Quantifying Memorization Across Neural Language Models · HackerPapers discussions

Quantifying Memorization Across Neural Language Models — mentioned by johndough

Tue, 21 Jul 2026 10:46:35 GMT

I am not arguing that Kimi did not distill Opus or Sonnet (which they almost certainly have, as opposed to Fable or Sol). I am arguing that even if they did not distill, the model could still identify itself as Opus or Sonnet. That being said, I'd like to point out a few things: - The second link (to claude-sonnet-4-2025051) had 17k matches, not just 3k. - grep.app does not index the entirety of GitHub, so the real number of occurrences of model identifiers is even higher. SourceGraph has a larger index, but the number is so high that it exceeds their result limit of 10k…

Paper and discussion history. A mention is not an endorsement.

Quantifying Memorization Across Neural Language Models — mentioned by mwcampbell

Tue, 29 Apr 2025 07:41:29 GMT

I'm not making an argument from grievance about my own code being plagiarized. I actually don't care if my own code is used without even the attribution required by the permissive licenses it's released under; I just want it to be used. I do also write proprietary code, but that's not in the training datasets, as far as I know. But the training datasets do include code under a variety of open-source licenses, both permissive and copyleft, and some of those developers do care how their code is used. We should respect that. As for our tendency to disrespect the copyrights of art, clearly we've…

Paper and discussion history. A mention is not an endorsement.

Quantifying Memorization Across Neural Language Models — mentioned by 1vuio0pswjnm7

Thu, 29 Aug 2024 02:17:30 GMT

"Can anyone find the filing?" https://arxiv.org/pdf/2202.07646 Personally, I would not rely on blogs like "developer-tech.com" for unbiased information about "AI" litigation. I would read the order and draw own conclusions.^1 (Note the plaintiffs are attempting to file an interloctory appeal re: the dimissal of the DMCA claims.) 1 https://ia904708.us.archive.org/6/items/gov.uscourts.cand.40... No doubt I am in the minority but I am more interested in the contract claims, which have survived dismissal, than in the DMCA ones. If plaintiffs can stop the "training" of "AI" through contract, then…

Paper and discussion history. A mention is not an endorsement.

Quantifying Memorization Across Neural Language Models — mentioned by versteegen

Fri, 17 Mar 2023 08:31:16 GMT

> They just show it to the AI, it doesn't store it - just data about it. The same as you when you look at something, be it a painting or a chair. In general for machine learning, yes, but deep learning models with large numbers of parameters such as transformers and stable diffusion do actually memorise part of their training data verbatim. The problem is mainly duplicate data points. E.g. https://arstechnica.com/information-technology/2023/02/resea... https://arxiv.org/pdf/2202.07646.pdf Quantifying Memorization Across Neural Language Models

Paper and discussion history. A mention is not an endorsement.

Quantifying Memorization Across Neural Language Models — HN submission

Tue, 07 Mar 2023 22:30:05 GMT

Quantifying memorization across language models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Quantifying Memorization Across Neural Language Models — mentioned by visarga

Fri, 04 Nov 2022 20:08:55 GMT

Deduplicating Training Data Makes Language Models Better https://arxiv.org/pdf/2107.06499 Quantifying Memorization Across Neural Language Models https://arxiv.org/pdf/2202.07646.pdf

Paper and discussion history. A mention is not an endorsement.

Quantifying Memorization Across Neural Language Models — mentioned by ijk

Wed, 31 Aug 2022 15:44:58 GMT

You are probably very aware of it, but just to highlight the importance of this for people who aren't aware: data duplication degrades the training and makes memorization (and therefore plagiarism, in the technical sense) more likely. For language models, this includes near-similarities, which I'd guess would extend to images. Quantifying Memorization Across Neural Language Models https://arxiv.org/abs/2202.07646 Deduplicating Training Data Makes Language Models Better https://arxiv.org/abs/2107.06499 https://twitter.com/arankomatsuzaki/status/14154721921003397...…

Paper and discussion history. A mention is not an endorsement.