Expired50% confidenceFactExact time
Top-tier models have approached the level of human judges on many evaluation tasks, but exhibit biases such as a tendency to give higher scores to longer responses
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/6/2026(expired)
Sources
构建长效AI智能体的七大核心组件详解
bilibiliTOP高效学习法7/6/2026
Related Claims
UnverifiedHuman annotators exhibit a cognitive bias toward more information being better when evaluating answers, causing reward models to implicitly link length with quality, which is one of the causes of model verbosity.77% similarUnverifiedResearch shows that human evaluators in RLHF tend to prefer longer, more detailed, and friendlier-toned responses, even when those responses are not superior in factual accuracy.74% similarUnverifiedIn the current mainstream alignment method RLHF (Reinforcement Learning from Human Feedback), raters tend to give higher scores to responses that exceed expectations and provide additional value, incentivizing models to fulfill needs the user has not explicitly expressed72% similarUnverified简历评估应使用会批判的模型而非过度迎合（sycophantic）的模型，否则会将夸大成就照单全收给出虚高评价71% similarPartially VerifiedLarge model evaluation mechanisms (how to ensure that large model outputs meet user requirements) are a frequently asked topic in recent enterprise interviews.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/232847API
curl https://kongchang.com/api/v1/knowledge/claims/232847MCP
get_claim(id=232847)