CoChat

Physics of Language Models: Part 3.2, Knowledge Manipulation

Open access
Allen-Zhu, Zeyuan, Li, Yuanzhi · 2025 · SSRN Electronic Journal

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

Overview

Integrity signals

Registry

Crossref · 10.2139/ssrn.5250621

Cites

19 of 19 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 19 references

Research works printed but not linked: 23

  1. Zeyuan Allen, 2023, Physics of Language Models: Part 1, Learning Hierarchical Language Structures
  2. Zeyuan Allen, 2024, Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws
  3. Lukas Berglund, 2023, The Reversal Curse: LLMs trained on "A is B" fail to learn
  4. Olga Golovneva, 2024, Reverse training to nurse the reversal curse
  5. Qingyan Guo, 2024, Mitigating reversal curse via semantic-aware permutation training
  6. Evan Hernandez, 2023, Measuring and manipulating knowledge representations in language models
  7. Alexandre Albert Q Jiang, 2023, Mistral 7b
  8. Mojtaba Komeili, 2021, Internet-augmented dialogue generation
  9. R�mi Lebret, 2016, Generating text from structured data with application to the biography domain
  10. Shangqing Liu, 2020, Retrieval-augmented generation for code summarization via hybrid gnn
  11. Yuning Mao, 2020, Generation-augmented retrieval for open-domain question answering
  12. Reham Omar, 2023, Chatgpt versus traditional question answering for knowledge graphs: Current status and future directions towards knowledge graph chatbots
  13. 2023, OpenAI. Gpt-4 technical report
  14. Md Rizwan Parvez, 2021, Retrieval augmented code generation and summarization
  15. Hao Peng, 2022, Copen: Probing conceptual knowledge in pre-trained language models
  16. Fabio Petroni, 2019, Language models as knowledge bases? arXiv preprint
  17. Alec Radford, 2019, Language models are unsupervised multitask learners, OpenAI blog, 1
  18. Ori Ram, 2023, -context retrieval-augmented language models
  19. Jianlin Su, 2021, Roformer: Enhanced transformer with rotary position embedding
  20. Kai Sun, 2023, Head-to-tail: How knowledgeable are large language models (llm)? aka will llms replace knowledge graphs? arXiv preprint
  21. Hugo Touvron, 2023, Open and efficient foundation language models
  22. Tian Ye, Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process
  23. Tian Ye, Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems

Cited by

See all 115

Metadata

Authors
Allen-Zhu, Z., & Li, Y.
Affiliations
  • Meta (United States) (US)
  • Mohamed bin Zayed University of Artificial Intelligence (AE)
Corresponding author
Allen-Zhu, Zeyuan
Venue
SSRN Electronic Journal
Publisher
Elsevier BV
Published
2025
ISSN
1556-5068 (ISSN-L)
OpenAlex
W4410357125
Cited by
8
References
11
Citations by year
2026: 5 · 2025: 3
Type
posted content
Language
en
Open access
Locations
  • SSRN Electronic Journal (acceptedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Neurobiology of Language and Bilingualism
Keywords
language models, knowledge manipulation, large language models, knowledge representation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Physics of Language Models: Part 3.2, Knowledge Manipulation. https://app.cochat.ai/papers/10.2139/ssrn.5250621
The paper
Allen-Zhu, Z., & Li, Y. (2025). Physics of Language Models: Part 3.2, Knowledge Manipulation. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.5250621

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.