AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

RPM: Reasoning-Level Personalization for Black-Box Large Language Models

Jieyong Kim, Tongyoung Kim, SooJin Yoon, Jaehyung Kim, Dongha Lee

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Faithfulness of LLM explanations · 1 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 RPM reasoning-level personalization vs best response-level baselinesGPT-4o-mini · LaMP-2accuracy: 0.526 -> 0.561Improved
add RPM vs best baselineGPT-4o-mini · LaMP-3MAE: 0.312 -> 0.259Improved
add chain-of-thought prompting to baselinesICL, RAG, HYDRA, Fermi · LaMP-2accuracy: 0.526 -> 0.493 (RAG)Hurt
add personalized reasoning generation for the target query (ablation)RPM · LaMP-3MAE: 0.305 -> 0.259Improved
add personalized reasoning generation for the target query (ablation)RPM · GOQAaccuracy: 0.820 -> 0.852Improved
use generic CoT reasoning examples instead of personalized reasoning (ablation)few-shot prompting · LaMP-3MAE: 0.274 -> 0.385Hurt
add personalized reasoning paths with features and factors (ablation)few-shot with features/factors · GOQAaccuracy: 0.806 -> 0.852Improved
add user factors and target features to zero-shot input (ablation)zero-shot · LaMP-3MAE: 0.361 -> 0.287Improved
add user factors and target features to zero-shot input (ablation)zero-shot · LaMP-5ROUGE-1: 0.446 -> 0.427Hurt
retrieve with extracted features instead of raw query (ablation)RPM over reasoning-augmented history · LaMP-2accuracy: 0.542 -> 0.561Improved
retrieve with extracted features instead of raw query (ablation)RPM over reasoning-augmented history · LaMP-3MAE: 0.272 -> 0.259Improved
retrieve with features from raw history instead of reasoning-augmented history (ablation)RPM · GOQAaccuracy: 0.809 -> 0.852Improved

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