---
res:
  bibo_abstract:
  - As artificial neural networks, and specifically large language models, have improved
    rapidly in capabilities and quality, they have increasingly been deployed in real-world
    applications, from customer service to Google search, despite the fact that they
    frequently make factually incorrect or undesirable statements. This trend has
    inspired practical and academic interest in model editing, that is, in adjusting
    the weights of the model to modify its likely outputs for queries relating to
    a specific fact or set of facts. This may be done either to amend a fact or set
    of facts, for instance, to fix a frequent error in the training data, or to suppress
    a fact or set of facts entirely, for instance, in case of dangerous knowledge.
    Multiple methods have been proposed to do such edits. However, at the same time,
    it has been shown that such model editing can be brittle and incomplete. Moreover
    the effectiveness of any model editing method necessarily depends on the data
    on which the model is trained, and, therefore, a good understanding of the interaction
    of the training data distribution and the way it is stored in the network is necessary
    and helpful to reliably perform model editing. However, working with large language
    models trained on real-world data does not allow us to understand this relationship
    or fully measure the effects of model editing. We therefore propose Behemoth,
    a fully synthetic data generation framework. To demonstrate the practical insights
    from the framework, we explore model editing in the context of simple tabular
    data, demonstrating surprising findings that, in some cases, echo real-world results,
    for instance, that in some cases restricting the update rank results in a more
    effective update.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Eugenia B
      foaf_name: Iofinova, Eugenia B
      foaf_surname: Iofinova
      foaf_workInfoHomepage: http://www.librecat.org/personId=f9a17499-f6e0-11ea-865d-fdf9a3f77117
    orcid: 0000-0002-7778-3221
  - foaf_Person:
      foaf_givenName: Dan-Adrian
      foaf_name: Alistarh, Dan-Adrian
      foaf_surname: Alistarh
      foaf_workInfoHomepage: http://www.librecat.org/personId=4A899BFC-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0003-3650-940X
  bibo_doi: 10.48550/arXiv.2601.23153
  dct_date: 2026^xs_gYear
  dct_language: eng
  dct_title: 'Behemoth: Benchmarking unlearning in LLMs using fully synthetic data@'
...