paper-with-me

홈 › Papers

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models

2023-10-02 · Qingqing Cao, Sewon Min, Yizhong Wang, Hannaneh Hajishirzi

Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language models (LMs) is slow and difficult to scale due to processing large amounts of retrieved text. We introduce binary token representations (BTR), which use 1-bit vectors to precompute every token in passages, significantly reducing computation during inference. Despite the potential loss of accuracy, our new calibration techniques and training objectives restore performance. Combined with offline and runtime compression, this only requires 127GB of disk space for encoding 3 billion tokens in Wikipedia. Our experiments show that on five knowledge-intensive NLP tasks, BTR accelerates state-of-the-art inference by up to 4x and reduces storage by over 100x while maintaining over 95% task performance.

📄 PDF Abstract BibTeX arXiv:2310.01329

Code (1)

csarron/btr 공식 구현 pytorch

Tasks

HallucinationRetrieval

Similar Papers 제목 키워드 기반

Surface-Based Retrieval Reduces Perplexity of Retrieval-Augmented Language Models

2023-05-25 · Ehsan Doostmohammadi, Tobias Norlund, Marco Kuhlmann, Richard Johansson

Augmenting language models with a retrieval mechanism has been shown to significantly improve their performance while keeping the number of parameters low. Retrieval-augmented models commonly rely on a semantic retrieval…

Re-RankingRetrievalSemantic Retrieval

MEMORY-VQ: Compression for Tractable Internet-Scale Memory

2023-08-28 · Yury Zemlyanskiy, Michiel de Jong, Luke Vilnis, Santiago Ontañón 외

Retrieval augmentation is a powerful but expensive method to make language models more knowledgeable about the world. Memory-based methods like LUMEN pre-compute token representations for retrieved passages to drasticall…

QuantizationRetrieval

Beyond Post-Quantization: Native Hash Learning with a Dedicated HASH Token

2026-07-03 · Xinze Liu, Ding Wang, Hengjie Zhu, Dayan Wu arxiv

Efficient large-scale image retrieval requires compact representations that preserve semantic similarity under fast Hamming-space search. Deep hashing is appealing, but most existing CNN- and ViT-based methods still foll…

Semantic SimilarityCode GenerationImage Retrieval

Tiny-Critic RAG: Empowering Agentic Fallback with Parameter-Efficient Small Language Models

2026-03-01 · Yichao Wu, Penghao Liang, Yafei Xiang, Mengwei Yuan 외 arxiv

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) to mitigate factual hallucinations. Recent paradigms shift from static pipelines to Modular and Agentic RAG frameworks, granting models autonomy f…

Retrieval-Pretrained Transformer: Long-range Language Modeling with Self-retrieval

2023-06-23 · Ohad Rubin, Jonathan Berant

Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added post-hoc to an already-pretrained LM, wh…

Language ModelingLanguage ModellingRetrieval