Query-Dependent Prompt Evaluation and Optimization with Offline Inverse
RL
- URL: http://arxiv.org/abs/2309.06553v4
- Date: Thu, 7 Mar 2024 16:12:21 GMT
- Title: Query-Dependent Prompt Evaluation and Optimization with Offline Inverse
RL
- Authors: Hao Sun, Alihan H\"uy\"uk, Mihaela van der Schaar
- Abstract summary: We aim to enhance arithmetic reasoning ability of Large Language Models (LLMs) through zero-shot prompt optimization.
We identify a previously overlooked objective of query dependency in such optimization.
We introduce Prompt-OIRL, which harnesses offline inverse reinforcement learning to draw insights from offline prompting demonstration data.
- Score: 62.824464372594576
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In this study, we aim to enhance the arithmetic reasoning ability of Large
Language Models (LLMs) through zero-shot prompt optimization. We identify a
previously overlooked objective of query dependency in such optimization and
elucidate two ensuing challenges that impede the successful and economical
design of prompt optimization techniques. One primary issue is the absence of
an effective method to evaluate prompts during inference when the golden answer
is unavailable. Concurrently, learning via interactions with the LLMs to
navigate the expansive natural language prompting space proves to be
resource-intensive. To address this, we introduce Prompt-OIRL, which harnesses
offline inverse reinforcement learning to draw insights from offline prompting
demonstration data. Such data exists as by-products when diverse prompts are
benchmarked on open-accessible datasets. With Prompt-OIRL, the query-dependent
prompt optimization objective is achieved by first learning an offline reward
model. This model can evaluate any query-prompt pairs without accessing LLMs.
Subsequently, a best-of-N strategy is deployed to recommend the optimal prompt.
Our experimental evaluations across various LLM scales and arithmetic reasoning
datasets underscore both the efficacy and economic viability of the proposed
approach.
Related papers
- Self-Supervised Prompt Optimization [16.06653117043314]
Well-designed prompts are crucial for enhancing Large language models' (LLMs) reasoning capabilities.
Existing prompt optimization methods rely heavily on external references such as ground truth or by humans.
We propose Self-Supervised Prompt Optimization (SPO), a cost-efficient framework that discovers effective prompts for both closed and open-ended tasks.
arXiv Detail & Related papers (2025-02-07T17:45:16Z) - Eliciting Causal Abilities in Large Language Models for Reasoning Tasks [14.512834333917414]
We introduce the Self-Causal Instruction Enhancement (SCIE) method, which enables LLMs to generate high-quality, low-quantity observational data.
In SCIE, the instructions are treated as the treatment, and textual features are used to process natural language.
Our method effectively generates instructions that enhance reasoning performance with reduced training cost of prompts.
arXiv Detail & Related papers (2024-12-19T17:03:02Z) - A Systematic Examination of Preference Learning through the Lens of Instruction-Following [83.71180850955679]
We use a novel synthetic data generation pipeline to generate 48,000 instruction unique-following prompts.
With our synthetic prompts, we use two preference dataset curation methods - rejection sampling (RS) and Monte Carlo Tree Search (MCTS)
Experiments reveal that shared prefixes in preference pairs, as generated by MCTS, provide marginal but consistent improvements.
High-contrast preference pairs generally outperform low-contrast pairs; however, combining both often yields the best performance.
arXiv Detail & Related papers (2024-12-18T15:38:39Z) - 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) - 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) - PhaseEvo: Towards Unified In-Context Prompt Optimization for Large
Language Models [9.362082187605356]
We present PhaseEvo, an efficient automatic prompt optimization framework that combines the generative capability of LLMs with the global search proficiency of evolution algorithms.
PhaseEvo significantly outperforms the state-of-the-art baseline methods by a large margin whilst maintaining good efficiency.
arXiv Detail & Related papers (2024-02-17T17:47:10Z) - Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs.
Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
arXiv Detail & Related papers (2023-02-22T17:44:15Z) - 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)
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.