Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Reranking

In pointwise document reranking, Chain-of-Thought models consistently underperform direct scoring models, a gap that persists across models up to 32B parameters. The authors conducted stress tests—reinforcement learning, fine‑grained supervision, and architectural decoupling—to address classification, score polarization, and calibration issues, which improved absolute scores but did not close the relative ranking gap. Their results indicate that routing continuous relevance semantics through discrete text imposes a stable bottleneck in ranking resolution that current standard methods cannot easily overcome.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• rag
• reinforcement-learning
• safety