paper-with-me

Papers

Generative Retrieval with Few-shot Indexing

2024-08-04 · Arian Askari, Chuan Meng, Mohammad Aliannejadi, Zhaochun Ren, Evangelos Kanoulas, Suzan Verberne

Existing generative retrieval (GR) approaches rely on training-based indexing, i.e., fine-tuning a model to memorise the associations between a query and the document identifier (docid) of a relevant document. Training-based indexing has three limitations: high training overhead, under-utilization of the pre-trained knowledge of large language models (LLMs), and challenges in adapting to a dynamic document corpus. To address the above issues, we propose a novel few-shot indexing-based GR framework (Few-Shot GR). It has a novel few-shot indexing process, where we prompt an LLM to generate docids for all documents in a corpus, ultimately creating a docid bank for the entire corpus. During retrieval, we feed a query to the same LLM and constrain it to generate a docid within the docid bank created during indexing, and then map the generated docid back to its corresponding document. Few-Shot GR relies solely on prompting an LLM without requiring any training, making it more efficient. Moreover, we devise few-shot indexing with one-to-many mapping to further enhance Few-Shot GR. Experiments show that Few-Shot GR achieves superior performance to state-of-the-art GR methods that require heavy training.

📄 PDF Abstract BibTeX arXiv:2408.02152

Code (0)

등록된 구현이 없습니다.

Tasks

Retrieval

Similar Papers 제목 키워드 기반

Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval

2024-07-16 · Yubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke 외

Generative retrieval uses differentiable search indexes to directly generate relevant document identifiers in response to a query. Recent studies have highlighted the potential of a strong generative retrieval model, tra…

MemorizationRetrieval

Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts

2026-04-03 · Jinsook Lee, Kirk Vanacore, Zhuqian Zhou, Bakhtawar Ahtisham 외 arxiv

Automated annotation of pedagogical dialogue is a high-stakes task where LLMs often fail without sufficient domain grounding. We present a domain-adapted RAG pipeline for tutoring move annotation. Rather than fine-tuning…

Bottleneck-Minimal Indexing for Generative Document Retrieval

2024-05-12 · Xin Du, Lixin Xiu, Kumiko Tanaka-Ishii

We apply an information-theoretic perspective to reconsider generative document retrieval (GDR), in which a document $x \in X$ is indexed by $t \in T$, and a neural autoregressive model is trained to map queries $Q$ to $…

Retrieval

ICICLE: Expanding Retrieval with In-Context Documents

2026-05-26 · Yu-Chen Den, Yung-Yu Shih, Zhi Rui Tam, Kuan-Yu Chen 외 arxiv

Generative retrieval (GR) maps queries directly to document identifiers (docids) using parametric knowledge, However, this design makes corpus expansion costly: adding new documents requires updating model parameters to …

Generative Retrieval as Dense Retrieval

2023-06-20 · Thong Nguyen, Andrew Yates

Generative retrieval is a promising new neural retrieval paradigm that aims to optimize the retrieval pipeline by performing both indexing and retrieval with a single transformer model. However, this new paradigm faces c…

Retrieval