Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
0
Shifting the focus from topical relevance to answerability, CLEAR reveals that many conversational retrievers miss the mark by overlooking critical answer-supporting passages.
Skewed item distributions in recommendation systems can be tamed with a learnable non-uniform quantization, leading to better codebook utilization and more accurate generative recommendations.
