An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models
- URL: http://arxiv.org/abs/2402.05359v6
- Date: Tue, 2 Jul 2024 18:18:18 GMT
- Title: An Examination on the Effectiveness of Divide-and-Conquer Prompting in Large Language Models
- Authors: Yizhou Zhang, Lun Du, Defu Cao, Qiang Fu, Yan Liu,
- Abstract summary: We provide a theoretic analysis to divide-and-conquer prompting strategy and help us identify the specific tasks where DaC prompting can bring performance boost with theoretic guarantee.
We present two cases (large integer arithmetic and fact verification) where experimental results align with our theoretic analysis.
- Score: 28.139780691709266
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Foundation models, such as Large language Models (LLMs), have attracted significant amount of interest due to their large number of applications. However, when handling tasks involving repetitive sub-tasks and/or deceptive contents, such as arithmetic calculation and article-level fake news detection, simple instructional prompts suffer from inaccurate responses. Existing works show that more complicated prompting strategies, such as Chain-of-Thoughts and Least-to-Most, can unlock LLM's powerful capacity in diverse areas. Recent researches reveal that simple divide-and-conquer prompting strategy, i.e. simply dividing the input sequence to multiple sub-inputs, can also substantially improve LLM's performance in some specific tasks such as misinformation detection. In this paper, we aim at examining the utility of divide-and-conquer prompting strategy and answer on which kind of tasks this strategy gets advantages. Specifically, we provide a theoretic analysis to divide-and-conquer prompting strategy and help us identify the specific tasks where DaC prompting can bring performance boost with theoretic guarantee. We then present two cases (large integer arithmetic and fact verification) where experimental results aligns with our theoretic analysis.
Related papers
- Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation [68.58373854950294]
We focus on causal reasoning and address the task of establishing causal relationships based on correlation information.
We introduce a prompting strategy for this problem that breaks the original task into fixed subquestions.
We evaluate our approach on an existing causal benchmark, Corr2Cause.
arXiv Detail & Related papers (2024-12-18T15:32:27Z) - LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant [63.28378110792787]
We introduce LamRA, a versatile framework designed to empower Large Multimodal Models with sophisticated retrieval and reranking capabilities.
For retrieval, we adopt a two-stage training strategy comprising language-only pre-training and multimodal instruction tuning.
For reranking, we employ joint training for both pointwise and listwise reranking, offering two distinct ways to further boost the retrieval performance.
arXiv Detail & Related papers (2024-12-02T17:10:16Z) - EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning [5.172620636569522]
Large language models (LLMs) have enabled in-context learning (ICL), allowing LLMs to acquire proficiency in a specific task using only a few demonstration samples (exemplars)
A critical challenge in ICL is the selection of optimal exemplars, which can be either task-specific (static) or test-example-specific (dynamic)
arXiv Detail & Related papers (2024-11-06T12:48:04Z) - Interpreting and Improving Large Language Models in Arithmetic Calculation [72.19753146621429]
Large language models (LLMs) have demonstrated remarkable potential across numerous applications.
In this work, we delve into uncovering a specific mechanism by which LLMs execute calculations.
We investigate the potential benefits of selectively fine-tuning these essential heads/MLPs to boost the LLMs' computational performance.
arXiv Detail & Related papers (2024-09-03T07:01:46Z) - LISA: Reasoning Segmentation via Large Language Model [68.24075852136761]
We propose a new segmentation task -- reasoning segmentation.
The task is designed to output a segmentation mask given a complex and implicit query text.
We present LISA: large Language Instructed Assistant, which inherits the language generation capabilities of multimodal Large Language Models.
arXiv Detail & Related papers (2023-08-01T17:50:17Z) - OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning [49.38867353135258]
We propose OverPrompt, leveraging the in-context learning capability of LLMs to handle multiple task inputs.
Our experiments show that OverPrompt can achieve cost-efficient zero-shot classification without causing significant detriment to task performance.
arXiv Detail & Related papers (2023-05-24T10:08:04Z) - Active Prompting with Chain-of-Thought for Large Language Models [26.5029080638055]
This paper proposes a new method, Active-Prompt, to adapt large language models to different tasks.
By borrowing ideas from the related problem of uncertainty-based active learning, we introduce several metrics to characterize the uncertainty.
Experimental results demonstrate the superiority of our proposed method, achieving state-of-the-art on eight complex reasoning tasks.
arXiv Detail & Related papers (2023-02-23T18:58:59Z) - Decomposed Prompting: A Modular Approach for Solving Complex Tasks [55.42850359286304]
We propose Decomposed Prompting to solve complex tasks by decomposing them (via prompting) into simpler sub-tasks.
This modular structure allows each prompt to be optimized for its specific sub-task.
We show that the flexibility and modularity of Decomposed Prompting allows it to outperform prior work on few-shot prompting.
arXiv Detail & Related papers (2022-10-05T17:28:20Z)
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.