# Fuzzy, Symbolic, and Contextual: Enhancing LLM Instruction via Cognitive Scaffolding

arXiv: https://arxiv.org/abs/2508.21204 · HTML: https://mlsanity.com/paper/2508.21204/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 28 Aug 2025.

## Builds on (most cited first, 10 of 10)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Data Distributional Properties Drive Emergent In-Context Learning in Transformers](https://mlsanity.com/paper/2205.05055/) (2022)
- [Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task](https://mlsanity.com/paper/2310.09336/) (2023)
- [(How) Do Language Models Track State?](https://mlsanity.com/paper/2503.02854/) (2025)
- [Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks](https://mlsanity.com/paper/2410.08133/) (2024)
- [A Fuzzy Logic Prompting Framework for Large Language Models in Adaptive and Uncertain Tasks](https://mlsanity.com/paper/2508.06754/) (2025)

## Built on by (most cited first, 2 of 2)

- [Beyond the Attention Stability Boundary: Agentic Self-Synthesizing Reasoning Protocols](https://mlsanity.com/paper/2604.24512/) (2026)
- [Symbolically Scaffolded Play: Designing Role-Sensitive Prompts for Generative NPC Dialogue](https://mlsanity.com/paper/2510.25820/) (2025)

## Abstract (arXiv)

We study how prompt-level inductive biases influence the cognitive behavior of large language models (LLMs) in instructional dialogue. We introduce a symbolic scaffolding method paired with a short-term memory schema designed to promote adaptive, structured reasoning in Socratic tutoring. Using controlled ablation across five system variants, we evaluate model outputs via expert-designed rubrics covering scaffolding, responsiveness, symbolic reasoning, and conversational memory. We present preliminary results using an LLM-based evaluation framework aligned to a cognitively grounded rubric. This enables scalable, systematic comparisons across architectural variants in early-stage experimentation. The preliminary results show that our full system consistently outperforms baseline variants. Analysis reveals that removing memory or symbolic structure degrades key cognitive behaviors, including abstraction, adaptive probing, and conceptual continuity. These findings support a processing-level account in which prompt-level cognitive scaffolds can reliably shape emergent instructional strategies in LLMs.