🚀NEW LABGetting Started with Claude AgentsStart lab
Evaluation

Shepherd

First page
Shepherd
Paper summary

Meta's Shepherd is a 7B language model specifically tuned to critique model outputs and suggest refinements.

Ask this paper

Key points
01

Critique-specialized 7B: A 7B parameter model fine-tuned specifically on the task of critiquing LLM responses and suggesting improvements.

02

Error identification: Capable of identifying diverse error types - factual, logical, stylistic, safety - and suggesting remedies for each.

03

ChatGPT-comparable critiques: Human evaluators judge Shepherd's critiques as similar or preferred to ChatGPT's, despite Shepherd being much smaller.

04

Critic-as-a-service: Points toward a deployment pattern where small specialized critic models are paired with larger generation models, a recurring theme in 2024 alignment work.

Every Monday
Get next week’s papers.
Subscribe on Substack