Language Models as a Service: Overview of a New Paradigm and its Challenges

• URL: http://arxiv.org/abs/2309.16573v2
• Date: Thu, 30 Nov 2023 07:59:26 GMT
• Title: Language Models as a Service: Overview of a New Paradigm and its Challenges
• Authors: Emanuele La Malfa, Aleksandar Petrov, Simon Frieder, Christoph Weinhuber, Ryan Burnell, Raza Nazar, Anthony G. Cohn, Nigel Shadbolt, Michael Wooldridge
• Abstract summary: Some of the most powerful language models currently are proprietary systems, accessible only via (typically restrictive) web or programming. This paper has two goals: on the one hand, we delineate how the aforementioned challenges act as impediments to the accessibility, replicability, reliability, and trustworthiness of LM interfaces. On the other hand, it serves as a comprehensive resource for existing knowledge on current, major LM, offering a synthesized overview of the licences and capabilities their interfaces offer.
• Score: 47.75762014254756
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Some of the most powerful language models currently are proprietary systems, accessible only via (typically restrictive) web or software programming interfaces. This is the Language-Models-as-a-Service (LMaaS) paradigm. In contrast with scenarios where full model access is available, as in the case of open-source models, such closed-off language models present specific challenges for evaluating, benchmarking, and testing them. This paper has two goals: on the one hand, we delineate how the aforementioned challenges act as impediments to the accessibility, replicability, reliability, and trustworthiness of LMaaS. We systematically examine the issues that arise from a lack of information about language models for each of these four aspects. We conduct a detailed analysis of existing solutions and put forth a number of considered recommendations, and highlight the directions for future advancements. On the other hand, it serves as a comprehensive resource for existing knowledge on current, major LMaaS, offering a synthesized overview of the licences and capabilities their interfaces offer.

Related papers

• Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities [89.40778301238642]
  Model merging is an efficient empowerment technique in the machine learning community. There is a significant gap in the literature regarding a systematic and thorough review of these techniques.
  arXiv  Detail & Related papers  (2024-08-14T16:58:48Z)
• LangSuitE: Planning, Controlling and Interacting with Large Language Models in Embodied Text Environments [70.91258869156353]
  We introduce LangSuitE, a versatile and simulation-free testbed featuring 6 representative embodied tasks in textual embodied worlds. Compared with previous LLM-based testbeds, LangSuitE offers adaptability to diverse environments without multiple simulation engines. We devise a novel chain-of-thought (CoT) schema, EmMem, which summarizes embodied states w.r.t. history information.
  arXiv  Detail & Related papers  (2024-06-24T03:36:29Z)
• L2CEval: Evaluating Language-to-Code Generation Capabilities of Large Language Models [102.00201523306986]
  We present L2CEval, a systematic evaluation of the language-to-code generation capabilities of large language models (LLMs) We analyze the factors that potentially affect their performance, such as model size, pretraining data, instruction tuning, and different prompting methods. In addition to assessing model performance, we measure confidence calibration for the models and conduct human evaluations of the output programs.
  arXiv  Detail & Related papers  (2023-09-29T17:57:00Z)
• Foundational Models Defining a New Era in Vision: A Survey and Outlook [151.49434496615427]
  Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The models learned to bridge the gap between such modalities coupled with large-scale training data facilitate contextual reasoning, generalization, and prompt capabilities at test time. The output of such models can be modified through human-provided prompts without retraining, e.g., segmenting a particular object by providing a bounding box, having interactive dialogues by asking questions about an image or video scene or manipulating the robot's behavior through language instructions.
  arXiv  Detail & Related papers  (2023-07-25T17:59:18Z)
• A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models [43.35892536887404]
  Prompt engineering involves augmenting a large pre-trained model with task-specific hints, known as prompts, to adapt the model to new tasks. This paper aims to provide a comprehensive survey of cutting-edge research in prompt engineering on three types of vision-language models.
  arXiv  Detail & Related papers  (2023-07-24T17:58:06Z)
• Foundation Models for Decision Making: Problems, Methods, and Opportunities [124.79381732197649]
  Foundation models pretrained on diverse data at scale have demonstrated extraordinary capabilities in a wide range of vision and language tasks. New paradigms are emerging for training foundation models to interact with other agents and perform long-term reasoning. Research at the intersection of foundation models and decision making holds tremendous promise for creating powerful new systems.
  arXiv  Detail & Related papers  (2023-03-07T18:44:07Z)
• Foundation Models for Natural Language Processing -- Pre-trained Language Models Integrating Media [0.0]
  Foundation Models are pre-trained language models for Natural Language Processing. They can be applied to a wide range of different media and problem domains, ranging from image and video processing to robot control learning. This book provides a comprehensive overview of the state of the art in research and applications of Foundation Models.
  arXiv  Detail & Related papers  (2023-02-16T20:42:04Z)
• An Overview on Controllable Text Generation via Variational Auto-Encoders [15.97186478109836]
  Recent advances in neural-based generative modeling have reignited the hopes of having computer systems capable of conversing with humans. Latent variable models (LVM) such as variational auto-encoders (VAEs) are designed to characterize the distributional pattern of textual data. This overview gives an introduction to existing generation schemes, problems associated with text variational auto-encoders, and a review of several applications about the controllable generation.
  arXiv  Detail & Related papers  (2022-11-15T07:36:11Z)
• On the Universality of Deep COntextual Language Models [15.218264849664715]
  Deep Contextual Language Models (LMs) like ELMO, BERT, and their successors dominate the landscape of Natural Language Processing. Multilingual versions of such models like XLM-R and mBERT have given promising results in zero-shot cross-lingual transfer. Due to this initial success, pre-trained models are being used as Universal Language Models'
  arXiv  Detail & Related papers  (2021-09-15T08:00:33Z)
• Combining pre-trained language models and structured knowledge [9.521634184008574]
  transformer-based language models have achieved state of the art performance in various NLP benchmarks. It has proven challenging to integrate structured information, such as knowledge graphs into these models. We examine a variety of approaches to integrate structured knowledge into current language models and determine challenges, and possible opportunities to leverage both structured and unstructured information sources.
  arXiv  Detail & Related papers  (2021-01-28T21:54:03Z)

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.