AI Paper Atlas

Research map / Large language models / Alignment and preferences

T-POP: Test-Time Personalization with Online Preference Feedback

Zikun Qu, Min Zhang, Mingze Kong, Xiang Li, Zhiwei Shang, Zhiyong Wang, Yikun Ban, Shuang Qiu, Yao Shu, Zhongxiang Dai

ICML 2026 · Large language models › Alignment and preferences · approach: LLM-as-judge and feedback data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add gradient-norm uncertainty bonus instead of random exploration (ablation)T-POP · Personal concise, Llama-3.1-8BArmoRM score: 0.51 -> 0.64Improved
use entropy bonus instead of random exploration (ablation)T-POP · Personal concise, Llama-3.1-8BArmoRM score: 0.51 -> 0.53No clear effect
use Boltzmann exploration instead of random exploration (ablation)T-POP · Personal concise, Llama-3.1-8BArmoRM score: 0.51 -> 0.57Improved
raise reward weight omega from 0.1 to 1.0 (ablation)T-POP · three backbonesArmoRM scoreImproved
raise reward weight omega from 1.0 to 2.0 and 5.0 (ablation)T-POP · three backbonesArmoRM scoreHurt
increase candidate size k from 10 to 20 (ablation)T-POP · Personal concise, Llama-3.1-8BArmoRM score: 0.642 -> 0.659Improved
increase candidate size k from 40 to 80 (ablation)T-POP · Personal concise, Llama-3.1-8BArmoRM score: 0.656 -> 0.633Hurt
flip 30% of preference labels (ablation)T-POP · Personal concise, Llama-3.1-8BArmoRM score: 0.656 -> 0.649No clear effect
flip 90% of preference labels (ablation)T-POP · Personal concise, Llama-3.1-8BArmoRM score: 0.656 -> 0.493Hurt
inject 60% local noise in middle phase versus uniform noise (ablation)T-POP · Personal concise, Llama-3.1-8BArmoRM score: 0.651 -> 0.643Hurt
inject 60% local noise in late phase versus uniform noise (ablation)T-POP · Personal concise, Llama-3.1-8BArmoRM score: 0.651 -> 0.656No clear effect
apply T-POP to Llama-3.2-1B-Instructbase model · ArmoRM personalizationArmoRM score: 0.28 -> 0.44Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy