mlsanityData to 14 Oct 2026

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

arXiv 2508.21204 ↗First posted 28 Aug 2025cs.AI cs.CLcited by 2

Not on the map. Why?

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.

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

10 of 31 references.

References · 10

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  4. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  5. 2016The Mythos of Model Interpretabilitycited by 721
  6. 2022Data Distributional Properties Drive Emergent In-Context Learning in Transformerscited by 309
  7. 2023Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Taskcited by 93
  8. 2025(How) Do Language Models Track State?cited by 34
  9. 2024Assessing Episodic Memory in LLMs with Sequence Order Recall Taskscited by 10
  10. 2025A Fuzzy Logic Prompting Framework for Large Language Models in Adaptive and Uncertain Taskscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2026Beyond the Attention Stability Boundary: Agentic Self-Synthesizing Reasoning Protocolscited by 2
  2. 2025Symbolically Scaffolded Play: Designing Role-Sensitive Prompts for Generative NPC Dialoguecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Large Language Models as Students Who Think Aloud: Overly Coherent, Verbose, and Confident
  2. 2025A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents
  3. 2025Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM
  4. 2025Reasoning Scaffolding: Distilling the Flow of Thought from LLMs
  5. 2025Dialogic Pedagogy for Large Language Models: Aligning Conversational AI with Proven Theories of Learning
  6. 2025Short-Path Prompting in LLMs: Analyzing Reasoning Instability and Solutions for Robust Performance
  7. 2026INSIDE the Student's Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators
  8. 2026Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education