Structured Object Language Modeling (SoLM): Native Structured Objects Generation Conforming to Complex Schemas with Self-Supervised Denoising

• URL: http://arxiv.org/abs/2411.19301v1
• Date: Thu, 28 Nov 2024 18:16:41 GMT
• Title: Structured Object Language Modeling (SoLM): Native Structured Objects Generation Conforming to Complex Schemas with Self-Supervised Denoising
• Authors: Amir Tavanaei, Kee Kiat Koo, Hayreddin Ceker, Shaobai Jiang, Qi Li, Julien Han, Karim Bouyarmane,
• Abstract summary: We frame the problem as a Language Modeling problem (Structured Object Language Modeling) We propose a self-supervised denoising method to train the model from an existing dataset of such objects. Experimental results show that the proposed method matches or outperforms prompt-engineered general-purpose state-of-the-art LLMs.
• Score: 7.59750288224997
• License:
• Abstract: In this paper, we study the problem of generating structured objects that conform to a complex schema, with intricate dependencies between the different components (facets) of the object. The facets of the object (attributes, fields, columns, properties) can be a mix of short, structured, type-constrained facts, or long natural-language descriptions. The object has to be self-consistent between the different facets in the redundant information it carries (relative consistency), while being grounded with respect to world knowledge (absolute consistency). We frame the problem as a Language Modeling problem (Structured Object Language Modeling) and train an LLM to perform the task natively, without requiring instructions or prompt-engineering. We propose a self-supervised denoising method to train the model from an existing dataset of such objects. The input query can be the existing object itself, in which case the model acts as a regenerator, completing, correcting, normalizing the input, or any unstructured blurb to be structured. We show that the self-supervised denoising training provides a strong baseline, and that additional supervised fine-tuning with small amount of human demonstrations leads to further improvement. Experimental results show that the proposed method matches or outperforms prompt-engineered general-purpose state-of-the-art LLMs (Claude 3, Mixtral-8x7B), while being order-of-magnitude more cost-efficient.

Related papers

• A Model Is Not Built By A Single Prompt: LLM-Based Domain Modeling With Question Decomposition [4.123601037699469]
  In real-world domain modeling, engineers usually decompose complex tasks into easily solvable sub-tasks. We propose an LLM-based domain modeling approach via question decomposition, similar to developer's modeling process. Preliminary results show that our approach outperforms the single-prompt-based prompt.
  arXiv  Detail & Related papers  (2024-10-13T14:28:04Z)
• A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language [0.0]
  We propose a framework that integrates Natural Language Processing (NLP), Large Language Models (LLMs), and Denoising Diffusion Probabilistic Models (DDPMs) Our framework employs contextual data augmentation, driven by a pretrained LLM, to generate and expand a diverse dataset of microstructure descriptors. A retrained NER model extracts relevant microstructure descriptors from user-provided natural language inputs, which are then used by the DDPM to generate microstructures with targeted mechanical properties and topological features.
  arXiv  Detail & Related papers  (2024-09-22T14:45:22Z)
• Enhancing LLM's Cognition via Structurization [41.13997892843677]
  Large language models (LLMs) process input contexts through a causal and sequential perspective. This paper presents a novel concept of context structurization. Specifically, we transform the plain, unordered contextual sentences into well-ordered and hierarchically structurized elements.
  arXiv  Detail & Related papers  (2024-07-23T12:33:58Z)
• LLMs for Robotic Object Disambiguation [21.101902684740796]
  Our study reveals the LLM's aptitude for solving complex decision making challenges. A pivotal focus of our research is the object disambiguation capability of LLMs. We have developed a few-shot prompt engineering system to improve the LLM's ability to pose disambiguating queries.
  arXiv  Detail & Related papers  (2024-01-07T04:46:23Z)
• Physics of Language Models: Part 1, Learning Hierarchical Language Structures [51.68385617116854]
  Transformer-based language models are effective but complex, and understanding their inner workings is a significant challenge. We introduce a family of synthetic CFGs that produce hierarchical rules, capable of generating lengthy sentences. We demonstrate that generative models like GPT can accurately learn this CFG language and generate sentences based on it.
  arXiv  Detail & Related papers  (2023-05-23T04:28:16Z)
• Neural Constraint Satisfaction: Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement [75.9289887536165]
  We present a hierarchical abstraction approach to uncover underlying entities. We show how to learn a correspondence between intervening on states of entities in the agent's model and acting on objects in the environment. We use this correspondence to develop a method for control that generalizes to different numbers and configurations of objects.
  arXiv  Detail & Related papers  (2023-03-20T18:19:36Z)
• StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objects [35.855172217856726]
  We propose StructDiffusion to build physically-valid structures without step-by-step instructions. Our method can perform multiple challenging language-conditioned multi-step 3D planning tasks. We show experiments on held-out objects in both simulation and on real-world tasks.
  arXiv  Detail & Related papers  (2022-11-08T23:04:49Z)
• Autoregressive Structured Prediction with Language Models [73.11519625765301]
  We describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at.
  arXiv  Detail & Related papers  (2022-10-26T13:27:26Z)
• Complex-Valued Autoencoders for Object Discovery [62.26260974933819]
  We propose a distributed approach to object-centric representations: the Complex AutoEncoder. We show that this simple and efficient approach achieves better reconstruction performance than an equivalent real-valued autoencoder on simple multi-object datasets. We also show that it achieves competitive unsupervised object discovery performance to a SlotAttention model on two datasets, and manages to disentangle objects in a third dataset where SlotAttention fails - all while being 7-70 times faster to train.
  arXiv  Detail & Related papers  (2022-04-05T09:25:28Z)
• Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models [61.480085460269514]
  We propose a framework for building interpretable systems that learn to solve complex tasks by decomposing them into simpler ones solvable by existing models. We use this framework to build ModularQA, a system that can answer multi-hop reasoning questions by decomposing them into sub-questions answerable by a neural factoid single-span QA model and a symbolic calculator.
  arXiv  Detail & Related papers  (2020-09-01T23:45:42Z)
• Look-into-Object: Self-supervised Structure Modeling for Object Recognition [71.68524003173219]
  We propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions. We show the recognition backbone can be substantially enhanced for more robust representation learning. Our approach achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft)
  arXiv  Detail & Related papers  (2020-03-31T12:22:51Z)

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.