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

Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Hassan Foroosh, Fei Liu


Abstract
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.
Anthology ID:
2023.emnlp-main.519
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8344–8357
Language:
URL:
https://aclanthology.org/2023.emnlp-main.519
DOI:
10.18653/v1/2023.emnlp-main.519
Bibkey:
Cite (ACL):
Yebowen Hu, Kaiqiang Song, Sangwoo Cho, Xiaoyang Wang, Hassan Foroosh, and Fei Liu. 2023. DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8344–8357, Singapore. Association for Computational Linguistics.
Cite (Informal):
DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4 (Hu et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.519.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.519.mp4