No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval

• URL: http://arxiv.org/abs/2206.02873v1
• Date: Mon, 6 Jun 2022 19:56:14 GMT
• Title: No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval
• Authors: Guilherme Moraes Rosa and Luiz Bonifacio and Vitor Jeronymo and Hugo Abonizio and Marzieh Fadaee and Roberto Lotufo and Rodrigo Nogueira
• Abstract summary: We show that the number of parameters and early query-document interaction play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Our largest reranker reaches the state of the art in 12 of the 18 datasets of the Benchmark-IR (BEIR) and surpasses the previous state of the art by 3 average points.
• Score: 4.712097135437801
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent work has shown that small distilled language models are strong competitors to models that are orders of magnitude larger and slower in a wide range of information retrieval tasks. This has made distilled and dense models, due to latency constraints, the go-to choice for deployment in real-world retrieval applications. In this work, we question this practice by showing that the number of parameters and early query-document interaction play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furthermore, we show that rerankers largely outperform dense ones of similar size in several tasks. Our largest reranker reaches the state of the art in 12 of the 18 datasets of the Benchmark-IR (BEIR) and surpasses the previous state of the art by 3 average points. Finally, we confirm that in-domain effectiveness is not a good indicator of zero-shot effectiveness. Code is available at https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git

Related papers

• Why Do More Experts Fail? A Theoretical Analysis of Model Merging [51.18155031364046]
  Model merging dramatically reduces storage and computational resources by combining multiple expert models into a single multi-task model.<n>Recent model merging methods have shown promising results, but struggle to maintain performance gains as the number of merged models increases.<n>We show that the limited effective parameter space imposes a strict constraint on the number of models that can be successfully merged.
  arXiv  Detail & Related papers  (2025-05-27T14:10:46Z)
• Enabling Small Models for Zero-Shot Classification through Model Label Learning [50.68074833512999]
  We introduce a novel paradigm, Model Label Learning (MLL), which bridges the gap between models and their functionalities. Experiments on seven real-world datasets validate the effectiveness and efficiency of MLL.
  arXiv  Detail & Related papers  (2024-08-21T09:08:26Z)
• Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends [49.68011233558541]
  Large autoregressive generative models have emerged as the cornerstone for achieving the highest performance across several Natural Language Processing tasks. We introduce Maverick, a pipeline that enables running a state-of-the-art Coreference Resolution system within the constraints of an academic budget. Maverick achieves state-of-the-art performance on the CoNLL-2012 benchmark, training with up to 0.006x the memory resources and obtaining a 170x faster inference compared to previous state-of-the-art systems.
  arXiv  Detail & Related papers  (2024-07-31T09:58:48Z)
• Tiny models from tiny data: Textual and null-text inversion for few-shot distillation [11.80626524879555]
  Few-shot image classification involves classifying images using very few training examples. Recent vision foundation models show excellent few-shot transfer abilities, but are large and slow at inference. We present a novel diffusion model inversion technique (TINT) combining the diversity of textual inversion with the specificity of null-text inversion.
  arXiv  Detail & Related papers  (2024-06-05T11:01:42Z)
• The Larger the Better? Improved LLM Code-Generation via Budget Reallocation [32.0844209512788]
  It is a common belief that large language models (LLMs) are better than smaller-sized ones. This begs the question: what happens when both models operate under the same budget? We analyze code generation LLMs of various sizes and make comparisons such as running a 70B model once vs. generating five outputs from a 13B model.
  arXiv  Detail & Related papers  (2024-03-31T15:55:49Z)
• Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines [83.65380507372483]
  Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box. This paper shows how to leverage recent advances in NLP and multi-modal learning to augment a pre-trained model with search engine retrieval.
  arXiv  Detail & Related papers  (2023-11-29T05:33:28Z)
• SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrieval [92.27387459751309]
  We provide SPRINT, a unified Python toolkit for evaluating neural sparse retrieval. We establish strong and reproducible zero-shot sparse retrieval baselines across the well-acknowledged benchmark, BEIR. We show that SPLADEv2 produces sparse representations with a majority of tokens outside of the original query and document.
  arXiv  Detail & Related papers  (2023-07-19T22:48:02Z)
• On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition [65.67315418971688]
  We show that truncating small eigenvalues of the Global Covariance Pooling (GCP) can attain smoother gradient. On fine-grained datasets, truncating the small eigenvalues would make the model fail to converge. Inspired by this observation, we propose a network branch dedicated to magnifying the importance of small eigenvalues.
  arXiv  Detail & Related papers  (2022-05-26T11:41:36Z)
• When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model [87.25037167380522]
  We propose a model that is accurate, robust, efficient, generalizable, and end-to-end trainable. In order to achieve a better accuracy, we propose two lightweight modules. DQInit dynamically initializes the queries of decoder from the inputs, enabling the model to achieve as good accuracy as the ones with multiple decoder layers. QAMem is designed to enhance the discriminative ability of queries on low-resolution feature maps by assigning separate memory values to each query rather than a shared one.
  arXiv  Detail & Related papers  (2021-05-27T13:51:42Z)
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models [41.45240621979654]
  We introduce BEIR, a heterogeneous benchmark for information retrieval. We study the effectiveness of nine state-of-the-art retrieval models in a zero-shot evaluation setup. Dense-retrieval models are computationally more efficient but often underperform other approaches.
  arXiv  Detail & Related papers  (2021-04-17T23:29:55Z)
• Contemplating real-world object classification [53.10151901863263]
  We reanalyze the ObjectNet dataset recently proposed by Barbu et al. containing objects in daily life situations. We find that applying deep models to the isolated objects, rather than the entire scene as is done in the original paper, results in around 20-30% performance improvement.
  arXiv  Detail & Related papers  (2021-03-08T23:29:59Z)

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.