Improving Structural Diversity of Blackbox LLMs via Chain-of-Specification Prompting
- URL: http://arxiv.org/abs/2408.06186v1
- Date: Mon, 12 Aug 2024 14:34:06 GMT
- Title: Improving Structural Diversity of Blackbox LLMs via Chain-of-Specification Prompting
- Authors: Halley Young, Yimeng Zeng, Jacob Gardner, Osbert Bastani,
- Abstract summary: We propose a diversity metric called structural diversity, where the user provides a mapping from generated text to features capturing the kinds of diversity that they care about.
In our experiments, we show that for structural diversity in the poetry and code domains, CoS significantly improves diversity compared to several baselines.
- Score: 28.971248570622603
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The capability to generate diverse text is a key challenge facing large language models (LLMs). Thus far, diversity has been studied via metrics such as $n$-gram diversity or diversity of BERT embeddings. However, for these kinds of diversity, the user has little control over the dimensions along which diversity is considered. For example, in the poetry domain, one might desire diversity in terms of rhyme and meter, whereas in the code domain, one might desire diversity in terms of the kinds of expressions used to solve a problem. We propose a diversity metric called structural diversity, where the user provides a mapping from generated text to features capturing the kinds of diversity that they care about. In addition, we propose a novel strategy called chain-of-specification (CoS) prompting for improving diversity by first having the LLM generate a specification encoding one instance of structural features, and then prompting the LLM to generate text that satisfies these features; notably, our strategy works with blackbox LLMs. In our experiments, we show that for structural diversity in the poetry and code domains, CoS significantly improves diversity compared to several baselines.
Related papers
- Exploring and Controlling Diversity in LLM-Agent Conversation [17.38671584773247]
We propose Adaptive Prompt Pruning (APP), a novel method that dynamically adjusts the content of the utterance generation prompt to control diversity.
APP effectively controls the output diversity across models and datasets, with pruning more information leading to more diverse output.
APP is compatible with established techniques like temperature sampling and top-p sampling, providing a versatile tool for diversity management.
arXiv Detail & Related papers (2024-12-30T17:25:58Z) - Improving Linguistic Diversity of Large Language Models with Possibility Exploration Fine-Tuning [23.456302461693053]
Possibility Exploration Fine-Tuning (PEFT) is a task-agnostic framework that enhances the text diversity of Large Language Models (LLMs) without increasing latency or computational cost.
PEFT significantly enhances the diversity of LLM outputs, as evidenced by lower similarity between candidate responses.
It can also notably reduce demographic bias in dialogue systems.
arXiv Detail & Related papers (2024-12-04T14:23:16Z) - Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting [9.116108409344177]
The source-free cross-domain few-shot learning task aims to transfer pretrained models to target domains utilizing minimal samples.
We propose the SeGD-VPT framework, which is divided into two phases.
The first step aims to increase feature diversity by adding diversity prompts to each support sample, thereby generating varying input and enhancing sample diversity.
arXiv Detail & Related papers (2024-12-01T11:00:38Z) - Meta-Task Prompting Elicits Embeddings from Large Language Models [54.757445048329735]
We introduce a new unsupervised text embedding method, Meta-Task Prompting with Explicit One-Word Limitation.
We generate high-quality sentence embeddings from Large Language Models without the need for model fine-tuning.
Our findings suggest a new scaling law, offering a versatile and resource-efficient approach for embedding generation across diverse scenarios.
arXiv Detail & Related papers (2024-02-28T16:35:52Z) - Diversify Question Generation with Retrieval-Augmented Style Transfer [68.00794669873196]
We propose RAST, a framework for Retrieval-Augmented Style Transfer.
The objective is to utilize the style of diverse templates for question generation.
We develop a novel Reinforcement Learning (RL) based approach that maximizes a weighted combination of diversity reward and consistency reward.
arXiv Detail & Related papers (2023-10-23T02:27:31Z) - ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple
yet General Complementary Transformer [91.43066633305662]
We propose a novel underlineComPlementary underlinetransformer, textbfComPtr, for diverse bi-source dense prediction tasks.
ComPtr treats different inputs equally and builds an efficient dense interaction model in the form of sequence-to-sequence on top of the transformer.
arXiv Detail & Related papers (2023-07-23T15:17:45Z) - A Unified Algorithm Framework for Unsupervised Discovery of Skills based
on Determinantal Point Process [53.86223883060367]
We show that diversity and coverage in unsupervised option discovery can indeed be unified under the same mathematical framework.
Our proposed algorithm, ODPP, has undergone extensive evaluation on challenging tasks created with Mujoco and Atari.
arXiv Detail & Related papers (2022-12-01T01:40:03Z) - Neural Text Generation with Part-of-Speech Guided Softmax [82.63394952538292]
We propose using linguistic annotation, i.e., part-of-speech (POS), to guide the text generation.
We show that our proposed methods can generate more diverse text while maintaining comparable quality.
arXiv Detail & Related papers (2021-05-08T08:53:16Z) - Evaluating the Evaluation of Diversity in Natural Language Generation [43.05127848086264]
We propose a framework for evaluating diversity metrics in natural language generation systems.
Our framework can advance the understanding of different diversity metrics, an essential step on the road towards better NLG systems.
arXiv Detail & Related papers (2020-04-06T20:44:10Z)
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.