Improving Minimum Bayes Risk Decoding with Multi-Prompt

• URL: http://arxiv.org/abs/2407.15343v2
• Date: Thu, 3 Oct 2024 22:14:57 GMT
• Title: Improving Minimum Bayes Risk Decoding with Multi-Prompt
• Authors: David Heineman, Yao Dou, Wei Xu,
• Abstract summary: We propose multi-prompt decoding, where many candidate generations are decoded from a prompt bank at inference-time. To ensemble candidates, we use Minimum Bayes Risk (MBR) decoding, which selects a final output using a trained value metric.
• Score: 10.401677244785166
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: While instruction fine-tuned LLMs are effective text generators, sensitivity to prompt construction makes performance unstable and sub-optimal in practice. Relying on a single "best" prompt cannot capture all differing approaches to a generation problem. Using this observation, we propose multi-prompt decoding, where many candidate generations are decoded from a prompt bank at inference-time. To ensemble candidates, we use Minimum Bayes Risk (MBR) decoding, which selects a final output using a trained value metric. We show multi-prompt improves MBR across a comprehensive set of conditional generation tasks, and show this is a result of estimating a more diverse and higher quality candidate space than that of a single prompt. Further experiments confirm multi-prompt improves generation across tasks, models and metrics.

Related papers

• QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning [58.767866109043055]
  We introduce Query-dependent Prompt Optimization (QPO), which iteratively fine-tune a small pretrained language model to generate optimal prompts tailored to the input queries. We derive insights from offline prompting demonstration data, which already exists in large quantities as a by-product of benchmarking diverse prompts on open-sourced tasks. Experiments on various LLM scales and diverse NLP and math tasks demonstrate the efficacy and cost-efficiency of our method in both zero-shot and few-shot scenarios.
  arXiv  Detail & Related papers  (2024-08-20T03:06:48Z)
• Large Language Models Prompting With Episodic Memory [53.8690170372303]
  We propose PrOmpting with Episodic Memory (POEM), a novel prompt optimization technique that is simple, efficient, and demonstrates strong generalization capabilities. In the testing phase, we optimize the sequence of examples for each test query by selecting the sequence that yields the highest total rewards from the top-k most similar training examples in the episodic memory. Our results show that POEM outperforms recent techniques like TEMPERA and RLPrompt by over 5.3% in various text classification tasks.
  arXiv  Detail & Related papers  (2024-08-14T11:19:28Z)
• MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization [73.7779735046424]
  We show that different prompts should be adapted to different Large Language Models (LLM) to enhance their capabilities across various downstream tasks in NLP. We then propose a model-adaptive prompt (MAPO) method that optimize the original prompts for each specific LLM in downstream tasks.
  arXiv  Detail & Related papers  (2024-07-04T18:39:59Z)
• Task Facet Learning: A Structured Approach to Prompt Optimization [14.223730629357178]
  We propose an algorithm that learns multiple facets of a task from a set of training examples. The resulting algorithm, UniPrompt, consists of a generative model to generate initial candidates for each prompt section. Empirical evaluation on multiple datasets and a real-world task shows that prompts generated using UniPrompt obtain higher accuracy than human-tuned prompts.
  arXiv  Detail & Related papers  (2024-06-15T04:54:26Z)
• Multi-Prompting Decoder Helps Better Language Understanding [23.084538462710125]
  We propose a simple yet effective Multi-Prompting Decoder (MPD) framework for MaaS adaptation. Our method achieves new state-of-the-art results on multiple natural language understanding datasets under the few-shot setting.
  arXiv  Detail & Related papers  (2024-06-10T13:58:46Z)
• 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)
• Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding [4.209844101827474]
  We develop diversity-promoting decoding algorithms by enforcing diversity objectives to Minimum Bayes-Risk decoding. We evaluate DMBR and KMBR on a variety of directed text generation tasks using encoder-decoder models and a large language model with prompting.
  arXiv  Detail & Related papers  (2024-01-10T10:23:41Z)
• RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning [84.75064077323098]
  This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL) RLPrompt is flexibly applicable to different types of LMs, such as masked gibberish (e.g., grammaBERT) and left-to-right models (e.g., GPTs) Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing finetuning or prompting methods.
  arXiv  Detail & Related papers  (2022-05-25T07:50:31Z)
• IDPG: An Instance-Dependent Prompt Generation Method [58.45110542003139]
  Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage. We propose a conditional prompt generation method to generate prompts for each input instance.
  arXiv  Detail & Related papers  (2022-04-09T15:45:27Z)

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.