nagpalchirag.bsky.social
@nagpalchirag.bsky.social
Reposted
Excited to share that our paper, “Understanding challenges to the interpretation of evaluations of algorithmic fairness” has been accepted to NeurIPS 2025! You can read the paper now on arXiv: arxiv.org/abs/2506.04193.
Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness
Disaggregated evaluation across subgroups is critical for assessing the fairness of machine learning models, but its uncritical use can mislead practitioners. We show that equal performance across sub...
arxiv.org
October 28, 2025 at 12:36 AM
October 16, 2025 at 11:51 PM
𝙇𝙀𝙉𝙂𝙏𝙃 of generations from an 𝙇𝙇𝙈 is an important heuristic used in post-training to understand model behavior.

𝘽𝙐𝙏 due to a 𝙁𝙄𝙓𝙀𝘿 𝙎𝙄𝙕𝙀 𝘾𝙊𝙉𝙏𝙀𝙓𝙏 𝙒𝙄𝙉𝘿𝙊𝙒, a large number of trajectories get truncated before ever reaching [𝗘𝗢𝗦] token.

𝙃𝙊𝙒 𝙏𝙃𝙀𝙉 does one accurately estimate model generation length ?
October 16, 2025 at 11:50 PM
Direct preference optimization is cox regression
September 16, 2025 at 4:25 AM
Kernel regression is the only way to achieve AGI
September 11, 2025 at 4:26 AM