paper-with-me

Papers

BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models

2024-02-13 · Haotian Sun, Yuchen Zhuang, Wei Wei, Chao Zhang, Bo Dai

Adapting state-of-the-art Large Language Models (LLMs) like GPT-4 and Gemini for specific tasks is challenging. Due to the opacity in their parameters, embeddings, and even output probabilities, existing fine-tuning adaptation methods are inapplicable. Consequently, adapting these black-box LLMs is only possible through their API services, raising concerns about transparency, privacy, and cost. To address these challenges, we introduce BBox-Adapter, a novel lightweight adapter for black-box LLMs. BBox-Adapter distinguishes target and source domain data by treating target data as positive and source data as negative. It employs a ranking-based Noise Contrastive Estimation (NCE) loss to promote the likelihood of target domain data while penalizing that of the source domain. Furthermore, it features an online adaptation mechanism, which incorporates real-time positive data sampling from ground-truth, human, or AI feedback, coupled with negative data from previous adaptations. Extensive experiments demonstrate BBox-Adapter's effectiveness and cost efficiency. It improves model performance by up to 6.77% across diverse tasks and domains, while reducing training and inference costs by 31.30x and 1.84x, respectively.

📄 PDF Abstract BibTeX arXiv:2402.08219

Code (1)

haotiansun14/bbox-adapter 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training

2025-07-02 · Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer 외

Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, its reliance on large volumes of labeled data raises privacy and security concerns suc…

Data PoisoningGeneralization Bounds

MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning

2024-05-05 · Wenqi Shi, ran Xu, Yuchen Zhuang, Yue Yu 외

Despite their improved capabilities in generation and reasoning, adapting large language models (LLMs) to the biomedical domain remains challenging due to their immense size and corporate privacy. In this work, we propos…

Privacy PreservingTest-time Adaptation

Black-Box Tuning of Vision-Language Models with Effective Gradient Approximation

2023-12-26 · Zixian Guo, Yuxiang Wei, Ming Liu, Zhilong Ji 외

Parameter-efficient fine-tuning (PEFT) methods have provided an effective way for adapting large vision-language models to specific tasks or scenarios. Typically, they learn a very small scale of parameters for pre-train…

parameter-efficient fine-tuning

TartuNLP @ SIGTYP 2024 Shared Task: Adapting XLM-RoBERTa for Ancient and Historical Languages

2024-04-19 · Aleksei Dorkin, Kairit Sirts

We present our submission to the unconstrained subtask of the SIGTYP 2024 Shared Task on Word Embedding Evaluation for Ancient and Historical Languages for morphological annotation, POS-tagging, lemmatization, character-…

Lemmatizationparameter-efficient fine-tuningPOSPOS Tagging

CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models

2023-05-23 · Aitor Ormazabal, Mikel Artetxe, Eneko Agirre

Methods for adapting language models (LMs) to new tasks and domains have traditionally assumed white-box access to the model, and work by modifying its parameters. However, this is incompatible with a recent trend in the…

Machine Translation