paper-with-me

Papers

Intermediate Distillation: Data-Efficient Distillation from Black-Box LLMs for Information Retrieval

2024-06-18 · Zizhong Li, Haopeng Zhang, Jiawei Zhang

Recent research has explored distilling knowledge from large language models (LLMs) to optimize retriever models, especially within the retrieval-augmented generation (RAG) framework. However, most existing training methods rely on extracting supervision signals from LLMs' weights or their output probabilities, which is not only resource-intensive but also incompatible with black-box LLMs. In this paper, we introduce \textit{Intermediate Distillation}, a data-efficient knowledge distillation training scheme that treats LLMs as black boxes and distills their knowledge via an innovative LLM-ranker-retriever pipeline, solely using LLMs' ranking generation as the supervision signal. Extensive experiments demonstrate that our proposed method can significantly improve the performance of retriever models with only 1,000 training instances. Moreover, our distilled retriever model significantly boosts performance in question-answering tasks within the RAG framework, demonstrating the potential of LLMs to economically and effectively train smaller models.

📄 PDF Abstract BibTeX arXiv:2406.12169

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalKnowledge DistillationQuestion AnsweringRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
WordPiece 설명 없음
Residual Connection 설명 없음
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 $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

DistillLens: Symmetric Knowledge Distillation Through Logit Lens

2026-02-14 · Manish Dhakal, Uthman Jinadu, Anjila Budathoki, Rajshekhar Sunderraman 외 arxiv

Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process as a black box. While feature-based dis…

Knowledge Distillation

Black-Box On-Policy Distillation of Large Language Models

2025-11-13 · Tianzhu Ye, Li Dong, Zewen Chi, Xun Wu 외 arxiv

Black-box distillation creates student large language models (LLMs) by learning from a proprietary teacher model's text outputs alone, without access to its internal logits or parameters. In this work, we introduce Gener…

Knowledge Distillation

Knowledge Distillation of Black-Box Large Language Models

2024-01-13 · Hongzhan Chen, Ruijun Chen, Yuqi Yi, Xiaojun Quan 외

Given the exceptional performance of proprietary large language models (LLMs) like GPT-4, recent research has increasingly focused on boosting the capabilities of smaller models through knowledge distillation (KD) from t…

Knowledge DistillationTransfer Learning

Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective

2026-02-03 · Hao Fang, Tianyi Zhang, Tianqu Zhuang, Jiawei Kong 외 arxiv

Proprietary large language models (LLMs) embody substantial economic value and are generally exposed only as black-box APIs, yet adversaries can still exploit their outputs to extract knowledge via distillation. Existing…

Model extraction

Syntriever: How to Train Your Retriever with Synthetic Data from LLMs

2025-02-06 · Minsang Kim, Seungjun Baek

LLMs have boosted progress in many AI applications. Recently, there were attempts to distill the vast knowledge of LLMs into information retrieval systems. Those distillation methods mostly use output probabilities of LL…

Information Retrieval