Knowledge Editing

TL;DR for operators AI systems do not merely fail by giving the wrong answer. They also fail by changing the kind of action they take when the meaning has not changed, or by spreading an update into places where it was never supposed to go. That is the shared lesson from two recent papers that, at first glance, live in different neighborhoods. One studies code-mixed hate moderation and shows that clean-English-tuned workflows can route the same underlying content differently when it appears as Tamil-English code-mix.1 The other studies multimodal knowledge editing and proposes a method for updating model knowledge so corrections generalize to related queries without disturbing visually or semantically nearby but unrelated facts.2 ...

Memory is useful until nobody can find where it lives. That, in miniature, is the operational problem with today’s language models. They can answer questions, imitate expertise, retrieve fragments of the past, and produce very confident nonsense with the composure of a senior consultant who has just discovered bullet points. But when a model gives a wrong factual answer, the organisation deploying it faces an awkward question: where, exactly, is that wrong fact stored? ...

TL;DR for operators Large language models age badly. Product names change, policies expire, executives move, medical or legal guidance becomes stale, and some facts in pre-training were never right in the first place. The usual repair options are clumsy: retrain the model, fine-tune it, hide updated facts in prompts, or bolt on retrieval and hope the model behaves. All useful. All annoying in different ways. ...