make-source-provenance-architectural-attention-bias TEC-0144 · proposedMake source provenance an architectural attention bias
Tag each input token with a discrete origin ring, add a learned origin embedding scaled by a learnable gate, and add a learned ring-by-ring bias to attention logits that suppresses attention from assistant/user queries to untrusted-source k
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.
Tag each input token with a discrete origin ring, add a learned origin embedding scaled by a learnable gate, and add a learned ring-by-ring bias to attention logits that suppresses attention from assistant/user queries to untrusted-source k Filed by the drafting stage from Origin Is All You Need: Provenance-Aware Transformers for Structural Trust-Boundary Separation (2609.21088) 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: Attack success rate on one in-distribution (SEP, 4,375) and three out-of-distribution injection sets (PI-Attack, DataSentinel, Math-Tutor) across four base models, against an architecture-free same-data SFT baseline and ten published defenses; OOD ASR <=0.05% versus 2.3-17.8% for SFT. Utility via AlpacaEval 2.0 length-controlled win rate against the base model (48.8-60.9% for three models, 42.7% for Mistral). Zeroing the attention bias at inference raises OOD ASR to 12-98%; skipping stage 1 leaves ASR unchanged but collapses win rate.. 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.