Search papers, labs, and topics across Lattice.
7
0
9
53
Improving descriptive reasoning trace quality can actually hinder recommendation effectiveness, challenging assumptions about the benefits of interpretability in AI systems.
Current benchmarks may mislead researchers about the necessity of complex modeling, as simple recency-weighted methods outperform advanced architectures in several cases.
Hypothesis-driven shelves can dramatically increase the diversity of personalized recommendations while maintaining competitive engagement metrics.
Grounding LLM evaluations in historical user behavior can boost relevance judgment accuracy by over 15%, making them more aligned with actual user preferences.
Forget full retraining: intelligently selecting data subsets using gradient-based representations can keep your generative recommender fresh and robust to drift.
Forget tool-augmented systems: NEO shows you can consolidate search, recommendation, and reasoning into a single language-steerable LLM by representing items as SIDs and interleaving them with natural language.
Spotify's GLIDE model proves that generative LLMs can drive significant gains in podcast discovery and non-habitual listening in a real-world, production environment.
