08:23:28Z)
• HFT: Half Fine-Tuning for Large Language Models [42.60438623804577]
  Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities. In this paper, we find that by regularly resetting partial parameters, LLMs can restore some of the original knowledge. We introduce Half Fine-Tuning (HFT) for LLMs, as a substitute for full fine-tuning (FFT), to mitigate the forgetting issues.
  arXiv  Detail & Related papers  (2024-04-29T07:07:58Z)
• Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model [50.339632513018934]
  supervised fine-tuning (SFT) has been a straightforward approach for tailoring the output of foundation large language model (LLM) to specific preferences. We critically examine this hypothesis within the scope of cross-lingual generation tasks. We introduce a novel training-free alignment method named PreTTY, which employs minimal task-related prior tokens.
  arXiv  Detail & Related papers  (2024-04-25T17:19:36Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment [105.34140537748546]
  We propose an improved alignment approach named FIGA. Different from prior methods, we incorporate fine-grained quality signals that are derived by contrasting good and bad responses. Our approach has made two major contributions. Firstly, we curate a refined alignment dataset that pairs initial responses and the corresponding revised ones. Secondly, we devise a new loss function can leverage fine-grained quality signals to instruct the learning of LLMs for alignment.
  arXiv  Detail & Related papers  (2023-11-07T15:36:40Z)
• FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning [70.38817963253034]
  This paper first discusses these challenges of federated fine-tuning LLMs, and introduces our package FS-LLM as a main contribution. We provide comprehensive federated parameter-efficient fine-tuning algorithm implementations and versatile programming interfaces for future extension in FL scenarios. We conduct extensive experiments to validate the effectiveness of FS-LLM and benchmark advanced LLMs with state-of-the-art parameter-efficient fine-tuning algorithms in FL settings.
  arXiv  Detail & Related papers  (2023-09-01T09:40:36Z)
• Instruction Tuning for Large Language Models: A Survey [52.86322823501338]
  We make a systematic review of the literature, including the general methodology of supervised fine-tuning (SFT) We also review the potential pitfalls of SFT along with criticism against it, along with efforts pointing out current deficiencies of existing strategies.
  arXiv  Detail & Related papers  (2023-08-21T15:35:16Z)

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.