REVIEW 3 cited by
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
Not yet reviewed by Pith; the record is open.
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
read the original abstract
Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle modification to the next-token training objective that we call the goldfish loss. During training, randomly sampled subsets of tokens are excluded from the loss computation. These dropped tokens are not memorized by the model, which prevents verbatim reproduction of a complete chain of tokens from the training set. We run extensive experiments training billion-scale Llama-2 models, both pre-trained and trained from scratch, and demonstrate significant reductions in extractable memorization with little to no impact on downstream benchmarks.
Forward citations
Cited by 3 Pith papers
-
Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
Margin Calibration, a non-saturating margin-anchored LoRA polish, crosses the margin cliff and cuts post-attack relearn recovery on all 97 populated cells in the paper's stress matrix.
-
A Closer Look on Memorization in Tabular Diffusion Model: A Data-Centric Perspective
A small subset of training samples drives most memorization in tabular diffusion models, and pruning them based on early memorization signals reduces measured leakage, though the evaluation metric makes part of the ga...
-
Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers
AxoNN combines 3D parallel matrix multiplication with data parallelism to reach 1.423 exaflop/s on 6,144 H100 GPUs, and reports one-pass catastrophic memorization at the 70B scale that a masked-loss technique suppresses.
Discussion (0). Continue with ORCID to comment.