GLIMMER: generalized late-interaction memory reranker

• URL: http://arxiv.org/abs/2306.10231v1
• Date: Sat, 17 Jun 2023 01:54:25 GMT
• Title: GLIMMER: generalized late-interaction memory reranker
• Authors: Michiel de Jong, Yury Zemlyanskiy, Nicholas FitzGerald, Sumit Sanghai, William W. Cohen, Joshua Ainslie
• Abstract summary: Memory-augmentation is a powerful approach for incorporating external information into language models. Recent work introduced LUMEN, a memory-retrieval hybrid that partially pre-computes memory and updates memory representations on the fly with a smaller live encoder. We propose GLIMMER, which improves on this approach through 1) exploiting free access to the powerful memory representations by applying a shallow reranker on top of memory to drastically improve retrieval quality at low cost.
• Score: 29.434777627686692
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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-retrieval hybrid that partially pre-computes memory and updates memory representations on the fly with a smaller live encoder. We propose GLIMMER, which improves on this approach through 1) exploiting free access to the powerful memory representations by applying a shallow reranker on top of memory to drastically improve retrieval quality at low cost, and 2) incorporating multi-task training to learn a general and higher quality memory and live encoder. GLIMMER achieves strong gains in performance at faster speeds compared to LUMEN and FiD on the KILT benchmark of knowledge-intensive tasks.

Related papers

• Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning [64.93848182403116]
  Current deep-learning memory models struggle in reinforcement learning environments that are partially observable and long-term. We introduce the Stable Hadamard Memory, a novel memory model for reinforcement learning agents. Our approach significantly outperforms state-of-the-art memory-based methods on challenging partially observable benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T03:50:17Z)
• $\text{Memory}^3$: Language Modeling with Explicit Memory [22.572376536612015]
  We equip large language models (LLMs) with explicit memory, a memory format cheaper than model parameters and text retrieval-augmented generation (RAG) As a preliminary proof of concept, we train from scratch a 2.4B LLM, which achieves better performance than much larger LLMs and RAG models. We introduce a memory circuitry theory to support the externalization of knowledge, and present novel techniques including a memory sparsification mechanism that makes storage tractable.
  arXiv  Detail & Related papers  (2024-07-01T11:07:23Z)
• MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memory [49.96019697955383]
  We introduce MemLLM, a novel method of enhancing knowledge capabilities by integrating a structured and explicit read-and-write memory module. Our experiments indicate that MemLLM enhances performance and interpretability, in language modeling general and in particular. We see MemLLM as an important step towards making LLMs more grounded and factual through memory augmentation.
  arXiv  Detail & Related papers  (2024-04-17T18:13:16Z)
• LLM in a flash: Efficient Large Language Model Inference with Limited Memory [19.668719251238176]
  Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. This paper tackles the challenge of efficiently running LLMs that exceed the available DRAM capacity. Our method involves constructing an inference cost model that takes into account the characteristics of flash memory.
  arXiv  Detail & Related papers  (2023-12-12T18:57:08Z)
• AdaLomo: Low-memory Optimization with Adaptive Learning Rate [59.64965955386855]
  We introduce low-memory optimization with adaptive learning rate (AdaLomo) for large language models. AdaLomo results on par with AdamW, while significantly reducing memory requirements, thereby lowering the hardware barrier to training large language models.
  arXiv  Detail & Related papers  (2023-10-16T09:04:28Z)
• MEMORY-VQ: Compression for Tractable Internet-Scale Memory [45.7528997281282]
  Memory-based methods like LUMEN pre-compute token representations for retrieved passages to drastically speed up inference. We propose MEMORY-VQ, a new method to reduce storage requirements of memory-augmented models without sacrificing performance.
  arXiv  Detail & Related papers  (2023-08-28T21:11:18Z)
• Augmenting Language Models with Long-Term Memory [142.04940250657637]
  Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit. We propose a framework, Language Models Augmented with Long-Term Memory (LongMem), which enables LLMs to memorize long history.
  arXiv  Detail & Related papers  (2023-06-12T15:13:39Z)
• Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory [72.36736686941671]
  We propose a novel framework, selfmem, for improving retrieval-augmented generation models. Selfmem iteratively employs a retrieval-augmented generator to create an unbounded memory pool and using a memory selector to choose one output as memory for the subsequent generation round. We evaluate the effectiveness of selfmem on three distinct text generation tasks.
  arXiv  Detail & Related papers  (2023-05-03T21:40:54Z)
• Pre-computed memory or on-the-fly encoding? A hybrid approach to retrieval augmentation makes the most of your compute [23.85786594315147]
  Fusion-in-Decoders are powerful, setting the state of the art on a variety of knowledge-intensive tasks. Some work avoids this cost by pre-encoding a text corpus into a memory and retrieving dense representations directly. We propose LUMEN, a hybrid between these two extremes, pre-computing the majority of the retrieval representation and completing the encoding on the fly. 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.
  arXiv  Detail & Related papers  (2023-01-25T07:55:45Z)
• Memformer: A Memory-Augmented Transformer for Sequence Modeling [55.780849185884996]
  We present Memformer, an efficient neural network for sequence modeling. Our model achieves linear time complexity and constant memory space complexity when processing long sequences.
  arXiv  Detail & Related papers  (2020-10-14T09:03:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.