Open Models Almanac
Methodspost-trainingreward modelling

single mention · post-training

Reward-scale calibration

Reward-scale calibration designs task rewards to have broadly comparable scales, so heterogeneous reward signals can be combined across tasks.1,2 In the described design, reward values typically fall in [0,1], with bonuses and penalties able to shift the final rewards outside this range.3

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. we design task rewards to have broadly comparable scales — technical report
  2. Each data source defines its own reward function by combining signals into a composite reward — technical report
  3. with values typically in [0,1] . Bonuses and penalties can shift the final rewards outside this range — technical report

Filed under post-training › reward modelling