mlsanityData to 14 Oct 2026

`Generalization is hallucination' through the lens of tensor completions

arXiv 2502.17305 ↗First posted 24 Feb 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

In this short position paper, we introduce tensor completions and artifacts and make the case that they are a useful theoretical framework for understanding certain types of hallucinations and generalizations in language models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 20 references that are in the map. First posted on arXiv 24 Feb 2025.

Builds on

14 of 20 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  3. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 671
  4. 2024Hallucination is Inevitable: An Innate Limitation of Large Language Modelscited by 332
  5. 2018Stronger generalization bounds for deep nets via a compression approachcited by 307
  6. 2024LLMs Will Always Hallucinate, and We Need to Live With Thiscited by 78
  7. 2022PAC-Bayes Compression Bounds So Tight That They Can Explain Generalizationcited by 76
  8. 2023Non-Vacuous Generalization Bounds for Large Language Modelscited by 53
  9. 2024Understanding Factual Recall in Transformers via Associative Memoriescited by 51
  10. 2017Tensor Completion Algorithms in Big Data Analyticscited by 48
  11. 2024Confabulation: The Surprising Value of Large Language Model Hallucinationscited by 43
  12. 2024Scaling Laws for Fact Memorization of Large Language Modelscited by 33
2 more
  1. 2024I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Tokencited by 26
  2. 2024Banishing LLM Hallucinations Requires Rethinking Generalizationcited by 13

Built on by

Not cited yet.