AI Paper Atlas

Research map / Large language models / AI and society

TRIPLE: Theory-Driven Integration of Planned and Habitual Behaviors for LLM-based Personalization

Taehyung Noh, Seungwan Jin, Haein Yeo, Kyungsik Han

AAAI 2026 · Large language models › AI and society · approach: Data commons and human baselines · 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 behavioral rationale to habit+intention profiles (ablation)TRIPLE (Llama-3.1-70B) · LaMP-5BLEU: 10.484 -> 11.467Improved
add behavioral rationale to habit+intention profiles (ablation)TRIPLE (Llama-3.1-70B) · LaMP-4BLEU: 3.810 -> 4.994Improved
add behavioral rationale to habit+intention profiles (ablation)TRIPLE (Llama-3.1-70B) · LaMP-3MAE: 0.290 -> 0.280Improved
add behavioral rationale to habit+intention profiles (ablation)TRIPLE (Llama-3.1-70B) · LaMP-2Maccuracy: 0.648 -> 0.610Hurt
add intention profile and rationale on top of habit profile (ablation)TRIPLE (Llama-3.1-70B) · LaMP-2Naccuracy: 0.805 -> 0.795Hurt
add intention profile to habit profile, without rationale (ablation)TRIPLE (Llama-3.1-70B) · LaMP-4BLEU: 4.394 -> 3.810Hurt
add habit profile to raw history (ablation)In-context baseline (Llama-3.1-70B) · LaMP-5BLEU: 4.048 -> 10.178Improved
use intention profile only instead of habit profile (ablation)TRIPLE (Llama-3.1-70B) · LaMP-5BLEU: 10.178 -> 9.049Hurt
TRIPLE vs best baseline on generationTRIPLE (Llama-3.1-70B) · LaMP-5BLEU: 7.341 -> 11.467Improved
TRIPLE vs best baseline on generationTRIPLE (Llama-3.1-8B) · LaMP-4BLEU: 0.961 -> 3.868Improved
TRIPLE vs best baseline on classificationTRIPLE (Llama-3.1-8B) · LaMP-2Naccuracy: 0.805 -> 0.800No clear effect
TRIPLE vs PURE on scholarly title ROUGE-1TRIPLE (Llama-3.1-70B) · LaMP-5ROUGE-1: 0.511 -> 0.493Hurt

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