APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training

• URL: http://arxiv.org/abs/2506.03483v1
• Date: Wed, 04 Jun 2025 01:46:38 GMT
• Title: APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training
• Authors: Jun Rao, Zepeng Lin, Xuebo Liu, Xiaopeng Ke, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang,
• Abstract summary: Large Language Models (LLMs) often require domain-specific fine-tuning to address targeted tasks.<n>Maintaining a balance between domain-specific enhancements and general model utility is a key challenge.<n>This paper proposes a novel approach named APT to enhance domain-specific performance with self-generated dis-preferred weakness data.
• Score: 21.570482838147225
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities. Maintaining a balance between domain-specific enhancements and general model utility is a key challenge. This paper proposes a novel approach named APT (Weakness Case Acquisition and Iterative Preference Training) to enhance domain-specific performance with self-generated dis-preferred weakness data (bad cases and similar cases). APT uniquely focuses on training the model using only those samples where errors occur, alongside a small, similar set of samples retrieved for this purpose. This targeted training minimizes interference with the model's existing knowledge base, effectively retaining generic capabilities. Experimental results on the LLama-2 and Mistral-V0.3 models across various benchmarks demonstrate that APT ensures no reduction in generic capacity and achieves superior performance on downstream tasks compared to various existing methods. This validates our method as an effective strategy for enhancing domain-specific capabilities without sacrificing the model's broader applicability.

Related papers

• Fake it till You Make it: Reward Modeling as Discriminative Prediction [49.31309674007382]
  GAN-RM is an efficient reward modeling framework that eliminates manual preference annotation and explicit quality dimension engineering.<n>Our method trains the reward model through discrimination between a small set of representative, unpaired target samples.<n>Experiments demonstrate our GAN-RM's effectiveness across multiple key applications.
  arXiv  Detail & Related papers  (2025-06-16T17:59:40Z)
• MAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models [30.04163729936878]
  Meticulous Adrial Attack (MAA) fully exploit model-independent characteristics and vulnerabilities of individual samples.<n>MAA emphasizes fine-grained optimization of adversarial images by developing a novel resizing and sliding crop (RScrop) technique.
  arXiv  Detail & Related papers  (2025-02-12T02:53:27Z)
• BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping [64.8477128397529]
  We propose a training-required and training-free test-time adaptation framework. We maintain a light-weight key-value memory for feature retrieval from instance-agnostic historical samples and instance-aware boosting samples. We theoretically justify the rationality behind our method and empirically verify its effectiveness on both the out-of-distribution and the cross-domain datasets.
  arXiv  Detail & Related papers  (2024-10-20T15:58:43Z)
• MITA: Bridging the Gap between Model and Data for Test-time Adaptation [68.62509948690698]
  Test-Time Adaptation (TTA) has emerged as a promising paradigm for enhancing the generalizability of models. We propose Meet-In-The-Middle based MITA, which introduces energy-based optimization to encourage mutual adaptation of the model and data from opposing directions.
  arXiv  Detail & Related papers  (2024-10-12T07:02:33Z)
• Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning [78.72226641279863]
  Sparse Mixture of Expert (SMoE) models have emerged as a scalable alternative to dense models in language modeling. Our research explores task-specific model pruning to inform decisions about designing SMoE architectures. We introduce an adaptive task-aware pruning technique UNCURL to reduce the number of experts per MoE layer in an offline manner post-training.
  arXiv  Detail & Related papers  (2024-09-02T22:35:03Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Feature Protection For Out-of-distribution Generalization [24.072876186625855]
  We show that protecting pre-trained features leads to a fine-tuned model more robust to generalization. We show that protecting pre-trained features leads to a fine-tuned model more robust to OOD generalization.
  arXiv  Detail & Related papers  (2024-05-25T03:00:06Z)
• Universal Adversarial Perturbations for Vision-Language Pre-trained Models [30.04163729936878]
  We propose a novel black-box method to generate Universal Adversarial Perturbations (UAPs) The ETU takes into account the characteristics of UAPs and the intrinsic cross-modal interactions to generate effective UAPs. To further enhance the effectiveness and transferability of UAPs, we also design a novel data augmentation method named ScMix.
  arXiv  Detail & Related papers  (2024-05-09T03:27:28Z)
• Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReID [39.98444065846305]
  ReID models struggle in learning domain-invariant representation solely through training on an instance classification objective. We introduce a method that guides model learning of the primary ReID instance classification objective by a concurrent auxiliary learning objective on weakly labeled pedestrian saliency detection. Our model can be extended with the recent test-time diagram to form the PAOA+, which performs on-the-fly optimization against the auxiliary objective.
  arXiv  Detail & Related papers  (2023-10-24T15:15:57Z)
• Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification [0.0]
  This paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. We put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.
  arXiv  Detail & Related papers  (2022-01-25T10:10:48Z)
• Adversarial Distributional Training for Robust Deep Learning [53.300984501078126]
  Adversarial training (AT) is among the most effective techniques to improve model robustness by augmenting training data with adversarial examples. Most existing AT methods adopt a specific attack to craft adversarial examples, leading to the unreliable robustness against other unseen attacks. In this paper, we introduce adversarial distributional training (ADT), a novel framework for learning robust models.
  arXiv  Detail & Related papers  (2020-02-14T12:36:59Z)

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.