read-impossibility-answerable-null-residual-subspace TEC-0290 · proposedRead impossibility from the answerable-null residual subspac
Fit PCA on hidden states of answerable prompts, project all states out of that subspace, and score the mean-difference direction between answerable and impossible prompts by cosine to detect pre-generation impossibility.
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Fit PCA on hidden states of answerable prompts, project all states out of that subspace, and score the mean-difference direction between answerable and impossible prompts by cosine to detect pre-generation impossibility. Filed by the drafting stage from Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions (2608.29109) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: One-dimensional cosine probe on held-out answerable/unanswerable splits, 5 seeds, 22 model-dataset cells: mean AUC 0.939 in the answerable-null subspace vs 0.907 full residual stream and 0.890 top-k answerable-PC subspace; generation-time steering along the direction changed invalidity-aware behaviour bidirectionally (+33 to +52pp gated flip over matched random directions) while random directions did not.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.