Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
47
This work designs two interventions to reduce offloading decisions: metacognitive feedback that makes the implications of offloading for users explicit, and an effort-based reward that incentivizes less extensive LLM assistance.
AutoSynthesis achieves expert-level meta-analysis with automated precision, making evidence synthesis scalable and accessible.
LLMs can automate reproducibility assessments, achieving a 41% recovery rate of effect sizes鈥攐utperforming human analysts.
GenAI coding assistants boost developer productivity, but the gains shrink outside the lab and don't translate to better learning.
