Research map / Large language models / Language, safety and interpretability
Cognitive model priors for predicting human decisions
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Pretrain on synthetic BEAST15 choices, then fine-tune on human data | MLP · CPC15 | MSE: 0.88 -> 0.53 (MSE×100) | Helped |
| Pretrain on synthetic BEAST18 choices, then fine-tune on human data | MLP · CPC18 | MSE: 0.57 -> 0.48 (MSE×100) | Helped |
| Pretrain on the BEAST15 cognitive prior | MLP · choices13k validation, 100% training data | MSE: 0.00947 versus 0.00945 | Helped |
| Pretrain on the BEAST15 cognitive prior | MLP · choices13k validation | MSE: 0.016 versus 0.039 | Helped |
| Use the cognitive model prior with 25% of training data | MLP · choices13k validation | MSE: decrease by 0.0009 | Helped |
| Use the cognitive model prior with 50% of training data | MLP · choices13k validation | MSE: decrease by 0.0003 | Helped |
| Use the cognitive model prior with 75% of training data | MLP · choices13k validation | MSE: decrease by 0.0002 | Helped |
| Reduce the block parameter from five blocks to two (ablation) | choices13k experiment design · choices13k | predictive accuracy | No clear effect |
| Fine-tune a cognitive-prior MLP instead of training from random initialization | MLP · choices13k validation, training efficiency | epochs to converge | Helped |
| Use sparse connections in the MLP (ablation) | MLP · choices13k validation | MSE: 1.03 -> 0.91 (MSE×100) | Helped |
Closest papers by meaning
- Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice (ICLR 2025 · similarity 0.89)
- Preference Learning of Latent Decision Utilities with a Human-like Model of Preferential Choice (NeurIPS 2024 · similarity 0.88)
- Conformal Prediction Sets Improve Human Decision Making (ICML 2024 · similarity 0.87)
- Large Language Models Assume People are More Rational than We Really are (ICLR 2025 · similarity 0.87)
- Decoding AI’s Nudge: A Unified Framework to Predict Human Behavior in AI-Assisted Decision Making (AAAI 2024 · similarity 0.86)
- Turning large language models into cognitive models (ICLR 2024 · similarity 0.86)
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.