DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4


Human preference judgments are pivotal in guiding large language models (LLMs) to produce outputs that align with human values. Human evaluations are also used in summarization tasks to compare outputs from various systems, complementing existing automatic metrics. Despite their significance, however, there has been limited research probing these pairwise or k-wise comparisons. The collective impact and relative importance of factors such as output length, informativeness, fluency, and factual consistency are still not well understood. It is also unclear if there are other hidden factors influencing human judgments. In this paper, we conduct an in-depth examination of a collection of pairwise human judgments released by OpenAI. Utilizing the Bradley-Terry-Luce (BTL) model, we reveal the inherent preferences embedded in these human judgments. We find that the most favored factors vary across tasks and genres, whereas the least favored factors tend to be consistent, e.g., outputs are too brief, contain excessive off-focus content or hallucinated facts. Our findings have implications on the construction of balanced datasets in human preference evaluations, which is a crucial step in shaping the behaviors of future LLMs.

In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Kaiqiang Song
Kaiqiang Song
Senior Research Scientist

Kaiqiang Song (宋凯强) is a Senior Research Scientist at Tencent AI Lab, Seattle, specializing in Natural Language Processing. His research focuses on advancing artificial intelligence through machine learning, NLP, and large language models. He is dedicated to optimizing AI model architectures for practical applications like text summarization and text generation, bridging the gap between foundational AI research and real-world impact.