BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models
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.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training
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 BoundsMedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning
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 AdaptationBlack-Box Tuning of Vision-Language Models with Effective Gradient Approximation
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-tuningTartuNLP @ SIGTYP 2024 Shared Task: Adapting XLM-RoBERTa for Ancient and Historical Languages
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 TaggingCombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models
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