paper-with-me

Papers

On Elastic Language Models

2023-11-13 · Chen Zhang, Benyou Wang, Dawei Song

Large-scale pretrained language models have achieved compelling performance in a wide range of language understanding and information retrieval tasks. Knowledge distillation offers an opportunity to compress a large language model to a small one, in order to reach a reasonable latency-performance tradeoff. However, for scenarios where the number of requests (e.g., queries submitted to a search engine) is highly variant, the static tradeoff attained by the compressed language model might not always fit. Once a model is assigned with a static tradeoff, it could be inadequate in that the latency is too high when the number of requests is large or the performance is too low when the number of requests is small. To this end, we propose an elastic language model (ElasticLM) that elastically adjusts the tradeoff according to the request stream. The basic idea is to introduce a compute elasticity to the compressed language model, so that the tradeoff could vary on-the-fly along scalable and controllable compute. Specifically, we impose an elastic structure to enable ElasticLM with compute elasticity and design an elastic optimization to learn ElasticLM under compute elasticity. To serve ElasticLM, we apply an elastic schedule. Considering the specificity of information retrieval, we adapt ElasticLM to dense retrieval and reranking and present ElasticDenser and ElasticRanker respectively. Offline evaluation is conducted on a language understanding benchmark GLUE; and several information retrieval tasks including Natural Question, Trivia QA, and MS MARCO. The results show that ElasticLM along with ElasticDenser and ElasticRanker can perform correctly and competitively compared with an array of static baselines. Furthermore, online simulation with concurrency is also carried out. The results demonstrate that ElasticLM can provide elastic tradeoffs with respect to varying request stream.

📄 PDF Abstract BibTeX arXiv:2311.07204

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalKnowledge DistillationLanguage ModelingLanguage ModellingLarge Language ModelRerankingRetrievalSpecificity

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control

2026-05-08 · Ali Taghibakhshi, Ruisi Cai, Saurav Muralidharan, Sharath Turuvekere Sreenivas 외 arxiv

Training a family of large language models (LLMs), either from scratch or via iterative compression, is prohibitively expensive and inefficient, requiring separate training runs for each model in the family. In this pape…

Knowledge Distillation

ELMS: Elasticized Large Language Models On Mobile Devices

2024-09-08 · Wangsong Yin, Rongjie Yi, Daliang Xu, Gang Huang 외

On-device Large Language Models (LLMs) are revolutionizing mobile AI, enabling applications such as UI automation while addressing privacy concerns. Currently, the standard approach involves deploying a single, robust LL…

GPULanguage Modelling

SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms

2024-06-05 · Xingrun Xing, Zheng Zhang, Ziyi Ni, Shitao Xiao 외

Towards energy-efficient artificial intelligence similar to the human brain, the bio-inspired spiking neural networks (SNNs) have advantages of biological plausibility, event-driven sparsity, and binary activation. Recen…

Language ModelingLanguage Modelling

Language Model Alignment with Elastic Reset

2023-12-06 · NeurIPS 2023 11 · Michael Noukhovitch, Samuel Lavoie, Florian Strub, Aaron Courville

Finetuning language models with reinforcement learning (RL), e.g. from human feedback (HF), is a prominent method for alignment. But optimizing against a reward model can improve on reward while degrading performance in …

ChatbotLanguage ModelingLanguage Modellingmodel+1

ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism

2025-07-14 · Zedong Liu, Shenggan Cheng, Guangming Tan, Yang You 외 arxiv

Multimodal large language models (MLLMs) extend LLMs to handle images, videos, and audio by incorporating feature extractors and projection modules. However, these additional components -- combined with complex inference…