BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models

• URL: http://arxiv.org/abs/2406.11675v5
• Date: Mon, 27 Jan 2025 16:00:59 GMT
• Title: BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
• Authors: Yibin Wang, Haizhou Shi, Ligong Han, Dimitris Metaxas, Hao Wang,
• Abstract summary: Large Language Models (LLMs) often suffer from overconfidence during inference.<n>We propose Bayesian Low-Rank Adaptation by Backpropagation (BLoB), an algorithm that continuously and jointly adjusts both the mean and covariance of LLM parameters.<n>Our results verify the effectiveness of BLoB in terms of generalization and uncertainty estimation, when evaluated on both in-distribution and out-of-distribution data.
• Score: 13.953203993774233
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) often suffer from overconfidence during inference, particularly when adapted to downstream domain-specific tasks with limited data. Previous work addresses this issue by employing approximate Bayesian estimation after the LLMs are trained, enabling them to quantify uncertainty. However, such post-training approaches' performance is severely limited by the parameters learned during training. In this paper, we go beyond post-training Bayesianization and propose Bayesian Low-Rank Adaptation by Backpropagation (BLoB), an algorithm that continuously and jointly adjusts both the mean and covariance of LLM parameters throughout the whole fine-tuning process. Our empirical results verify the effectiveness of BLoB in terms of generalization and uncertainty estimation, when evaluated on both in-distribution and out-of-distribution data.

Related papers

• BAPE: Learning an Explicit Bayes Classifier for Long-tailed Visual Recognition [78.70453964041718]
  Current deep learning algorithms usually solve for the optimal classifier by emphimplicitly estimating the posterior probabilities.<n>This simple methodology has been proven effective for meticulously balanced academic benchmark datasets.<n>However, it is not applicable to the long-tailed data distributions in the real world.<n>This paper presents a novel approach (BAPE) that provides a more precise theoretical estimation of the data distributions.
  arXiv  Detail & Related papers  (2025-06-29T15:12:50Z)
• Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training [57.03005244917803]
  Large language models (LLMs) often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.<n>Here, we aim to mitigate such spurious correlations through causality-aware post-training (CAPT)<n> Experiments on the formal causal inference benchmark CLadder and the logical reasoning dataset PrOntoQA show that 3B-scale language models fine-tuned with CAPT can outperform both traditional SFT and larger LLMs on in-distribution (ID) and OOD tasks.
  arXiv  Detail & Related papers  (2025-06-11T06:30:28Z)
• Efficient Uncertainty Estimation via Distillation of Bayesian Large Language Models [12.69571386421462]
  In this paper, we investigate the possibility of eliminating the need for test-time sampling for uncertainty estimation.<n>We distill an off-the-shelf Bayesian LLM into a non-Bayesian student LLM by minimizing the divergence between their predictive distributions.<n>Our experiments demonstrate that uncertainty estimation capabilities on training data can successfully generalize to unseen test data.
  arXiv  Detail & Related papers  (2025-05-16T22:26:03Z)
• Entropy-regularized Gradient Estimators for Approximate Bayesian Inference [2.44755919161855]
  This paper addresses the estimation of the Bayesian posterior to generate diverse samples by approximating the gradient flow of the Kullback-Leibler divergence. It presents empirical evaluations on classification tasks to assess the method's performance and discuss its effectiveness for Model-Based Reinforcement Learning.
  arXiv  Detail & Related papers  (2025-03-15T02:30:46Z)
• Efficient Membership Inference Attacks by Bayesian Neural Network [12.404604217229101]
  Membership Inference Attacks (MIAs) aim to estimate whether a specific data point was used in the training of a given model. We propose a novel approach - Bayesian Membership Inference Attack (BMIA), which performs conditional attack through Bayesian inference.
  arXiv  Detail & Related papers  (2025-03-10T15:58:43Z)
• In-Context Parametric Inference: Point or Distribution Estimators? [66.22308335324239]
  We show that amortized point estimators generally outperform posterior inference, though the latter remain competitive in some low-dimensional problems. Our experiments indicate that amortized point estimators generally outperform posterior inference, though the latter remain competitive in some low-dimensional problems.
  arXiv  Detail & Related papers  (2025-02-17T10:00:24Z)
• Training-Free Bayesianization for Low-Rank Adapters of Large Language Models [18.98810667057975]
  Training-Free Bayesianization(TFB) transforms existing off-the-shelf trained LoRA adapters into Bayesian ones without additional training. We show that TFB achieves superior uncertainty estimation and generalization compared to existing methods.
  arXiv  Detail & Related papers  (2024-12-07T18:49:27Z)
• Scaling Laws for Predicting Downstream Performance in LLMs [75.28559015477137]
  This work focuses on the pre-training loss as a more-efficient metric for performance estimation. We extend the power law analytical function to predict domain-specific pre-training loss based on FLOPs across data sources. We employ a two-layer neural network to model the non-linear relationship between multiple domain-specific loss and downstream performance.
  arXiv  Detail & Related papers  (2024-10-11T04:57:48Z)
• Self-Evolutionary Large Language Models through Uncertainty-Enhanced Preference Optimization [9.618391485742968]
  Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs) We present an uncertainty-enhanced textbfPreference textbfOptimization framework to make the LLM self-evolve with reliable feedback. Our framework substantially alleviates the noisy problem and improves the performance of iterative preference optimization.
  arXiv  Detail & Related papers  (2024-09-17T14:05:58Z)
• 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)
• Unraveling Batch Normalization for Realistic Test-Time Adaptation [22.126177142716188]
  This paper delves into the problem of mini-batch degradation. By unraveling batch normalization, we discover that the inexact target statistics largely stem from the substantially reduced class diversity in batch. We introduce a straightforward tool, Test-time Exponential Moving Average (TEMA), to bridge the class diversity gap between training and testing batches.
  arXiv  Detail & Related papers  (2023-12-15T01:52:35Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift [19.945634052291542]
  We evaluate modern BDL algorithms on real-world datasets from the WILDS collection containing challenging classification and regression tasks. We compare the algorithms on a wide range of large, convolutional and transformer-based neural network architectures. We provide the first systematic evaluation of BDL for fine-tuning large pre-trained models.
  arXiv  Detail & Related papers  (2023-06-21T14:36:03Z)
• Personalized Federated Learning under Mixture of Distributions [98.25444470990107]
  We propose a novel approach to Personalized Federated Learning (PFL), which utilizes Gaussian mixture models (GMM) to fit the input data distributions across diverse clients. FedGMM possesses an additional advantage of adapting to new clients with minimal overhead, and it also enables uncertainty quantification. Empirical evaluations on synthetic and benchmark datasets demonstrate the superior performance of our method in both PFL classification and novel sample detection.
  arXiv  Detail & Related papers  (2023-05-01T20:04:46Z)
• On the Practicality of Deterministic Epistemic Uncertainty [106.06571981780591]
  deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution data. It remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications.
  arXiv  Detail & Related papers  (2021-07-01T17:59:07Z)
• Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
  Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
  arXiv  Detail & Related papers  (2021-04-11T09:50:24Z)
• Adaptive Sampling for Estimating Distributions: A Bayesian Upper Confidence Bound Approach [30.76846526324949]
  A Bayesian variant of the existing upper confidence bound (UCB) based approaches is proposed. The effectiveness of this strategy is discussed using data obtained from a seroprevalence survey in Los Angeles county.
  arXiv  Detail & Related papers  (2020-12-08T00:53:34Z)

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.