Compressing Language Models for Specialized Domains

• URL: http://arxiv.org/abs/2502.18424v1
• Date: Tue, 25 Feb 2025 18:20:00 GMT
• Title: Compressing Language Models for Specialized Domains
• Abstract summary: General-purpose compression methods can negatively affect performance in specialized domains.<n>We propose cross-calibration, a novel training-free approach for improving the domain performance of compressed LMs.
• Score: 34.786926062666176
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compression techniques such as pruning and quantization offer a solution for more efficient deployment of language models (LMs), albeit with small performance drops in benchmark performance. However, general-purpose LM compression methods can negatively affect performance in specialized domains (e.g. biomedical or legal). Recent work has sought to address this, yet requires computationally expensive full-parameter fine-tuning. To this end, we propose cross-calibration, a novel training-free approach for improving the domain performance of compressed LMs. Our approach effectively leverages Hessian-based sensitivity to identify weights that are influential for both in-domain and general performance. Through extensive experimentation, we demonstrate that cross-calibration substantially outperforms existing approaches on domain-specific tasks, without compromising general performance. Notably, these gains come without additional computational overhead, displaying remarkable potential towards extracting domain-specialized compressed models from general-purpose LMs.

Related papers

• Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting [63.86964530167364]
  This paper presents a Bayesian domain weighting method to infer the weights from a Dirichlet distribution via introducing Gamma prior information learned from observations.<n> Experimental results demonstrate that proposed method could achieve stable and efficient domain weights learning, and identifies optimal mixtures while consuming substantially less data than search-based function-fitting methods, revitalizing optimization-based domain weighting for large-scale applications.
  arXiv  Detail & Related papers  (2026-07-30T09:41:02Z)
• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Gradually Compacting Large Language Models for Reasoning Like a Boiling Frog [72.4168434368873]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources.<n>We propose a gradual compacting method that divides the compression process into multiple fine-grained iterations.<n>This iterative approach-reminiscent of the "boiling frog" effect-enables the model to be progressively compressed without abrupt performance loss.
  arXiv  Detail & Related papers  (2026-02-04T06:56:52Z)
• EfficientXpert: Efficient Domain Adaptation for Large Language Models via Propagation-Aware Pruning [0.19116784879310023]
  EfficientXpert is a lightweight domain-pruning framework that combines a propagation-aware pruning criterion and an efficient adapter-update algorithm.<n>It enables a one-step transformation of general pretrained models into sparse, domain-adapted experts.<n>It retains up to 98% of dense-model performance at 40% sparsity, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-11-25T05:20:17Z)
• Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimation [13.83897333268682]
  Spacecraft Pose Estimation is a fundamental capability for autonomous space operations such as rendezvous, docking, and in-orbit docking.<n>Existing domain adaptation approaches aim to mitigate this issue but often underperform when a modest number of labeled target samples are available.<n>We propose the first Supervised Domain Adaptation (SDA) framework tailored for SPE keypoint regression.
  arXiv  Detail & Related papers  (2025-09-17T08:03:05Z)
• Unified modality separation: A vision-language framework for unsupervised domain adaptation [60.8391821117794]
  Unsupervised domain adaptation (UDA) enables models trained on a labeled source domain to handle new unlabeled domains.<n>We propose a unified modality separation framework that accommodates both modality-specific and modality-invariant components.<n>Our methods achieve up to 9% performance gain with 9 times of computational efficiencies.
  arXiv  Detail & Related papers  (2025-08-07T02:51:10Z)
• Heterogeneous User Modeling for LLM-based Recommendation [70.52873882470328]
  A key challenge to advancing open-domain recommendation is effectively modeling user preferences from users' heterogeneous behaviors.<n>Existing approaches, including ID-based and semantic-based modeling, struggle with poor generalization.<n>We propose a Heterogeneous User Modeling (HUM) method, which incorporates a compression enhancer and a robustness enhancer for LLM-based recommendation.
  arXiv  Detail & Related papers  (2025-07-07T03:08:28Z)
• Perception-Oriented Latent Coding for High-Performance Compressed Domain Semantic Inference [30.78149130760627]
  Perception-Oriented Latent Coding (POLC) is an approach that enriches the semantic content of latent features for high-performance semantic inference.<n>POLC requires only a plug-and-play adapter for fine-tuning, significantly reducing the parameter count compared to previous MSE-oriented methods.
  arXiv  Detail & Related papers  (2025-07-02T11:21:38Z)
• DIDS: Domain Impact-aware Data Sampling for Large Language Model Training [61.10643823069603]
  We present Domain Impact-aware Data Sampling (DIDS) for large language models.<n>DIDS group training data based on learning effects, where a proxy language model and dimensionality reduction are employed.<n>It achieves 3.4% higher average performance while maintaining comparable training efficiency.
  arXiv  Detail & Related papers  (2025-04-17T13:09:38Z)
• Advancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic Data [3.877325424485755]
  This report investigates enhancing semantic caching effectiveness by employing specialized, fine-tuned embedding models. We propose leveraging smaller, domain-specific embedding models, fine-tuned with targeted real-world and synthetically generated datasets.
  arXiv  Detail & Related papers  (2025-04-03T04:27:02Z)
• DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization [61.492590008258986]
  Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. We propose DRPruning, which incorporates distributionally robust optimization to restore balanced performance across domains.
  arXiv  Detail & Related papers  (2024-11-21T12:02:39Z)
• Sample-efficient Bayesian Optimisation Using Known Invariances [56.34916328814857]
  We show that vanilla and constrained BO algorithms are inefficient when optimising invariant objectives. We derive a bound on the maximum information gain of these invariant kernels. We use our method to design a current drive system for a nuclear fusion reactor, finding a high-performance solution.
  arXiv  Detail & Related papers  (2024-10-22T12:51:46Z)
• QT-DoG: Quantization-aware Training for Domain Generalization [58.439816306817306]
  We propose Quantization-aware Training for Domain Generalization (QT-DoG) QT-DoG exploits quantization as an implicit regularizer by inducing noise in model weights. We demonstrate that QT-DoG generalizes across various datasets, architectures, and quantization algorithms.
  arXiv  Detail & Related papers  (2024-10-08T13:21:48Z)
• ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models [14.310720048047136]
  ALPS is an optimization-based framework that tackles the pruning problem using the operator splitting technique and a preconditioned gradient conjugate-based post-processing step. Our approach incorporates novel techniques to accelerate and theoretically guarantee convergence while leveraging vectorization and GPU parallelism for efficiency. On the OPT-30B model with 70% sparsity, ALPS achieves a 13% reduction in test perplexity on the WikiText dataset and a 19% improvement in zero-shot benchmark performance compared to existing methods.
  arXiv  Detail & Related papers  (2024-06-12T02:57:41Z)
• Surgical Feature-Space Decomposition of LLMs: Why, When and How? [8.826164604720738]
  We empirically study the efficacy of weight and feature space decomposition in transformer-based language models. We show that surgical decomposition provides critical insights into the trade-off between compression and language modelling performance. We extend our investigation to the implications of low-rank approximations on model bias.
  arXiv  Detail & Related papers  (2024-05-17T07:34:03Z)
• Pruning as a Domain-specific LLM Extractor [44.81262364608468]
  Large Language Models (LLMs) have exhibited remarkable proficiency across a wide array of NLP tasks. Few efforts have explored model pruning techniques to reduce the size of LLMs. This work introduces an innovative unstructured dual-pruning methodology, D-Pruner, for domain-specific compression on LLM.
  arXiv  Detail & Related papers  (2024-05-10T07:05:02Z)
• Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models [109.06052781040916]
  We introduce a technique to enhance the inference efficiency of parameter-shared language models. We also propose a simple pre-training technique that leads to fully or partially shared models. Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
  arXiv  Detail & Related papers  (2023-10-19T15:13:58Z)
• SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision [54.16430358203348]
  We propose a simple but effective slimmable semantic segmentation (SlimSeg) method, which can be executed at different capacities during inference. We show that our proposed SlimSeg with various mainstream networks can produce flexible models that provide dynamic adjustment of computational cost and better performance.
  arXiv  Detail & Related papers  (2022-07-13T14:41:05Z)
• Locally Interpretable Model Agnostic Explanations using Gaussian Processes [2.9189409618561966]
  Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique for explaining the prediction of a single instance. We propose a Gaussian Process (GP) based variation of locally interpretable models. We demonstrate that the proposed technique is able to generate faithful explanations using much fewer samples as compared to LIME.
  arXiv  Detail & Related papers  (2021-08-16T05:49:01Z)
• Likelihood-Free Inference with Deep Gaussian Processes [70.74203794847344]
  Surrogate models have been successfully used in likelihood-free inference to decrease the number of simulator evaluations. We propose a Deep Gaussian Process (DGP) surrogate model that can handle more irregularly behaved target distributions. Our experiments show how DGPs can outperform GPs on objective functions with multimodal distributions and maintain a comparable performance in unimodal cases.
  arXiv  Detail & Related papers  (2020-06-18T14:24:05Z)

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.