Pith. sign in

REVIEW 3 cited by

Aspects of human memory and Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2311.03839 v3 pith:DTJFMGL7 submitted 2023-11-07 cs.CL cs.AIcs.LGq-bio.NC

Romuald A. Janik This is my paper · ORCID
classification cs.CLcs.AIcs.LGq-bio.NC
keywords memorylanguagehumanlargellmsmodelmodelsproperties
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) are huge artificial neural networks which primarily serve to generate text, but also provide a very sophisticated probabilistic model of language use. Since generating a semantically consistent text requires a form of effective memory, we investigate the memory properties of LLMs and find surprising similarities with key characteristics of human memory. We argue that the human-like memory properties of the Large Language Model do not follow automatically from the LLM architecture but are rather learned from the statistics of the training textual data. These results strongly suggest that the biological features of human memory leave an imprint on the way that we structure our textual narratives.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context

    cs.CL 2025-10 conditional novelty 7.0 of 10

    In-context entity retrieval in LMs is a mixture of positional, lexical, and reflexive mechanisms; the pure positional view fails in middle positions of long lists.

  2. Memorization $\neq$ Understanding: Do Large Language Models Have the Ability of Scenario Cognition?

    cs.CL 2025-09 conditional novelty 5.0 of 10

    LLMs fine-tuned on paraphrases of fictional facts can recall the paraphrases but cannot answer questions about who did what in those facts, suggesting memorization without robust scenario-level understanding.

  3. Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training

    cs.LG 2025-02 conditional novelty 4.0 of 10

    Attention heads in trained GPT-2 models develop temporal contiguity, recency, and primacy effects, and ablating induction heads removes the resulting serial-recall bias in outputs.

Pith tools