Zhi Liu

Stop chasing leaderboard gains on generic benchmarks: PJB reveals that domain-specific weaknesses in person-job retrieval far outweigh the benefits of general model upgrades, and that query understanding modules can actually hurt performance.

Ditch static embeddings: Generative retrieval, powered by reinforcement learning, lets models dynamically reason about relevance, outperforming larger contrastively-trained models on reasoning-intensive tasks.