让大模型用类BASIC语言分步推理，提升可解释性。
Cognitive BASIC: An In-Model Interpreted Reasoning Language for LLMs
- 用编号行和简单命令构建可解释的推理流程
- 三款大模型均能执行，知识提取与矛盾检测效果良好
- 适合需要透明推理过程的研究者或安全敏感场景
Cognitive BASIC 是一种基于经典 BASIC 风格的极简提示语言及模型内解释器，将大语言模型（LLM）的推理过程结构化为显式的、分步执行的轨迹。受复古 BASIC 简洁性的启发，我们复用编号行和基础指令作为可解释的认知控制层。现代大模型能够可靠地模拟此类短程序，实现在模型内部的透明多步推理。一个自然语言编写的解释器文件定义了命令语义、内存更新规则和日志行为。我们的心理模型解释器可提取命题与过程性知识，检测逻辑矛盾，并在必要时生成解决策略。在知识抽取、冲突检测与推理任务的基准测试中，三款 LLM 均能执行 Cognitive BASIC 程序，整体表现良好但存在差异。
原文摘要 · Abstract (English)
Cognitive BASIC is a minimal, BASIC-style prompting language and in-model interpreter that structures large language model (LLM) reasoning into explicit, stepwise execution traces. Inspired by the simplicity of retro BASIC, we repurpose numbered lines and simple commands as an interpretable cognitive control layer. Modern LLMs can reliably simulate such short programs, enabling transparent multi-step reasoning inside the model. A natural-language interpreter file specifies command semantics, memory updates, and logging behavior. Our mental-model interpreter extracts declarative and procedural knowledge, detects contradictions, and produces resolutions when necessary. A comparison across three LLMs on a benchmark of knowledge extraction, conflict detection, and reasoning tasks shows that all models can execute Cognitive BASIC programs, with overall strong but not uniform performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。