On Elastic Language Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalKnowledge DistillationLanguage ModelingLanguage ModellingLarge Language ModelRerankingRetrievalSpecificityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control
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 DistillationELMS: Elasticized Large Language Models On Mobile Devices
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 ModellingSpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms
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 ModellingLanguage Model Alignment with Elastic Reset
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+1ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism
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…