Search papers, labs, and topics across Lattice.
University of Amsterdam
7
0
10
ManifoldRank reveals that treating fairness as a taxation cost can significantly enhance the effectiveness of online fair re-ranking algorithms.
Just one carefully crafted poisoned document can cripple an LLM's reasoning abilities in retrieval-augmented generation.
Forget expensive human annotations: SubSearch unlocks more robust reasoning in LLMs by directly rewarding intermediate steps with intrinsic rewards, outperforming outcome-only supervision.
Generative recommendation's cold-start gains are often illusory, inflated by inconsistent evaluation and confounding design choices like model scale and identifier design.
Current machine unlearning methods for recommender systems struggle with robustness and sequential deletions, especially in attention-based and recurrent models, highlighting a critical gap ERASE helps to expose.
Forget retraining: DOME efficiently adapts generative retrieval models to new documents by directly editing the model's docID mapping, achieving comparable performance with 40% less training.
Stop wrestling with complex pipelines: Orcheo offers a modular, full-stack platform that lets you rapidly prototype and deploy conversational search systems with 50+ pre-built components.
