Locating and Editing Factual Associations in GPT · HackerPapers discussions

Locating and Editing Factual Associations in GPT — mentioned by stalfie

Sun, 12 Jul 2026 16:23:53 GMT

Sure, here are some citations: https://arxiv.org/abs/2401.03910?utm_source=chatgpt.com https://www.frontiersin.org/journals/psychology/articles/10.... https://arxiv.org/pdf/2408.04666 https://arxiv.org/abs/2402.00901 https://ar5iv.labs.arxiv.org/html/2407.11015 https://ar5iv.labs.arxiv.org/html/2202.05262 https://www.sciencedirect.com/science/article/abs/pii/S13646... My point was not to argue one point or another about LLM intelligence, but to push against the notion that you have to be "delusional" to even argue that it is possible that LLMs can qualify as intelligent (although the op…

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

Locating and Editing Factual Associations in GPT — mentioned by killerstorm

Mon, 20 May 2024 11:00:58 GMT

There's definitely scientific insight and analysis. E.g. "In-context Learning and Induction Heads" is an excellent paper. Another paper ("ROME") https://arxiv.org/abs/2202.05262 formulates hypothesis over how these models store information, and provide experimental evidence. The thing is, a 3-layer MLP is basically an associative memory + a bit of compute. People understand that if you stack enough of them you can compute or memorize pretty much anything. Attention provides information routing. Again, that is pretty well-understood. The rest is basically finding an optimal trade-off. These…

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

Locating and Editing Factual Associations in GPT — mentioned by filterfiber

Fri, 01 Dec 2023 20:35:31 GMT

The most likely "real solution" is going to be using various tricks and finetuning on higher context lengths to just extend the context window. However I will say knowledge graphs are becoming more popular. I made a comment the other day with a list of some of the popular methods: https://news.ycombinator.com/item?id=38476596 I completely forgot to mention ROME in my last comment, where you can modify facts within an LLM https://arxiv.org/pdf/2202.05262.pdf Note that there could be something more recent then these that I missed, but as far as I know knowledge-graphs/RAG are what most people…

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

Locating and Editing Factual Associations in GPT — mentioned by numeri

Thu, 16 Nov 2023 02:03:48 GMT

This post isn't a scientific investigation. It's someone playing around with a black-box model with few to little controls – which is unfortunately the only thing we can do when experimenting with GPT-4, which does excuse this partially. Unfortunately, though, the author seems unaware of the actual state of research on the actual mechanics of how LLMs store knowledge and specifically binary relations. The ROME paper[1], among others, shows that the feed-forward layers function as a key-value store, where the feed-forward's up projection of the last token in a noun phrase (say, "the Eiffel…

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

Locating and Editing Factual Associations in GPT — mentioned by KhoomeiK

Mon, 16 Oct 2023 20:11:21 GMT

The title made me think this was an approach that used memory editing techniques (e.g. ROME [1]) to allow an LLM's neural memory (not just its context) to change over the course of conversation. Pretty happy to realize that this is just a fancy RAG work—will be building my version of MemEditGPT soon. [1] https://arxiv.org/abs/2202.05262

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

Locating and Editing Factual Associations in GPT — mentioned by KhoomeiK

Sun, 27 Aug 2023 19:57:47 GMT

Fyi, Meng et al 2022 [1] is pretty much required reading in order to understand this paper [1] https://arxiv.org/abs/2202.05262

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

Locating and Editing Factual Associations in GPT — mentioned by bhickey

Tue, 09 May 2023 18:49:02 GMT

Transformer editing is an active field of research. https://arxiv.org/abs/2202.05262 https://arxiv.org/abs/2210.07229

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

Locating and Editing Factual Associations in GPT — mentioned by nl

Thu, 23 Feb 2023 22:31:42 GMT

> does anyone know of ML directions that could add any kind of factual confidence level to ChatGPT and similar? Yes. It's a very active area of research. For example: Discovering Latent Knowledge in Language Models Without Supervision (https://arxiv.org/abs/2212.03827) shows an unsupervised approach for probing a LLM to discover things it thinks are facts Locating and Editing Factual Associations in GPT (https://arxiv.org/pdf/2202.05262.pdf) shows an approach to editing a LLM to edit facts. Language Models as Knowledge Bases? (https://aclanthology.org/D19-1250.pdf) is some slightly older work…

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

Locating and Editing Factual Associations in GPT — mentioned by sharemywin

Fri, 17 Feb 2023 21:43:17 GMT

you might find this paper interesting: https://arxiv.org/abs/2202.05262 Locating and Editing Factual Associations in GPT

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