Xiaofeng Wang

Wenhong Zhu, Zhiwei He, Xiaofeng Wang et al.

Aligning language models (LMs) with human preferences has become a key area of research, enabling these models to meet diverse user needs better. Inspired by weak-to-strong generalization, where a strong LM fine-tuned on labels generated by a weaker model can consistently outperform its weak supervisor, we extend this idea to model alignment. In this work, we observe that the alignment behavior in weaker models can be effectively transferred to stronger models and even exhibit an amplification effect. Based on this insight, we propose a method called Weak-to-Strong Preference Optimization (WSPO), which achieves strong model alignment by learning the distribution differences before and after the alignment of the weak model. Experiments demonstrate that WSPO delivers outstanding performance, improving the win rate of Qwen2-7B-Instruct on Arena-Hard from 39.70 to 49.60, achieving a remarkable 47.04 length-controlled win rate on AlpacaEval 2, and scoring 7.33 on MT-bench. Our results suggest that using the weak model to elicit a strong model with a high alignment ability is feasible.

Daniel Graziotin, Fabian Fagerholm, Xiaofeng Wang et al.

The growing literature on affect among software developers mostly reports on the linkage between happiness, software quality, and developer productivity. Understanding the positive side of happiness -- positive emotions and moods -- is an attractive and important endeavor. Scholars in industrial and organizational psychology have suggested that also studying the negative side -- unhappiness -- could lead to cost-effective ways of enhancing working conditions, job performance, and to limiting the occurrence of psychological disorders. Our comprehension of the consequences of (un)happiness among developers is still too shallow, and is mainly expressed in terms of development productivity and software quality. In this paper, we attempt to uncover the experienced consequences of unhappiness among software developers. Using qualitative data analysis of the responses given by 181 questionnaire participants, we identified 49 consequences of unhappiness while doing software development. We found detrimental consequences on developers' mental well-being, the software development process, and the produced artifacts. Our classification scheme, available as open data, will spawn new happiness research opportunities of cause-effect type, and it can act as a guideline for practitioners for identifying damaging effects of unhappiness and for fostering happiness on the job.