all tags

large-language-models

15 notes carry this tag — 9 claims, 1 observation, 2 questions, 3 captures. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

• Is Qi et al.'s (2023) ten-example fine-tuning jailbreak of GPT-3.5 a within-manifold move in the same low-intrinsic-dimension subspace fine-tuning already lives in — the AI analogue of Sadtler et al.'s (2014) within-manifold BCI-relearning result?
  capture seedling 2026-09-15 · neural-manifolds, intrinsic-dimension, dimensionality, fine-tuning, jailbreak
• 'Intrinsic dimension' already names two different objects inside machine learning — representation-space (activation) ID versus weight-space (objective-landscape) ID — and only the former is the same type of object as a neuroscience neural manifold (Ansuini et al. 2019)
  claim seedling Tier 1 2026-07-25 · dimensionality, intrinsic-dimension, representation-geometry, neural-manifolds, large-language-models
• GeLoRA derives the representation-space intrinsic dimension as a lower bound on the optimal rank of LoRA weight updates — the only located formal bridge between the two ML notions of intrinsic dimension (Ed-dib et al. 2024)
  claim seedling Tier 1 2026-07-25 · dimensionality, intrinsic-dimension, LoRA, representation-geometry, fine-tuning
• The 'intrinsic dimension' behind LLM fine-tuning originates as the codimension of a solution set in weight space, measured by random-subspace training (Li et al. 2018)
  claim seedling Tier 1 2026-07-25 · dimensionality, intrinsic-dimension, fine-tuning, LoRA, objective-landscape
• Is the 'low-dimensional subspace that constrains adaptation' one shared mathematical object across neural manifolds and LLM intrinsic dimension — or three analogies that share a shape?
  capture promoted 2026-07-19 · neural-manifolds, intrinsic-dimension, dimensionality, fine-tuning, LoRA
• Pre-training acts as an implicit compressor of the average NLP task — Aghajanyan et al.'s proposed mechanism for why larger, better-pretrained models have lower intrinsic dimension
  claim seedling Tier 1 2026-07-18 · dimensionality, fine-tuning, intrinsic-dimension, pre-training, compression
• LoRA shows GPT-3 175B's fine-tuning weight update has intrinsic rank as low as 1 or 2, extending the falling-intrinsic-dimension trend two orders of magnitude past Aghajanyan et al.'s test range
  claim seedling Tier 1 2026-07-18 · dimensionality, fine-tuning, intrinsic-dimension, LoRA, scaling
• Fine-tuning GPT-3.5 Turbo on just 10 adversarial examples, for under $0.20, jailbreaks its safety guardrails
  claim seedling Tier 1 2026-07-18 · safety-alignment, fine-tuning, jailbreak, large-language-models, fine-tuning-api-risk
• Larger LLMs' higher-dimensional activation spaces are associated with more exploitable linear safety structure, not less — a distinct dimensionality from fine-tuning's weight-space intrinsic dimension
  claim seedling Tier 1 2026-07-18 · dimensionality, safety-alignment, jailbreak, linear-representation-hypothesis, activation-engineering
• Safety alignment lies in a low-rank intrinsic subspace of the gradient — the same low-dimensional structure that makes it cheap to attack via fine-tuning also makes it cheap to repair, regardless of model size
  claim seedling Tier 1 2026-07-18 · dimensionality, safety-alignment, fine-tuning, jailbreak, intrinsic-dimension
• Why does the intrinsic dimension of fine-tuning fall as models get larger — and does that make bigger models geometrically safer to adapt?
  capture promoted Tier 1 2026-07-17 · dimensionality, fine-tuning, intrinsic-dimension, scaling, LoRA
• Fine-tuning a large language model has very low intrinsic dimension: 200 parameters tune RoBERTa to 90% of full performance on MRPC (Aghajanyan et al. 2020)
  claim seedling Tier 1 2026-07-12 · dimensionality, fine-tuning, LoRA, intrinsic-dimension, large-language-models
• The same shape — useful adaptation confined to a low-dimensional subspace of a much larger space — recurs across monkey motor cortex, artificial recurrent networks, and LLM fine-tuning
  observation seedling Tier 2 2026-07-12 · neural-manifolds, dimensionality, learning, fine-tuning, cross-domain-bridge
• Why does the intrinsic dimension of fine-tuning fall as models get larger — and does that make bigger models geometrically safer to adapt?
  question answered 2026-07-12 · dimensionality, fine-tuning, intrinsic-dimension, scaling, LoRA
• Is the 'low-dimensional subspace that constrains adaptation' one shared mathematical object across neural manifolds and LLM intrinsic dimension — or three analogies that share a shape?
  question open 2026-07-12 · neural-manifolds, dimensionality, cross-domain-convergence, fine-tuning, learning