AI Paper Atlas

Research map / Large language models / Alignment and preferences

Personalized Reasoning: Just-in-time Personalization and Why LLMs Fail at It

Shuyue Stella Li, Avinandan Bose, Faeze Brahman, Simon Shaolei Du, Pang Wei Koh, Maryam Fazel, Yulia Tsvetkov

ICLR 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior

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
attempt preference discovery by asking questions (vs generic baseline)21 frontier LLMs · PrefDisco, 10 tasksnormalized preference alignment: 61 of 210 model-task combinations negative (29.0%)Mixed
ask more questions before answeringdiscovery mode LLMs · PrefDisco, 10 taskspreference alignment: r=0.445Improved
provide full ground-truth preferences (oracle) in the promptfrontier LLMs · PrefDisco, 10 taskstask accuracy (%): 65.2 -> 61.8Hurt
add interactive preference discoveryfrontier LLMs · PrefDisco, 10 taskstask accuracy (%): 65.2 -> 60.1Hurt
add personalization constraintsfrontier LLMs · AIMEtask accuracy (%): 12.1% lossHurt
add personalization constraintsfrontier LLMs · CommonsenseQAtask accuracy (%): 5.4% gainImproved
add personalization constraintsfrontier LLMs · mathematical reasoning (summary)task accuracy (%): 3.5% accuracy lossHurt
add personalization constraintsfrontier LLMs · social reasoning (summary)task accuracy (%): 3.1% gainImproved
force a fixed number of questions (2, 4 or 8) instead of letting the model stop (ablation)discovery mode LLMs · MATH and MascQA vs CommonsenseQA and SocialIQApreference alignment: Auto: 1.4 turns vs Fixed: 8.0 turnsMixed
use newer model (Claude Sonnet-4 instead of Claude 3-Opus)Claude models · PrefDisco discovery alignmentnormalized preference alignmentMixed

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