Research map / Large language models / AI and society
Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory
Ankur Sikarwar, Mengmi Zhang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| compare GRU with LSTM and RNN at same capacity | recurrent WM models · SMU task | recall accuracy | Improved |
| increase memory capacity from 96 to 256 | RNN · SMU task | recall accuracy | Improved |
| use recurrent backbone (LSTM/GRU) instead of transformer | WM models · WorM tasks | accuracy | Improved |
| increase list length L | LSTM-256 · VSR | top-1 accuracy | Hurt |
| retention interval 0 to 5 | WM models · VIR | accuracy | No clear effect |
| add spatial distractor task / higher cognitive load | WM model · CS | accuracy | Hurt |
| add visual distractor task | WM model · CS | accuracy | No clear effect |
| increase set size | recurrent models · SMU | recall accuracy | Hurt |
| increase set size | TRF-96 · SMU | recall accuracy | Improved |
| increase pattern-distractor difference n | WM models · VSRec | accuracy | Improved |
| vary feature conditions in CD | WM models · CD | accuracy | No clear effect |
| switch from joint training to single-task VSR training (ablation) | LSTM-256 · VSR | primacy/recency effect | No clear effect |
Closest papers by meaning
- Generating Computational Cognitive models using Large Language Models (NeurIPS 2025 · similarity 0.89)
- Geometry of naturalistic object representations in recurrent neural network models of working memory (NeurIPS 2024 · similarity 0.89)
- Working Memory Capacity of ChatGPT: An Empirical Study (AAAI 2024 · similarity 0.88)
- Turning large language models into cognitive models (ICLR 2024 · similarity 0.87)
- Simulating Human Memory with Language Models (NeurIPS 2026 · similarity 0.87)
- CogBench: a large language model walks into a psychology lab (ICML 2024 · similarity 0.87)
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.
