Online Cascade Learning for Efficient Inference over Streams
- URL: http://arxiv.org/abs/2402.04513v3
- Date: Mon, 17 Jun 2024 18:54:36 GMT
- Title: Online Cascade Learning for Efficient Inference over Streams
- Authors: Lunyiu Nie, Zhimin Ding, Erdong Hu, Christopher Jermaine, Swarat Chaudhuri,
- Abstract summary: Large Language Models (LLMs) have a natural role in answering complex queries about data streams.
We propose online cascade learning, the first approach to address this challenge.
We formulate the task of learning cascades online as an imitation-learning problem.
- Score: 9.516197133796437
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large Language Models (LLMs) have a natural role in answering complex queries about data streams, but the high computational cost of LLM inference makes them infeasible in many such tasks. We propose online cascade learning, the first approach to address this challenge. The objective here is to learn a "cascade" of models, starting with lower-capacity models (such as logistic regression) and ending with a powerful LLM, along with a deferral policy that determines the model to be used on a given input. We formulate the task of learning cascades online as an imitation-learning problem, where smaller models are updated over time imitating the collected LLM demonstrations, and give a no-regret algorithm for the problem. Experimental results across four benchmarks show that our method parallels LLMs in accuracy while cutting down inference costs by as much as 90% with strong robustness against input distribution shifts, underscoring its efficacy and adaptability in stream processing.
Related papers
- S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.
Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
arXiv Detail & Related papers (2025-02-18T13:40:22Z) - Multi-Objective Large Language Model Unlearning [3.372396620898397]
Gradient Ascent (GA) is a proactive way to decrease the prediction probability of the model on the target data.
We propose Multi-Objective Large Language Model Unlearning (MOLLM) algorithm to overcome gradient explosion and catastrophic forgetting.
Our empirical results verify that MoLLM outperforms the SOTA GA-based LLM unlearning methods in terms of unlearning effect and model utility preservation.
arXiv Detail & Related papers (2024-12-29T09:35:56Z) - Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities.
In-Context Learning (ICL) and.
Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting.
LLMs to downstream tasks.
We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
arXiv Detail & Related papers (2024-09-30T10:48:20Z) - Accelerating Large Language Model Pretraining via LFR Pedagogy: Learn, Focus, and Review [50.78587571704713]
Learn-Focus-Review (LFR) is a dynamic training approach that adapts to the model's learning progress.
LFR tracks the model's learning performance across data blocks (sequences of tokens) and prioritizes revisiting challenging regions of the dataset.
Compared to baseline models trained on the full datasets, LFR consistently achieved lower perplexity and higher accuracy.
arXiv Detail & Related papers (2024-09-10T00:59:18Z) - CoMMIT: Coordinated Instruction Tuning for Multimodal Large Language Models [68.64605538559312]
In this paper, we analyze the MLLM instruction tuning from both theoretical and empirical perspectives.
Inspired by our findings, we propose a measurement to quantitatively evaluate the learning balance.
In addition, we introduce an auxiliary loss regularization method to promote updating of the generation distribution of MLLMs.
arXiv Detail & Related papers (2024-07-29T23:18:55Z) - Learning to Reduce: Optimal Representations of Structured Data in
Prompting Large Language Models [42.16047343029512]
Large Language Models (LLMs) have been widely used as general-purpose AI agents.
We propose a framework, Learning to Reduce, that fine-tunes a language model to generate a reduced version of an input context.
We show that our model achieves comparable accuracies in selecting the relevant evidence from an input context.
arXiv Detail & Related papers (2024-02-22T00:41:23Z) - LLM-augmented Preference Learning from Natural Language [19.700169351688768]
Large Language Models (LLMs) are equipped to deal with larger context lengths.
LLMs can consistently outperform the SotA when the target text is large.
Few-shot learning yields better performance than zero-shot learning.
arXiv Detail & Related papers (2023-10-12T17:17:27Z) - Scaling Sentence Embeddings with Large Language Models [43.19994568210206]
In this work, we propose an in-context learning-based method aimed at improving sentence embeddings performance.
Our approach involves adapting the previous prompt-based representation method for autoregressive models.
By scaling model size, we find scaling to more than tens of billion parameters harms the performance on semantic textual similarity tasks.
arXiv Detail & Related papers (2023-07-31T13:26:03Z) - Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM
Inference Pipeline [22.08897444328099]
Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks.
In this paper, we propose an efficient LLM inference pipeline that harnesses the power of LLMs.
arXiv Detail & Related papers (2023-05-22T15:36:06Z) - LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
Large language models (LLMs) have shown remarkable capabilities in language understanding and generation.
We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset.
Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
arXiv Detail & Related papers (2023-05-19T12:10:53Z) - CodeGen2: Lessons for Training LLMs on Programming and Natural Languages [116.74407069443895]
We unify encoder and decoder-based models into a single prefix-LM.
For learning methods, we explore the claim of a "free lunch" hypothesis.
For data distributions, the effect of a mixture distribution and multi-epoch training of programming and natural languages on model performance is explored.
arXiv Detail & Related papers (2023-05-03T17:55:25Z)
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.