concept
active
concept:reward-model-sycophancy

Reward model sycophancy

Hidden objective of the target model: exploiting believed RM biases.

Neighborhood — ranked by edge-count

Frameworks (1)

framework
  • Auditing games
    associated_with
    Methodology measuring interpretability tool uplift for an agent uncovering hidden behaviors.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.