Tech Meridian ← LIVE FEED
RU

NEWS · RESEARCH · #331

Cappy: 360M-parameter RoBERTa scorer that authors say boosts and adapts large multi-task LLMs without finetuning

Google Research introduces Cappy, a lightweight (≈360M params) scorer based on continual pretraining of RoBERTa that assigns a 0–1 correctness score to an instruction–response pair. The authors report Cappy can operate standalone on classification tasks or be used as an auxiliary component to boost large multi-task LLMs and enable downstream supervision and adaptation without backpropagating through the LLM or needing access to its parameters (e.g., closed-source WebAPI models).

KEY POINTS

  1. Google Research introduces Cappy, a lightweight (≈360M params) scorer based on continual pretraining of RoBERTa that assigns a 0–1 correctness score to an instruction–response pair.
  2. The authors report Cappy can operate standalone on classification tasks or be used as an auxiliary component to boost large multi-task LLMs and enable downstream supervision and adaptation without backpropagating through the LLM or needing access to its parameters (e.g., closed-source WebAPI models).
  3. If the reported results hold, a small external scorer that enables supervision and adaptation of large or closed-source multi-task LLMs without finetuning could reduce compute/memory costs and broaden practical use of such models.

WHY IT MATTERS

If the reported results hold, a small external scorer that enables supervision and adaptation of large or closed-source multi-task LLMs without finetuning could reduce compute/memory costs and broaden practical use of such models.

SOURCES & TIMELINE

1