architecture · debiasing-vector-separates-validity-plausibility TEC-0070 · proposed

Debiasing vector that separates validity from plausibility

Find the plausibility and validity directions in activation space, construct a vector that removes the plausibility component from the validity judgement, and add it at inference so conclusions are judged by form rather than believability.

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.

Find the plausibility and validity directions in activation space, construct a vector that removes the plausibility component from the validity judgement, and add it at inference so conclusions are judged by form rather than believability. Filed by the drafting stage from How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects (2510.06700) 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: Content-effect size and accuracy before and after steering across model sizes; causal steering in both directions; alignment-effect correlation across models. Open models only.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Deducing validly from logical structure

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

Either way, bring evidence: a link, or what you saw.

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.