# Cross-Prompt Reuse of Entity-Replacement Responses

**Authors:** Jinkun Chen, Xuemin Yu, Sijia Han, Vlado Keselj  
**Lab:** Dalhousie University · **Published:** 29 Oct 2026 · **Upvotes:** 2  
**Links:** [arXiv](https://arxiv.org/abs/2611.00352) · [PDF](https://arxiv.org/pdf/2611.00352) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.00352.html)

## Key numbers

- **50%**: Hidden reuse injects the aligned change at 50% depth before the target's remaining layers
- **45%**: hidden reuse removes 45% and 49% of no-change error on 0.5-1B Qwen and Llama
- **22%**: Gemma-2-2B removes 22% and passes one of three comparisons in plain text without its default beginning-of-sequence

## Abstract

With model weights fixed, we measure how much of an entity-replacement response transfers between English factual questions, beyond whether answers change. We add the hidden-state change from two source questions to a target question about the same entity, comparing the predicted log-probability shift between two relations' published answers, given known answer prefixes, with the measured one. Hidden reuse injects the aligned change at 50% depth before the target's remaining layers; direct reuse adds source output-score changes. With other-relation sources, hidden reuse removes 45% and 49% of no-change error on 0.5-1B Qwen and Llama. Gemma-2-2B removes 22% and passes one of three comparisons in plain text without its default beginning-of-sequence (BOS) token. A later protocol restoring it yields 58-68%, passing every comparison on three cohorts. Larger checkpoints, chat format and new entities show replication and format- or cohort-dependent failures. On small plain-format checkpoints, other-relation hidden reuse mainly reproduces the shift both relations' questions share, without reliably lowering relation-selective error. With target-relation sources, hidden reuse's post hoc advantage over direct reuse is 0.2-0.9 nats outside chat format, unconfirmed and not replacement-specific. The same relation-neutral change at both questions' entity tokens lowers relation-selective error more than random or other-replacement changes, indicating receiving-question dependence.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.