Task-oriented Prompt Enhancement via Script Generation
Chung-Yu Wang, Alireza DaghighFarsoodeh, Hung Viet Pham

TL;DR
TITAN introduces a zero-shot, script-generation approach that enhances large language models' ability to handle task-oriented prompts without manual templates, significantly improving performance across diverse tasks.
Contribution
This work presents TITAN, a novel zero-shot script generation method that eliminates manual prompt engineering and improves LLMs' task performance using chain-of-thought and step-back prompting techniques.
Findings
TITAN outperforms state-of-the-art zero-shot methods by 7.6% with GPT-3.5.
TITAN achieves state-of-the-art results in 8 out of 11 tasks without human annotation.
TITAN's approach is effective across diverse task types, demonstrating broad applicability.
Abstract
Large Language Models (LLMs) have demonstrated remarkable abilities across various tasks, leveraging advanced reasoning. Yet, they struggle with task-oriented prompts due to a lack of specific prior knowledge of the task answers. The current state-of-the-art approach, PAL, utilizes code generation to address this issue. However, PAL depends on manually crafted prompt templates and examples while still producing inaccurate results. In this work, we present TITAN-a novel strategy designed to enhance LLMs' performance on task-oriented prompts. TITAN achieves this by generating scripts using a universal approach and zero-shot learning. Unlike existing methods, TITAN eliminates the need for detailed task-specific instructions and extensive manual efforts. TITAN enhances LLMs' performance on various tasks by utilizing their analytical and code-generation capabilities in a streamlined process.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSoftware Testing and Debugging Techniques · Software Reliability and Analysis Research · Formal Methods in Verification
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · 15 Ways to Contact How can i speak to someone at Delta Airlines · Attention Is All You Need · Sparse Evolutionary Training · Cosine Annealing · {Dispute@FaQ-s}How to file a dispute with Expedia? · Linear Layer · Weight Decay · Position-Wise Feed-Forward Layer · Label Smoothing
