Search papers, labs, and topics across Lattice.
Dartmouth College
4
1
6
33
Mitigating stereotypes in NLP can backfire, leading to increased bias against other groups, a phenomenon often missed by standard evaluation metrics.
Significant variations in stereotypical behavior across Spanish-speaking countries reveal the limitations of English-centric stereotype datasets in AI.
Online political discussions tend to be intellectual humility echo chambers, but simple interventions can break the cycle and foster more open-mindedness.
LLMs can reason through chains of thought 2.5x longer and solve more complex math problems by optimizing for the influence of each token on future reasoning steps.
