A Roadmap for Tamed Interactions with Large Language Models

Abstract

Large Language Models (LLMs) are increasingly embedded in software systems ( GenAIware), enabling new forms of automation and interaction However, their probabilistic nature and reliance on prompt programming challenge reliability, robustness, and maintainability In current practice, prompt-related concerns (e.g., context management, interaction logic, output validation) are embedded in general-purpose code, leading to implicit, hard-to-analyze systems We argue that prompt programming should be treated as a first-class Software Engineering (SE ) concern and propose LLM Scripting Language (LSL ), a Domain Specific Language ( DSL) for structuring LLM interactions as analyzable programs LSL introduces abstractions for interaction blocks, context scopes, output constraints, and control flow, separating deterministic logic from probabilistic model behavior while ensuring syntactic compliance From an SE perspective, LSL supports disciplined development by making interaction logic explicit, analyzable, and amenable to verification and validation It also acts as cognitive scaffolding, externalizing prompt design into programmable artifacts that reduce implicit reasoning and support systematic debugging, evolution, and reuse We illustrate these properties in a structured generation scenario, showing improved failure localization and interaction transparency While LSL does not guarantee semantic correctness or factual accuracy, it provides a principled foundation for more analyzable and maintainable prompt-based systems.

References in corpus (27)

• Survey of Hallucination in Natural Language Generation
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Scaling Instruction-Finetuned Language Models
• Gemini: A Family of Highly Capable Multimodal Models
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Code Llama: Open Foundation Models for Code
• Mistral 7B
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• DeepSeek-V3 Technical Report
• Gemma: Open Models Based on Gemini Research and Technology
• Large Language Models: A Survey
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
• GPT-4o System Card
• Gemma 2: Improving Open Language Models at a Practical Size
• Mixtral of Experts
• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
• DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• Eliciting Latent Predictions from Transformers with the Tuned Lens
• A Survey of Context Engineering for Large Language Models
• A Research Roadmap for Augmenting Software Engineering Processes and Software Products with Generative AI
• Natural Language Outlines for Code: Literate Programming in the LLM Era
• Large Language Models as Software Components: A Taxonomy for LLM-Integrated Applications
• Challenges in Testing Large Language Model Based Software: A Faceted Taxonomy
• Promptware Engineering: Software Engineering for Prompt-Enabled Systems
• LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models
• InTraVisTo: Inside Transformer Visualisation Tool