Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction

• URL: http://arxiv.org/abs/2504.15266v1
• Date: Mon, 21 Apr 2025 17:47:46 GMT
• Title: Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
• Authors: Vaishnavh Nagarajan, Chen Henry Wu, Charles Ding, Aditi Raghunathan,
• Abstract summary: We design a suite of minimal algorithmic tasks that are a loose abstraction of open-ended real-world tasks.<n>Our work offers a principled, minimal test-bed for analyzing open-ended creative skills.
• Score: 20.432182363429977
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We design a suite of minimal algorithmic tasks that are a loose abstraction of open-ended real-world tasks. This allows us to cleanly and controllably quantify the creative limits of the present-day language model. Much like real-world tasks that require a creative, far-sighted leap of thought, our tasks require an implicit, open-ended stochastic planning step that either (a) discovers new connections in an abstract knowledge graph (like in wordplay, drawing analogies, or research) or (b) constructs new patterns (like in designing math problems or new proteins). In these tasks, we empirically and conceptually argue how next-token learning is myopic and memorizes excessively; comparatively, multi-token approaches, namely teacherless training and diffusion models, excel in producing diverse and original output. Secondly, in our tasks, we find that to elicit randomness from the Transformer without hurting coherence, it is better to inject noise right at the input layer (via a method we dub hash-conditioning) rather than defer to temperature sampling from the output layer. Thus, our work offers a principled, minimal test-bed for analyzing open-ended creative skills, and offers new arguments for going beyond next-token learning and softmax-based sampling. We make part of the code available under https://github.com/chenwu98/algorithmic-creativity

Related papers

• Large Concept Models: Language Modeling in a Sentence Representation Space [62.73366944266477]
  We present an attempt at an architecture which operates on an explicit higher-level semantic representation, which we name a concept.<n> Concepts are language- and modality-agnostic and represent a higher level idea or action in a flow.<n>We show that our model exhibits impressive zero-shot generalization performance to many languages.
  arXiv  Detail & Related papers  (2024-12-11T23:36:20Z)
• Brain-Inspired Two-Stage Approach: Enhancing Mathematical Reasoning by Imitating Human Thought Processes [6.512667145063511]
  We propose a novel approach, named Brain, to imitate human thought processes to enhance mathematical reasoning abilities. First, we achieve SOTA performance in comparison with Code LLaMA 7B based models through this method. Secondly, we find that plans can be explicitly extracted from natural language, code, or formal language.
  arXiv  Detail & Related papers  (2024-02-23T17:40:31Z)
• Reverse Stable Diffusion: What prompt was used to generate this image? [73.10116197883303]
  We study the task of predicting the prompt embedding given an image generated by a generative diffusion model. We propose a novel learning framework comprising a joint prompt regression and multi-label vocabulary classification objective. We conduct experiments on the DiffusionDB data set, predicting text prompts from images generated by Stable Diffusion.
  arXiv  Detail & Related papers  (2023-08-02T23:39:29Z)
• Momentum Decoding: Open-ended Text Generation As Graph Exploration [49.812280360794894]
  Open-ended text generation with autoregressive language models (LMs) is one of the core tasks in natural language processing. We formulate open-ended text generation from a new perspective, i.e., we view it as an exploration process within a directed graph. We propose a novel decoding method -- textitmomentum decoding -- which encourages the LM to explore new nodes outside the current graph.
  arXiv  Detail & Related papers  (2022-12-05T11:16:47Z)
• Text and Patterns: For Effective Chain of Thought, It Takes Two to Tango [11.344587937052697]
  This work initiates the preliminary steps towards a deeper understanding of reasoning mechanisms in large language models. Our work centers around querying the model while controlling for all but one of the components in a prompt: symbols, patterns, and text. We posit that text imbues patterns with commonsense knowledge and meaning.
  arXiv  Detail & Related papers  (2022-09-16T02:54:00Z)
• Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models [8.166629393064097]
  The ability to extrapolate, i.e., to make predictions on sequences that are longer than those presented as training examples, is a challenging problem for deep learning models. Recent work shows that this limitation persists in state-of-the-art Transformer-based models. We demonstrate that large language models can succeed in extrapolation without modifying their architecture or training procedure.
  arXiv  Detail & Related papers  (2022-08-24T11:25:27Z)
• Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation [79.60988242843437]
  We propose a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously. Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than supervised learning based state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-18T07:18:25Z)
• Fine-Grained Visual Entailment [51.66881737644983]
  We propose an extension of this task, where the goal is to predict the logical relationship of fine-grained knowledge elements within a piece of text to an image. Unlike prior work, our method is inherently explainable and makes logical predictions at different levels of granularity. We evaluate our method on a new dataset of manually annotated knowledge elements and show that our method achieves 68.18% accuracy at this challenging task.
  arXiv  Detail & Related papers  (2022-03-29T16:09:38Z)
• Coarse-to-Fine Curriculum Learning [26.213618168827026]
  We propose a novel curriculum learning approach which decomposes challenging tasks into sequences of easier intermediate goals. We focus on classification tasks, and design the intermediate tasks using an automatically constructed label hierarchy. We show significant performance gains especially on classification problems with many labels.
  arXiv  Detail & Related papers  (2021-06-08T03:09:38Z)
• MetaKernel: Learning Variational Random Features with Limited Labels [120.90737681252594]
  Few-shot learning deals with the fundamental and challenging problem of learning from a few annotated samples, while being able to generalize well on new tasks. We propose meta-learning kernels with random Fourier features for few-shot learning, we call Meta Kernel.
  arXiv  Detail & Related papers  (2021-05-08T21:24:09Z)
• COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning [78.13740204156858]
  We show that we can reuse prior data to extend new skills simply through dynamic programming. We demonstrate the effectiveness of our approach by chaining together several behaviors seen in prior datasets for solving a new task. We train our policies in an end-to-end fashion, mapping high-dimensional image observations to low-level robot control commands.
  arXiv  Detail & Related papers  (2020-10-27T17:57:29Z)
• Deep Reinforcement Learning for Complex Manipulation Tasks with Sparse Feedback [0.0]
  Hindsight Experience Replay (HER) is a multi-goal reinforcement learning algorithm. We present three algorithms based on the existing HER algorithm that improves its performances.
  arXiv  Detail & Related papers  (2020-01-12T07:22:15Z)

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.