用意识理论指导大模型生成，让输出更简洁准确。
Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework
- 基于意识理论设计奖励函数，鼓励文本因果性与整合性。
- 在跨域任务上输出长度减少31%，准确率仍保持接近基线。
- 无需额外数据或模型，适合提升推理效率的场景。
追求通用人工智能（AGI）是语言模型发展的核心目标，其中类意识处理可能成为关键推动力。尽管当前语言模型不具备意识，但表现出某些意识特征的行为。本文通过基于奖励的学习范式，将集成信息理论（IIT）这一主流意识理论应用于语言模型中。IIT提供了一套形式化的、基于公理的数学框架来量化意识。受其核心原则启发，我们构建了一个新型奖励函数，用于衡量文本的因果性、连贯性和整合性，这些特性与意识加工相关。实验发现，优化该受IIT启发的奖励能促使模型生成更简洁的文本。在域外任务上，经仔细调参后，输出长度最多减少31%，同时保持与基线模型相当的准确性。此外，还分析了该训练方法对模型置信度校准及测试时计算量扩展的影响。所提框架具有显著实用性：概念简单、计算高效，无需外部数据或辅助模型，且使用通用能力驱动信号而非特定任务启发式。代码已公开于 https://github.com/MH-Sameti/LLM_PostTraining.git。
原文摘要 · Abstract (English)
The pursuit of Artificial General Intelligence (AGI) is a central goal in language model development, in which consciousness-like processing could serve as a key facilitator. While current language models are not conscious, they exhibit behaviors analogous to certain aspects of consciousness. This paper investigates the implementation of a leading theory of consciousness, Integrated Information Theory (IIT), within language models via a reward-based learning paradigm. IIT provides a formal, axiom-based mathematical framework for quantifying consciousness. Drawing inspiration from its core principles, we formulate a novel reward function that quantifies a text's causality, coherence and integration, characteristics associated with conscious processing. Empirically, it is found that optimizing for this IIT-inspired reward leads to more concise text generation. On out of domain tasks, careful tuning achieves up to a 31% reduction in output length while preserving accuracy levels comparable to the base model. In addition to primary task performance, the broader effects of this training methodology on the model's confidence calibration and test-time computational scaling is analyzed. The proposed framework offers significant practical advantages: it is conceptually simple, computationally efficient, requires no external data or auxiliary models, and leverages a general, capability-driven signal rather than task-specific heuristics. Code available at https://github.com/MH-Sameti/LLM_PostTraining.git
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。