Discrete Prompt Optimization via Constrained Generation for Zero-shot
Re-ranker
- URL: http://arxiv.org/abs/2305.13729v1
- Date: Tue, 23 May 2023 06:35:33 GMT
- Title: Discrete Prompt Optimization via Constrained Generation for Zero-shot
Re-ranker
- Authors: Sukmin Cho, Soyeong Jeong, Jeongyeon Seo and Jong C. Park
- Abstract summary: Large-scale language model (LLM) is utilized as a zero-shot re-ranker with excellent results.
LLM is highly dependent on the prompts, the impact and the optimization of the prompts for the zero-shot re-ranker are not explored yet.
We propose a novel discrete prompt optimization method, Constrained Prompt generation (Co-Prompt), with the metric estimating the optimum for re-ranking.
- Score: 0.2580765958706853
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Re-rankers, which order retrieved documents with respect to the relevance
score on the given query, have gained attention for the information retrieval
(IR) task. Rather than fine-tuning the pre-trained language model (PLM), the
large-scale language model (LLM) is utilized as a zero-shot re-ranker with
excellent results. While LLM is highly dependent on the prompts, the impact and
the optimization of the prompts for the zero-shot re-ranker are not explored
yet. Along with highlighting the impact of optimization on the zero-shot
re-ranker, we propose a novel discrete prompt optimization method, Constrained
Prompt generation (Co-Prompt), with the metric estimating the optimum for
re-ranking. Co-Prompt guides the generated texts from PLM toward optimal
prompts based on the metric without parameter update. The experimental results
demonstrate that Co-Prompt leads to outstanding re-ranking performance against
the baselines. Also, Co-Prompt generates more interpretable prompts for humans
against other prompt optimization methods.
Related papers
- Discovering Preference Optimization Algorithms with and for Large Language Models [50.843710797024805]
offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs.
We perform objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention.
Experiments demonstrate the state-of-the-art performance of DiscoPOP, a novel algorithm that adaptively blends logistic and exponential losses.
arXiv Detail & Related papers (2024-06-12T16:58:41Z) - Prompt Optimization with Human Feedback [69.95991134172282]
We study the problem of prompt optimization with human feedback (POHF)
We introduce our algorithm named automated POHF (APOHF)
The results demonstrate that our APOHF can efficiently find a good prompt using a small number of preference feedback instances.
arXiv Detail & Related papers (2024-05-27T16:49:29Z) - AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs [51.217126257318924]
We present a novel method that uses another Large Language Models, called the AdvPrompter, to generate human-readable adversarial prompts in seconds.
We train the AdvPrompter using a novel algorithm that does not require access to the gradients of the TargetLLM.
The trained AdvPrompter generates suffixes that veil the input instruction without changing its meaning, such that the TargetLLM is lured to give a harmful response.
arXiv Detail & Related papers (2024-04-21T22:18:13Z) - LlamaRec: Two-Stage Recommendation using Large Language Models for
Ranking [10.671747198171136]
We propose a two-stage framework using large language models for ranking-based recommendation (LlamaRec)
In particular, we use small-scale sequential recommenders to retrieve candidates based on the user interaction history.
LlamaRec consistently achieves datasets superior performance in both recommendation performance and efficiency.
arXiv Detail & Related papers (2023-10-25T06:23:48Z) - Revisiting Large Language Models as Zero-shot Relation Extractors [8.953462875381888]
Relation extraction (RE) consistently involves a certain degree of labeled or unlabeled data even if under zero-shot setting.
Recent studies have shown that large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt.
This work focuses on the study of exploring LLMs as zero-shot relation extractors.
arXiv Detail & Related papers (2023-10-08T06:17:39Z) - Query-Dependent Prompt Evaluation and Optimization with Offline Inverse
RL [62.824464372594576]
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.
arXiv Detail & Related papers (2023-09-13T01:12:52Z) - Robust Prompt Optimization for Large Language Models Against
Distribution Shifts [80.6757997074956]
Large Language Model (LLM) has demonstrated significant ability in various Natural Language Processing tasks.
We propose a new problem of robust prompt optimization for LLMs against distribution shifts.
This problem requires the prompt optimized over the labeled source group can simultaneously generalize to an unlabeled target group.
arXiv Detail & Related papers (2023-05-23T11:30:43Z) - 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.