147 citations · 479 across the 25 of their papers we have counts for
17 papers · 1 filter
A transfer learning framework for weak-to-strong generalization
Seamus Somerstep, Felipe Maia Polo, Moulinath Banerjee +3
Modern large language model (LLM) alignment techniques rely on human feedback, but it is unclear whether these techniques fundamentally limit the capabilities of aligned LLMs. In p…
Weak Supervision Performance Evaluation via Partial Identification
Felipe Maia Polo, Subha Maity, Mikhail Yurochkin +2
Programmatic Weak Supervision (PWS) enables supervised model training without direct access to ground truth labels, utilizing weak labels from heuristics, crowdsourcing, or pre-tra…
An Investigation of Representation and Allocation Harms in Contrastive Learning
Subha Maity, Mayank Agarwal, Mikhail Yurochkin +1
The effect of underrepresentation on the performance of minority groups is known to be a serious problem in supervised learning settings; however, it has been underexplored so far…
Post-processing for Individual Fairness
Felix Petersen, Debarghya Mukherjee, Yuekai Sun +1
Post-processing in algorithmic fairness is a versatile approach for correcting bias in ML systems that are already used in production. The main appeal of post-processing is that it…
Statistical inference for individual fairness
Subha Maity, Songkai Xue, Mikhail Yurochkin +1
As we rely on machine learning (ML) models to make more consequential decisions, the issue of ML models perpetuating or even exacerbating undesirable historical biases (e.g., gende…
Individually Fair Ranking
Amanda Bower, Hamid Eftekhari, Mikhail Yurochkin +1
We develop an algorithm to train individually fair learning-to-rank (LTR) models. The proposed approach ensures items from minority groups appear alongside similar items from major…