Monotonic Paraphrasing Improves Generalization of Language Model Prompting
- URL: http://arxiv.org/abs/2403.16038v2
- Date: Thu, 18 Apr 2024 05:22:01 GMT
- Title: Monotonic Paraphrasing Improves Generalization of Language Model Prompting
- Authors: Qin Liu, Fei Wang, Nan Xu, Tianyi Yan, Tao Meng, Muhao Chen,
- Abstract summary: MonoPara is an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts.
It does not require any training and can monotonically lower the perplexity of the paraphrased prompt or instruction.
It is also shown to effectively improve LMs' generalization on perturbed and unseen task instructions.
- Score: 42.74429247000797
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Performance of large language models (LLMs) may vary with different prompts or instructions of even the same task. One commonly recognized factor for this phenomenon is the model's familiarity with the given prompt or instruction, which is typically estimated by its perplexity. However, finding the prompt with the lowest perplexity is challenging, given the enormous space of possible prompting phrases. In this paper, we propose monotonic paraphrasing (MonoPara), an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt (or instruction) rewriting, and a target LM (i.e. the prompt or instruction executor) that constrains the generation for lower perplexity. The ensemble decoding process can efficiently paraphrase the original prompt without altering its semantic meaning, while monotonically decreasing the perplexity of each generation as calculated by the target LM. We explore in detail both greedy and search-based decoding as two alternative decoding schemes of MonoPara. Notably, MonoPara does not require any training and can monotonically lower the perplexity of the paraphrased prompt or instruction, leading to improved performance of zero-shot LM prompting as evaluated on a wide selection of tasks. In addition, MonoPara is also shown to effectively improve LMs' generalization on perturbed and unseen task instructions.
Related papers
- Set-Based Prompting: Provably Solving the Language Model Order Dependency Problem [18.020492646988746]
We present Set-Based Prompting, a technique that guarantees the output of an LLM will not have order dependence on a specified set of sub-sequences.
Despite our inputs being out of distribution, the impact on expected accuracy is small, where the expectation is over the order of uniformly chosen shuffling of the candidate responses.
arXiv Detail & Related papers (2024-06-04T16:09:13Z) - Contrastive Instruction Tuning [61.97704869248903]
We propose Contrastive Instruction Tuning to maximize the similarity between semantically equivalent instruction-instance pairs.
Experiments on the PromptBench benchmark show that CoIN consistently improves LLMs' robustness to unseen instructions with variations across character, word, sentence, and semantic levels by an average of +2.5% in accuracy.
arXiv Detail & Related papers (2024-02-17T00:09:32Z) - A Prompt Learning Framework for Source Code Summarization [24.33455799484519]
We propose a novel prompt learning framework for code summarization called PromptCS.
PromptCS trains a prompt agent that can generate continuous prompts to unleash the potential for LLMs in code summarization.
We evaluate PromptCS on the CodeSearchNet dataset involving multiple programming languages.
arXiv Detail & Related papers (2023-12-26T14:37:55Z) - Prompt Sketching for Large Language Models [7.687678490751105]
Recent prompting strategies for large language models (LLMs) query the model multiple times sequentially.
This leads to disconnected and undesirably wordy intermediate responses.
We propose prompt sketching, a new prompting paradigm in which an LLM does not only respond by completing a prompt, but by predicting values for multiple variables in a template.
arXiv Detail & Related papers (2023-11-08T18:57:23Z) - Instruction Position Matters in Sequence Generation with Large Language
Models [67.87516654892343]
Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization.
We propose enhancing the instruction-following capability of LLMs by shifting the position of task instructions after the input sentences.
arXiv Detail & Related papers (2023-08-23T12:36:57Z) - Self-regulating Prompts: Foundational Model Adaptation without
Forgetting [112.66832145320434]
We introduce a self-regularization framework for prompting called PromptSRC.
PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations.
arXiv Detail & Related papers (2023-07-13T17:59:35Z) - 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) - 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.