5 accepted papers
The powerful generative abilities of large language models (LLMs) show potential in generating relevance labels for search applications. Previous work has found that directly asking about relevancy, such as "*How relevant is document A to query Q?*”, results in suboptimal ranking. Instead, the pairw…
Local feature selection in machine learning provides instance-specific explanations by focusing on the most relevant features for each prediction, enhancing the interpretability of complex models. However, such methods tend to produce misleading explanations by encoding additional information in the…
Computing the gradient of stochastic Plackett-Luce (PL) ranking models for relevance and fairness metrics can be infeasible because it requires iterating over all possible permutations of items. In this paper, we introduce a novel algorithm: PL-Rank, that estimates the gradient of a PL ranking mode…
Model interpretability has become an important problem in machine learning (ML) due to the increased effect algorithmic decisions have on humans. Counterfactual explanations can help users understand not only why ML models make certain decisions, but also how these decisions can be changed. We f…
State-of-the-art Learning to Rank (LTR) methods for optimizing ranking systems based on user interactions are divided into online approaches – that learn by direct interaction – and counterfactual approaches – that learn from historical interactions. We propose a novel intervention-aware estimator t…