# Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework

arXiv: https://arxiv.org/abs/2601.22786 · HTML: https://mlsanity.com/paper/2601.22786/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 54 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 30 of 31)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [A Long Way to Go: Investigating Length Correlations in RLHF](https://mlsanity.com/paper/2310.03716/) (2023)
- [O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning](https://mlsanity.com/paper/2501.12570/) (2025)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025)
- [Token-Budget-Aware LLM Reasoning](https://mlsanity.com/paper/2412.18547/) (2024)
- [Training Language Models to Reason Efficiently](https://mlsanity.com/paper/2502.04463/) (2025)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [Thinkless: LLM Learns When to Think](https://mlsanity.com/paper/2505.13379/) (2025)
- [Consciousness in Artificial Intelligence: Insights from the Science of Consciousness](https://mlsanity.com/paper/2308.08708/) (2023)
- [Knowledge of Knowledge: Exploring Known-Unknowns Uncertainty with Large Language Models](https://mlsanity.com/paper/2305.13712/) (2023)
- [Following Length Constraints in Instructions](https://mlsanity.com/paper/2406.17744/) (2024)
- [Knowledge Boundary of Large Language Models: A Survey](https://mlsanity.com/paper/2412.12472/) (2024)
- [Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks](https://mlsanity.com/paper/2504.18838/) (2025)
- [Integrated information theory (IIT) 4.0: Formulating the properties of phenomenal existence in physical terms](https://mlsanity.com/paper/2212.14787/) (2022)
- [Self-Cognition in Large Language Models: An Exploratory Study](https://mlsanity.com/paper/2407.01505/) (2024)
- [Prompt-Based Length Controlled Generation with Reinforcement Learning](https://mlsanity.com/paper/2308.12030/) (2023)
- [From Imitation to Introspection: Probing Self-Consciousness in Language Models](https://mlsanity.com/paper/2410.18819/) (2024)
- [Precise Length Control in Large Language Models](https://mlsanity.com/paper/2412.11937/) (2024)
- [SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models](https://mlsanity.com/paper/2506.05745/) (2025)
- [A Case for AI Consciousness: Language Agents and Global Workspace Theory](https://mlsanity.com/paper/2410.11407/) (2024)
- [Dissociating Artificial Intelligence from Artificial Consciousness](https://mlsanity.com/paper/2412.04571/) (2024)
- [Token-Efficient RL for LLM Reasoning](https://mlsanity.com/paper/2504.20834/) (2025)
- [Survey of Consciousness Theory from Computational Perspective](https://mlsanity.com/paper/2309.10063/) (2023)
- [The Phi measure of integrated information is not well-defined for general physical systems](https://mlsanity.com/paper/1902.04321/) (2019)

## Abstract (arXiv)

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