Improving Retrieval-Augmented Large Language Models via Data Importance Learning

• URL: http://arxiv.org/abs/2307.03027v1
• Date: Thu, 6 Jul 2023 14:44:07 GMT
• Title: Improving Retrieval-Augmented Large Language Models via Data Importance Learning
• Authors: Xiaozhong Lyu, Stefan Grafberger, Samantha Biegel, Shaopeng Wei, Meng Cao, Sebastian Schelter, Ce Zhang
• Abstract summary: We propose an algorithm based on multilinear extension for evaluating the data importance of retrieved data points. We show that weights based on multilinear extension can be computed efficiently in practice.
• Score: 27.97176983906107
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Retrieval augmentation enables large language models to take advantage of external knowledge, for example on tasks like question answering and data imputation. However, the performance of such retrieval-augmented models is limited by the data quality of their underlying retrieval corpus. In this paper, we propose an algorithm based on multilinear extension for evaluating the data importance of retrieved data points. There are exponentially many terms in the multilinear extension, and one key contribution of this paper is a polynomial time algorithm that computes exactly, given a retrieval-augmented model with an additive utility function and a validation set, the data importance of data points in the retrieval corpus using the multilinear extension of the model's utility function. We further proposed an even more efficient ({\epsilon}, {\delta})-approximation algorithm. Our experimental results illustrate that we can enhance the performance of large language models by only pruning or reweighting the retrieval corpus, without requiring further training. For some tasks, this even allows a small model (e.g., GPT-JT), augmented with a search engine API, to outperform GPT-3.5 (without retrieval augmentation). Moreover, we show that weights based on multilinear extension can be computed efficiently in practice (e.g., in less than ten minutes for a corpus with 100 million elements).

Related papers

• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• Rethinking Chunk Size For Long-Document Retrieval: A Multi-Dataset Analysis [0.0]
  We evaluate fixed-size chunking strategies and their influence on retrieval performance using multiple embedding models.<n>Our experiments, conducted on both short-form and long-form datasets, reveal that chunk size plays a critical role in retrieval effectiveness.
  arXiv  Detail & Related papers  (2025-05-27T19:39:16Z)
• Exploring Training and Inference Scaling Laws in Generative Retrieval [50.82554729023865]
  We investigate how model size, training data scale, and inference-time compute jointly influence generative retrieval performance. Our experiments show that n-gram-based methods demonstrate strong alignment with both training and inference scaling laws. We find that LLaMA models consistently outperform T5 models, suggesting a particular advantage for larger decoder-only models in generative retrieval.
  arXiv  Detail & Related papers  (2025-03-24T17:59:03Z)
• Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality [67.67387254989018]
  We study model performance at various compute budgets and across multiple pre-training datasets created through data filtering and deduplication. We find that, given appropriate modifications to the training recipe, repeating existing aggressively filtered datasets for up to ten epochs can outperform training on the ten times larger superset for a single epoch across multiple compute budget orders of magnitude.
  arXiv  Detail & Related papers  (2025-03-10T21:51:17Z)
• Likelihood as a Performance Gauge for Retrieval-Augmented Generation [78.28197013467157]
  We show that likelihoods serve as an effective gauge for language model performance. We propose two methods that use question likelihood as a gauge for selecting and constructing prompts that lead to better performance.
  arXiv  Detail & Related papers  (2024-11-12T13:14:09Z)
• Retrieval with Learned Similarities [2.729516456192901]
  State-of-the-art retrieval algorithms have migrated to learned similarities. We show that Mixture-of-Logits (MoL) can be realized empirically to achieve superior performance on diverse retrieval scenarios.
  arXiv  Detail & Related papers  (2024-07-22T08:19:34Z)
• Scaling Retrieval-Based Language Models with a Trillion-Token Datastore [85.4310806466002]
  We find that increasing the size of the datastore used by a retrieval-based LM monotonically improves language modeling and several downstream tasks without obvious saturation. By plotting compute-optimal scaling curves with varied datastore, model, and pretraining data sizes, we show that using larger datastores can significantly improve model performance for the same training compute budget.
  arXiv  Detail & Related papers  (2024-07-09T08:27:27Z)
• Learning to Extract Structured Entities Using Language Models [52.281701191329]
  Recent advances in machine learning have significantly impacted the field of information extraction. We reformulate the task to be entity-centric, enabling the use of diverse metrics. We contribute to the field by introducing Structured Entity Extraction and proposing the Approximate Entity Set OverlaP metric.
  arXiv  Detail & Related papers  (2024-02-06T22:15:09Z)
• Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning [47.02160072880698]
  We introduce a self-evolving mechanism that allows the model itself to actively sample subsets that are equally or even more effective. The key to our data sampling technique lies in the enhancement of diversity in the chosen subsets. Extensive experiments across three datasets and benchmarks demonstrate the effectiveness of DiverseEvol.
  arXiv  Detail & Related papers  (2023-11-14T14:10:40Z)
• How to Unleash the Power of Large Language Models for Few-shot Relation Extraction? [28.413620806193165]
  In this paper, we investigate principal methodologies, in-context learning and data generation, for few-shot relation extraction via GPT-3.5. We observe that in-context learning can achieve performance on par with previous prompt learning approaches, and data generation with the large language model can boost previous solutions to obtain new state-of-the-art few-shot results.
  arXiv  Detail & Related papers  (2023-05-02T15:55:41Z)
• Compactness Score: A Fast Filter Method for Unsupervised Feature Selection [66.84571085643928]
  We propose a fast unsupervised feature selection method, named as, Compactness Score (CSUFS) to select desired features. Our proposed algorithm seems to be more accurate and efficient compared with existing algorithms.
  arXiv  Detail & Related papers  (2022-01-31T13:01:37Z)
• Improving Classifier Training Efficiency for Automatic Cyberbullying Detection with Feature Density [58.64907136562178]
  We study the effectiveness of Feature Density (FD) using different linguistically-backed feature preprocessing methods. We hypothesise that estimating dataset complexity allows for the reduction of the number of required experiments. The difference in linguistic complexity of datasets allows us to additionally discuss the efficacy of linguistically-backed word preprocessing.
  arXiv  Detail & Related papers  (2021-11-02T15:48:28Z)
• Efficient Nearest Neighbor Language Models [114.40866461741795]
  Non-parametric neural language models (NLMs) learn predictive distributions of text utilizing an external datastore. We show how to achieve up to a 6x speed-up in inference speed while retaining comparable performance.
  arXiv  Detail & Related papers  (2021-09-09T12:32:28Z)

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.