paper-with-me

Papers

Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute

2023-01-25 · Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Joshua Ainslie, Sumit Sanghai, Fei Sha, William Cohen

Retrieval-augmented language models such as Fusion-in-Decoder are powerful, setting the state of the art on a variety of knowledge-intensive tasks. However, they are also expensive, due to the need to encode a large number of retrieved passages. Some work avoids this cost by pre-encoding a text corpus into a memory and retrieving dense representations directly. However, pre-encoding memory incurs a severe quality penalty as the memory representations are not conditioned on the current input. We propose LUMEN, a hybrid between these two extremes, pre-computing the majority of the retrieval representation and completing the encoding on the fly using a live encoder that is conditioned on the question and fine-tuned for the task. We show that LUMEN significantly outperforms pure memory on multiple question-answering tasks while being much cheaper than FiD, and outperforms both for any given compute budget. Moreover, the advantage of LUMEN over FiD increases with model size.

📄 PDF Abstract BibTeX arXiv:2301.10448

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderQuestion AnsweringRetrieval

Similar Papers 제목 키워드 기반

SYNAPSE: Empowering LLM Agents with Episodic-Semantic Memory via Spreading Activation

2026-01-06 · Hanqi Jiang, Junhao Chen, Yi Pan, Ling Chen 외 arxiv

While Large Language Models (LLMs) excel at generalized reasoning, standard retrieval-augmented approaches fail to address the disconnected nature of long-term agentic memory. To bridge this gap, we introduce Synapse (Sy…

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

Hybrid-RACA: Hybrid Retrieval-Augmented Composition Assistance for Real-time Text Prediction

2023-08-08 · Menglin Xia, Xuchao Zhang, Camille Couturier, Guoqing Zheng 외

Large language models (LLMs) enhanced with retrieval augmentation has shown great performance in many applications. However, the computational demands for these models pose a challenge when applying them to real-time tas…

HallucinationLanguage ModellingLarge Language ModelRetrieval

GLIMMER: generalized late-interaction memory reranker

2023-06-17 · Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Sumit Sanghai 외

Memory-augmentation is a powerful approach for efficiently incorporating external information into language models, but leads to reduced performance relative to retrieving text. Recent work introduced LUMEN, a memory-ret…

Retrieval

Hybrid Encoder: Towards Efficient and Precise Native AdsRecommendation via Hybrid Transformer Encoding Networks

2021-04-22 · Junhan Yang, Zheng Liu, Bowen Jin, Jianxun Lian 외

Transformer encoding networks have been proved to be a powerful tool of understanding natural languages. They are playing a critical role in native ads service, which facilitates the recommendation of appropriate ads bas…

Retrieval