Investigating Non-Transitivity in LLM-as-a-Judge
원문 초록
Automatic evaluation methods based on large language models (LLMs) are emerging as the standard tool for assessing the instruction-following abilities of LLM-based agents. The most common method in this paradigm, pairwise comparisons with a baseline model, critically depends on the assumption of transitive preferences. However, the validity of this assumption remains largely unexplored. In this study, we investigate the presence of non-transitivity within the AlpacaEval framework and analyze its effects on model rankings. We find that LLM judges exhibit non-transitive preferences, leading to rankings that are sensitive to the choice of the baseline model. To mitigate this issue, we show that round-robin tournaments combined with Bradley-Terry models of preference can produce more reliable rankings. Notably, our method increases both the Spearman correlation and the Kendall correlation with Chatbot Arena (95.0% -> 96.4% and 82.1% -> 86.3% respectively). To address the computational cost of round-robin tournaments, we propose Swiss-Wise Iterative Matchmaking (Swim) tournaments, using a dynamic matching strategy to capture the benefits of round-robin tournaments while maintaining computational efficiency.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
TuneShield: Mitigating Toxicity in Conversational AI while Fine-tuning on Untrusted Data
Project Riley: Multimodal Multi-Agent LLM Collaboration with Emotional Reasoning and Voting
From Roots to Rewards: Dynamic Tree Reasoning with RL
DCR: Quantifying Data Contamination in LLMs Evaluation
U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV
토론
이 논문과 연결된 포럼 글이 아직 없습니다.