Fine-tuning large language models requires minimal data, making them efficient.
problem Achieving state-of-the-art performance with large language models.
method Using BERT as an example, fine-tuning only the most critical layers of the pre-trained model.
result Fine-tuned models are close in parameter space to the pre-trained model, with many good solutions found in sparsified versions.
CoLoRA leverages task similarity to boost fine-tuning efficiency.
problem Efficiently fine-tuning large foundation models with scarce labeled data.
method CoLoRA trains a shared adapter for task similarity and personalized adapters for user-specific tasks.
result CoLoRA significantly boosts fine-tuning performance when tasks are similar.
EVA adapts LoRA for faster, more efficient fine-tuning.
problem Fast and efficient fine-tuning of large models for specific tasks.
method EVA uses directions capturing most activation variance for initialization, maximizing gradient signal and reducing parameters.
result EVA achieves faster convergence and higher average scores across tasks, reducing parameters.
GeLoRA optimizes LoRA fine-tuning by dynamically adjusting ranks based on intrinsic dimensionality.
problem Efficient fine-tuning of large language models with limited computational resources.
method GeLoRA computes intrinsic dimensionality to adaptively select LoRA ranks, balancing expressivity and efficiency.
result GeLoRA consistently outperforms recent baselines within the same parameter budget on multiple tasks.
LaLoRA prevents forgetting in LoRA fine-tuning.
problem Catastrophic forgetting in fine-tuned models.
method LaLoRA applies Laplace approximation to LoRA weights for regularization.
result Improved learning-forgetting trade-off with controllable regularization strength.
TensorGuide improves LoRA efficiency and expressivity through joint tensor-train optimization.
problem Limited expressivity and generalization of standard LoRA.
method TensorGuide uses a unified tensor-train structure with controlled Gaussian noise to generate correlated low-rank matrices.
result TensorGuide achieves superior accuracy and scalability with fewer parameters compared to standard LoRA and TT-LoRA.
Paper proposes CLAIR for efficient LLM fine-tuning across clients.
problem Fine-tuning large language models (LLMs) efficiently and collaboratively.
method Federated LoRA fine-tuning with Collaborative Low-rank Alignment and Identifiable Recovery (CLAIR).
result CLAIR achieves better performance and contamination detection compared to local fine-tuning.
Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. However, in the presence of many downstream tasks, fine-tuning is parameter inefficient: an entire new model is required for every task. As an alternative, we propose transfer with adapter modules. Adapter modules yield a compact and extens…
Paper fine-tunes LLMs for financial tasks using data fusion.
problem Improving LLMs for financial analysis tasks.
method Fine-tuned Llama3-8B and Mistral-7B using PEFT and LoRA, combined datasets for data fusion.
result Enhanced model performance across financial tasks.
LORENZA improves LLM fine-tuning efficiency and generalization.
problem Improving robustness and generalization of LLMs under hardware constraints.
method AdaZo-SAM and LORENZA, combining Adam and SAM with zeroth-order estimation and randomized SVD.
result LORENZA achieves better generalization and reduced memory consumption compared to existing methods.
New framework explains how larger pre-trained models reduce downstream learning sample complexity.
problem Understanding why larger pre-trained models reduce sample complexity in downstream tasks.
method Introducing a novel framework called Caulking inspired by PEFT methods.
result Improved pre-trained models provably decrease downstream task sample complexity.
A new method for efficient neural network fine-tuning using queryable low-rank update atoms.
problem Rigidity of static low-rank adaptation methods when input and depth-wise computation vary.
method A shared queryable memory of low-rank update atoms, allowing dynamic and context-sensitive adaptation.
result Improves final test performance and training stability compared to standard low-rank adaptation.
ICE-Pruning accelerates deep neural network pruning by 9.61x.
problem Efficiently pruning deep neural networks while maintaining accuracy.
method Iterative pruning with automatic fine-tuning steps, freezing strategy, and custom learning rate scheduler.
result Significantly reduces pruning time by up to 9.61x.
Research reveals deep networks often learn low-rank structures, leading to more efficient training and fine-tuning.
problem Efficient training and deployment of large-scale deep learning models.
method Complementary theoretical perspectives on low-rank structures during training and convergence, and practical applications of LoRA and masked training.
result Understanding and exploiting low-rank structures can improve efficiency and effectiveness of training and fine-tuning.
LOFT separates subspace rotation and transformation for orthogonal fine-tuning.
problem Conflating subspace rotation and transformation in orthogonal fine-tuning.
method LOFT explicitly separates subspace rotation and transformation, using task-aware support selection.
result LOFT recovers principal-subspace orthogonal adaptation and improves efficiency-performance trade-off.
Transfer learning boosts chemically accurate neural network potentials for organic molecules.
problem Developing accurate interatomic potentials from ab-initio data.
method Discriminative fine-tuning of pre-trained neural networks.
result Fine-tuning with energy labels alone can achieve accurate atomic forces.
LoRA enhances model adaptability without increasing parameters.
problem Theoretical understanding of LoRA's adaptability.
method Theoretical analysis of LoRA's expressive power.
result LoRA can adapt any model to a smaller target model with a specific rank.
LoRA fine-tuning on CPUs without GPUs achieves comparable performance to GPU-based methods.
problem Limited computational resources for fine-tuning LLMs.
method Developed a CPU-efficient method to learn meta-operators for LoRA weights.
result LoRA adapters trained on CPUs outperform base models on downstream tasks.
ADAPT improves robustness of Vision Transformers without full model fine-tuning.
problem Vulnerability of Vision Transformers to adversarial attacks.
method Parameter-efficient prompt tuning with ADAPT framework for adaptive adversarial training.
result ADAPT achieves robust accuracy of ~40% w.r.t. SOTA methods using only ~1% of the parameters.
New method improves reliability of depth estimation models.
problem Uncertainty quantification in large-scale vision models.
method Parameter-efficient Bayesian neural networks with PEFT methods.
result Combining PEFT methods with Bayesian inference enhances predictive performance.
Feature representations from pre-trained deep neural networks have been known to exhibit excellent generalization and utility across a variety of related tasks. Fine-tuning is by far the simplest and most widely used approach that seeks to exploit and adapt these feature representations to novel tasks with limited data…
FGSM is more stable in adversarially robust transfer learning than PGD.
problem Computational efficiency in adversarially robust transfer learning.
method Revisited use of FGSM in adversarial fine-tuning.
result FGSM is more stable and efficient in adversarial fine-tuning.
We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead of fine-tuning the last layer or the entire network. For instance, we show that l…
In2Core selects a coreset for efficient LLM fine-tuning with reduced data.
problem Costly fine-tuning of large language models due to extensive parameters and data requirements.
method Analyzes model gradients to estimate training sample influence, optimizing for efficiency.
result Achieves similar performance with 50% of training data using In2Core.
Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the requirement of a large training set and the time-consuming training procedure. …
Simplified trust region method reduces representation change during fine-tuning.
problem Stability and representational collapse in fine-tuning pre-trained models.
method Replaces adversarial objectives with parametric noise in trust region theory.
result Matches or exceeds previous trust region methods in performance and speed.
We present BOFFIN TTS (Bayesian Optimization For FIne-tuning Neural Text To Speech), a novel approach for few-shot speaker adaptation. Here, the task is to fine-tune a pre-trained TTS model to mimic a new speaker using a small corpus of target utterances. We demonstrate that there does not exist a one-size-fits-all ada…
Multi-task learning shares information between related tasks, sometimes reducing the number of parameters required. State-of-the-art results across multiple natural language understanding tasks in the GLUE benchmark have previously used transfer from a single large task: unsupervised pre-training with BERT, where a sep…
Improved forecast accuracy for energy systems through decision-focused fine-tuning.
problem Challenges in integrating forecast values into time series models for diverse and specific instances.
method Decision-focused fine-tuning within time series foundation models for dispatchable feeder optimization.
result Improvement of 9.45% in average total daily costs.
This work introduces 'Artificial Entanglement' to understand LLMs' fine-tuning effectiveness.
problem Understanding the effectiveness of parameter-efficient fine-tuning methods for large language models.
method Adopting a quantum-information-inspired perspective, the study measures 'Artificial Entanglement' in neural networks.
result LoRA and FFT induce distinct internal entanglement signatures but not external ones, suggesting a 'no-hair' property.
Paper fine-tunes a simulation-driven estimator to reduce out-of-distribution errors.
problem Out-of-distribution errors in simulation-driven parameter estimators.
method Fine-tuning a Two-Stage estimator to improve accuracy for true parameters outside the sampled range.
result The fine-tuning approach reduces out-of-distribution errors and improves accuracy.
Improved NLP performance with fewer parameters and less data using conditional multi-task learning.
problem Challenges in transferring knowledge across different NLP tasks, including overfitting, forgetting, and negative transfer.
method Proposes a novel Transformer architecture with conditional attention and task-conditioned modules for efficient parameter sharing and mitigating forgetting.
result Achieves state-of-the-art performance on 26 NLP tasks with 66% less data and 50% fewer parameters compared to existing methods.
Unified LLM-agent with RL improves financial trading performance.
problem LLMs struggle with complex, multi-step financial tasks.
method Fusion of LLMs and gradient-based RL for policy optimization.
result Improves LLM performance in trading and other financial tasks.
FisherSFT selects informative examples to fine-tune LLMs efficiently.
problem Adapting large language models to new domains efficiently.
method Selects examples maximizing information gain using Hessian of log-likelihood.
result Empirically demonstrates improved performance with reduced computational cost.
DataInf efficiently approximates data influence in large models, improving transparency and identifying mislabeled data.
problem Efficiently estimating data influence in large-scale models like LoRA-tuned LLMs and diffusion models.
method DataInf uses a closed-form expression to approximate influence scores efficiently.
result DataInf outperforms existing methods in computational and memory efficiency, accurately identifying influential data points.
LoRA-Curve connects independent LoRA optima through continuous low-loss valleys, improving Bayesian model averaging.
problem Challenges in estimating epistemic uncertainty in LoRA-based Bayesian inference.
method Introduces LoRA-Curve, a segmented Bézier curve parameterization in the LoRA space, with free and anchored configurations.
result Empirically shows that connecting independent LoRA optima through continuous low-loss valleys improves mutual information of the predictive distribution.
Improved financial VA intent classification accuracy.
problem Determining user intents for unseen open intents.
method Supervised pre-training of intent representations using prefix-tuning and fine-tuning.
result 1.63% - 2.07% higher accuracy on banking77 benchmark.
Fine-tuning harms in-context learning, but restricting updates to the value matrix improves zero-shot performance.
problem Fine-tuning harms in-context learning, reducing zero-shot performance on unseen tasks.
method Theoretical analysis of linear attention models, identifying conditions for degraded few-shot performance.
result Restricting updates to the value matrix improves zero-shot performance while preserving in-context learning.
Paper fine-tunes LLaMA-3-8B for financial NER using instruction and LoRA.
problem LLMs struggle with financial NER, especially differentiating entities and amounts.
method Instruction fine-tuning combined with LoRA for parameter-efficient learning.
result Micro-F1 score of 0.894 on financial NER tasks, outperforming other models.
New method fine-tunes discrete diffusion models for RLHF tasks.
problem Fine-tuning discrete diffusion models with policy gradient methods is challenging.
method Proposed SEPO algorithm for efficient fine-tuning over non-differentiable rewards.
result Numerical experiments show scalability and efficiency of SEPO.
The paper develops a theory linking pretraining and fine-tuning in neural networks.
problem Understanding how initialization choices impact feature learning and generalization in neural networks.
method Analytical theory of diagonal linear networks, deriving generalization error as a function of initialization parameters and task statistics.
result Different initialization choices place networks into four fine-tuning regimes with varying abilities to support feature learning and generalization.
New method prevents forgetting in LLMs by dynamically identifying task-specific subspaces.
problem Catastrophic forgetting in continual learning of LLMs.
method Adaptive Singular Value Decomposition (SVD) for constrained full fine-tuning.
result Achieves state-of-the-art results in continual learning benchmarks.
Develops a method to ensure accuracy of few-shot transfer learning models.
problem Lack of generalization guarantees for low-data transfer learning.
method Trains a distribution over PEFT parameters using upstream tasks and samples plausible PEFTs for downstream tasks.
result Demonstrates non-vacuous generalization guarantees compared to existing methods in the low-shot regime.
New method calibrates LLMs for safety-critical tasks with scalable Bayesian inference.
problem Overconfidence in LLMs after fine-tuning for specific tasks.
method Orthogonalized Low-Rank Adapters (PoLAR) with variational Bayesian inference.
result Scalable and well-calibrated uncertainty estimation for LLMs.
Pre-training on different modalities improves Transformer performance in offline reinforcement learning.
problem Improving Transformer-based models for offline reinforcement learning tasks.
method Empirical investigation of pre-training on language and vision data, analysis of internal representations, and fine-tuning with no context.
result Pre-trained Transformers with language data can utilize context-like information to solve reinforcement learning tasks efficiently.
This paper simplifies fine-tuning for small LLMs, reducing barriers for developers.
problem Limited resources for fine-tuning large language models (LLMs) by individual developers and small organizations.
method Instruction-tuning datasets, small-sized LLMs (3B to 7B parameters), various training configurations and strategies.
result Improved model performance on benchmarks with specific training configurations, and insights into early termination and hyperparameter simplifications.
LoRA fine-tuning causes forgetting, studied via particle system dynamics.
problem Catastrophic forgetting in LoRA fine-tuning.
method Mean-field self-attention model, partial differential equations, dynamical systems.
result Characterization of phase transitions in forgetting behavior.
Transformers learn functionals from distributions without losing information.
problem Lack of rigorous mathematical theory supporting Transformer performance.
method Proposed a Transformer learning framework, attention operator, and distribution regression.
result Transformers can compress distributions into function representations without loss of information.