Large Language Models as Innovators: A Framework to Leverage Latent Space Exploration for Novelty Discovery

• URL: http://arxiv.org/abs/2507.13874v1
• Date: Fri, 18 Jul 2025 12:54:28 GMT
• Title: Large Language Models as Innovators: A Framework to Leverage Latent Space Exploration for Novelty Discovery
• Authors: Mateusz Bystroński, Mikołaj Hołysz, Grzegorz Piotrowski, Nitesh V. Chawla, Tomasz Kajdanowicz,
• Abstract summary: Large language models (LLMs) often struggle to produce outputs that are both novel and relevant.<n>We propose a model-agnostic latent-space ideation framework that enables controlled, scalable creativity.
• Score: 19.394116388173885
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Innovative idea generation remains a core challenge in AI, as large language models (LLMs) often struggle to produce outputs that are both novel and relevant. Despite their fluency, LLMs tend to replicate patterns seen during training, limiting their ability to diverge creatively without extensive prompt engineering. Prior work has addressed this through domain-specific heuristics and structured prompting pipelines, but such solutions are brittle and difficult to generalize. In this paper, we propose a model-agnostic latent-space ideation framework that enables controlled, scalable creativity by navigating the continuous embedding space of ideas. Unlike prior methods, our framework requires no handcrafted rules and adapts easily to different domains, input formats, and creative tasks. This paper introduces an early-stage prototype of our method, outlining the conceptual framework and preliminary results highlighting its potential as a general-purpose co-ideator for human-AI collaboration.

Related papers

• Breaking Thought Patterns: A Multi-Dimensional Reasoning Framework for LLMs [3.5056249219229296]
  Large language models (LLMs) are often constrained by rigid reasoning processes, limiting their ability to generate creative responses.<n>To address this, a novel framework called LADDER is proposed, combining Chain-of-Thought (CoT) reasoning, Mixture of Experts (MoE) models, and multi-dimensional up/down-sampling strategies.
  arXiv  Detail & Related papers  (2025-06-16T07:59:51Z)
• ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges [72.19809898215857]
  We introduce ModelingBench, a novel benchmark featuring real-world-inspired, open-ended problems from math modeling competitions across diverse domains.<n>These tasks require translating natural language into formal mathematical formulations, applying appropriate tools, and producing structured, defensible reports.<n>We also present ModelingAgent, a multi-agent framework that coordinates tool use, supports structured, creative solutions, and generates well-grounded, creative solutions.
  arXiv  Detail & Related papers  (2025-05-21T03:33:23Z)
• Large Language Models Post-training: Surveying Techniques from Alignment to Reasoning [185.51013463503946]
  Large Language Models (LLMs) have fundamentally transformed natural language processing, making them indispensable across domains ranging from conversational systems to scientific exploration.<n>These challenges necessitate advanced post-training language models (PoLMs) to address shortcomings, such as restricted reasoning capacities, ethical uncertainties, and suboptimal domain-specific performance.<n>This paper presents the first comprehensive survey of PoLMs, systematically tracing their evolution across five core paradigms: Fine-tuning, which enhances task-specific accuracy; Alignment, which ensures ethical coherence and alignment with human preferences; Reasoning, which advances multi-step inference despite challenges in reward design; Integration and Adaptation, which
  arXiv  Detail & Related papers  (2025-03-08T05:41:42Z)
• LLM-Generated Heuristics for AI Planning: Do We Even Need Domain-Independence Anymore? [87.71321254733384]
  Large language models (LLMs) can generate planning approaches tailored to specific planning problems.<n>LLMs can achieve state-of-the-art performance on some standard IPC domains.<n>We discuss whether these results signify a paradigm shift and how they can complement existing planning approaches.
  arXiv  Detail & Related papers  (2025-01-30T22:21:12Z)
• A Novel Idea Generation Tool using a Structured Conversational AI (CAI) System [0.0]
  This paper presents a novel conversational AI-enabled active ideation interface as a creative idea-generation tool to assist novice designers. It is a dynamic, interactive, and contextually responsive approach, actively involving a large language model (LLM) from the domain of natural language processing (NLP) in artificial intelligence (AI) Integrating such AI models with ideation creates what we refer to as an Active Ideation scenario, which helps foster continuous dialogue-based interaction, context-sensitive conversation, and prolific idea generation.
  arXiv  Detail & Related papers  (2024-09-09T16:02:27Z)
• Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models [3.0566617373924325]
  Sentence embedding is a fundamental task within the realm of Natural Language Processing, finding extensive application in search engines, expert systems, and question-and-answer platforms. With the continuous evolution of large language models such as LLaMA and Mistral, research on sentence embedding has recently achieved notable breakthroughs. We propose two innovative prompt engineering techniques capable of further enhancing the expressive power of PLMs' raw embeddings.
  arXiv  Detail & Related papers  (2024-04-05T07:07:15Z)
• On the Challenges and Opportunities in Generative AI [157.96723998647363]
  We argue that current large-scale generative AI models exhibit several fundamental shortcomings that hinder their widespread adoption across domains.<n>We aim to provide researchers with insights for exploring fruitful research directions, thus fostering the development of more robust and accessible generative AI solutions.
  arXiv  Detail & Related papers  (2024-02-28T15:19:33Z)
• Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation [19.62178304006683]
  We argue that current interaction paradigms fall short, guiding users towards rapid convergence on a limited set of ideas. We propose a framework that facilitates the structured generation of design space in which users can seamlessly explore, evaluate, and synthesize a multitude of responses.
  arXiv  Detail & Related papers  (2023-10-19T17:53:14Z)
• Re-Reading Improves Reasoning in Large Language Models [87.46256176508376]
  We introduce a simple, yet general and effective prompting method, Re2, to enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs) Unlike most thought-eliciting prompting methods, such as Chain-of-Thought (CoT), Re2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. We evaluate Re2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality.
  arXiv  Detail & Related papers  (2023-09-12T14:36:23Z)
• ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints [56.824187892204314]
  We present the task of creative text-to-image generation, where we seek to generate new members of a broad category. We show that the creative generation problem can be formulated as an optimization process over the output space of the diffusion prior. We incorporate a question-answering Vision-Language Model (VLM) that adaptively adds new constraints to the optimization problem, encouraging the model to discover increasingly more unique creations.
  arXiv  Detail & Related papers  (2023-08-03T17:04:41Z)
• Challenges in creative generative models for music: a divergence maximization perspective [3.655021726150369]
  Development of generative Machine Learning models in creative practices is raising more interest among artists, practitioners and performers. Most models are still unable to generate content that lay outside of the domain defined by the training dataset. We propose an alternative prospective framework, starting from a new general formulation of ML objectives.
  arXiv  Detail & Related papers  (2022-11-16T12:02:43Z)
• WenLan 2.0: Make AI Imagine via a Multimodal Foundation Model [74.4875156387271]
  We develop a novel foundation model pre-trained with huge multimodal (visual and textual) data. We show that state-of-the-art results can be obtained on a wide range of downstream tasks.
  arXiv  Detail & Related papers  (2021-10-27T12:25:21Z)

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.