mlsanityData to 14 Oct 2026

Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency

arXiv 2605.18732 ↗First posted 18 May 2026cs.CL cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

While scaling laws govern aggregate large language model performance, no scaling law has linked factual recall to both model size and training-data composition. We evaluated 38 models on over 8,900 scholarly references evaluated by an automated reference verification system. Recall quality follows a sigmoid in the log-linear combination of model parameter count and topic representation in training data. These two variables alone explain 60% of the variance across 16 dense models from four families, rising to 74-94% within individual families. The form matches a superposition-inspired account in which recall is gated by a signal-to-noise ratio: signal strength scales with concept frequency and the noise floor with model capacity.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

18 of 23 references.

References · 18

  1. 2020Scaling Laws for Neural Language Modelscited by 6,586
  2. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  3. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  4. 2022Toy Models of Superpositioncited by 971
  5. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  6. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  7. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 332
  8. 2025Why Language Models Hallucinatecited by 220
  9. 2023Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?cited by 168
  10. 2022Scaling Laws and Interpretability of Learning from Repeated Datacited by 152
  11. 2024Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Lawscited by 144
  12. 2023The Quantization Model of Neural Scalingcited by 138
6 more
  1. 2024Scaling Laws for Fact Memorization of Large Language Modelscited by 33
  2. 2025Superposition Yields Robust Neural Scalingcited by 31
  3. 2025The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucinationcited by 23
  4. 2025The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigationcited by 10
  5. 2024Towards a Holistic Evaluation of LLMs on Factual Knowledge Recallcited by 8
  6. 2025Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerabilitycited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Memory vs. Context? Influential Factors of Factual Recall in Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity
  2. 2026Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights
  3. 2025Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Models
  4. 2024Quantifying the Capabilities of LLMs across Scale and Precision
  5. 2026Do Factual Recall Mechanisms Carry over from Text to Speech in Multimodal Language Models?
  6. 2026On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance
  7. 2026Do LLMs Make More Mistakes If They Do Not Believe the Input Data?
  8. 2024Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style