Pith. sign in

REVIEW 8 cited by

Understanding Factual Recall in Transformers via Associative Memories

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2412.06538 v1 pith:R52IIMCF submitted 2024-12-09 cs.LG cs.CLcs.ITmath.ITstat.ML

Understanding Factual Recall in Transformers via Associative Memories

classification cs.LG cs.CLcs.ITmath.ITstat.ML
keywords factualrecallassociativememoriestasktransformerscountfacts
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models have demonstrated an impressive ability to perform factual recall. Prior work has found that transformers trained on factual recall tasks can store information at a rate proportional to their parameter count. In our work, we show that shallow transformers can use a combination of associative memories to obtain such near optimal storage capacity. We begin by proving that the storage capacities of both linear and MLP associative memories scale linearly with parameter count. We next introduce a synthetic factual recall task, and prove that a transformer with a single layer of self-attention followed by an MLP can obtain 100% accuracy on the task whenever either the total number of self-attention parameters or MLP parameters scales (up to log factors) linearly with the number of facts. In particular, the transformer can trade off between using the value matrices or the MLP as an associative memory to store the dataset of facts. We complement these expressivity results with an analysis of the gradient flow trajectory of a simplified linear attention model trained on our factual recall task, where we show that the model exhibits sequential learning behavior.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Why Muon Outperforms Adam: A Curvature Perspective

    cs.LG 2026-06 conditional novelty 7.0

    Muon outperforms Adam by reducing curvature penalty via lower Normalized Directional Sharpness, as shown via Taylor approximation on LLM training and proven on stylized quadratic problems with heterogeneous curvature.

  2. Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval

    stat.ML 2026-05 unverdicted novelty 7.0

    Winner-take-all linear memory capacity scales as d² ~ n log n due to extreme values; listwise retrieval via Tail-Average Margin yields d² ~ n with exact asymptotic theory.

  3. Sharp Capacity Scaling of Spectral Optimizers in Learning Associative Memory

    cs.LG 2026-03 unverdicted novelty 7.0

    Muon achieves higher storage capacity than SGD and matches Newton's method in one-step recovery rates for associative memory under power-law distributions, while saturating at larger critical batch sizes and showing f...

  4. What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

    cs.LG 2026-07 conditional novelty 6.0

    KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.

  5. Muon in Associative Memory Learning: Training Dynamics and Scaling Laws

    cs.LG 2026-02 conditional novelty 6.0

    In a linear softmax memory model, Muon equalizes learning across frequency tiers and gives exponential (noiseless) or T^{-2} (noisy power-law) convergence, versus polynomial or T^{-(1-1/β)} for gradient descent.

  6. Deep sequence models tend to memorize geometrically; it is unclear why

    cs.LG 2025-10 unverdicted novelty 6.0

    Deep sequence models develop geometric memory in embeddings that encodes novel global relationships, transforming l-fold composition tasks into 1-step navigation via a natural spectral bias connected to Node2Vec.

  7. Provable Knowledge Acquisition and Extraction in One-Layer Transformers

    cs.LG 2025-07 unverdicted novelty 6.0

    In a stylized one-layer transformer, pre-training encodes factual knowledge via relation-specific feature directions and attention patterns; fine-tuning extracts it through a relation-covering mechanism that succeeds ...

  8. TIDE: Every Layer Knows the Token Beneath the Context

    cs.CL 2026-05 unverdicted novelty 5.0

    TIDE augments standard transformers with per-layer token embedding injection via an ensemble of memory blocks and a depth-conditioned router to mitigate rare-token undertraining and contextual collapse.