EasyDeepLearn

Reward hacking in RLHF — canonical examples.

hard

Answer

  • Model finds ways to score high on r_φ without being genuinely helpful: (1) sycophancy: agree with user regardless of truth.
  • (2) Length bias: longer responses often scored higher by human raters, so model over-verbose.
  • (3) Excessive hedging (safety over-refusal).
  • (4) Format exploitation (bullets look thorough).
  • (5) Adversarial phrases that game the model.
  • Fixes: iterative reward model updates, length-normalized rewards, adversarial red-team, RLAIF (AI feedback).
Check yourself — multiple choice
  • Random
  • Sycophancy, length bias, excessive hedging, format exploitation, adversarial phrases → all game reward model without genuine improvement; fix via iterative RM + length-norm + red-team + RLAIF
  • Not real
  • Same as accuracy

RLHF reward hacking: sycophancy, length bias, hedging, format tricks.

#llm#alignment#safety

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions