pith. sign in

Pre-training large memory language models with internal and external knowledge

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CL 1 cs.LG 1

years

2026 2

roles

background 1

polarities

background 1

representative citing papers

Autolearn: Learn by Surprise, Commit by Proof

cs.LG · 2026-04-02 · unverdicted · novelty 6.0

Autolearn uses high-loss passages and self-generated Q&A training to drive the perturbation gap below baseline, improving novel fact acquisition while suppressing memorization in language models.

citing papers explorer

Showing 2 of 2 citing papers.

  • Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts cs.CL · 2026-04-09 · conditional · none · ref 101

    Loss-based pruning of training data to limit facts and flatten their frequency distribution enables a 110M-parameter GPT-2 model to memorize 1.3 times more entity facts than standard training, matching a 1.3B-parameter model on the full dataset.

  • Autolearn: Learn by Surprise, Commit by Proof cs.LG · 2026-04-02 · unverdicted · none · ref 18

    Autolearn uses high-loss passages and self-generated Q&A training to drive the perturbation gap below baseline, improving novel fact acquisition while suppressing memorization in language models.