Zhendong Wang

Yisi Han, Zhendong Wang, Yang Feng et al.

The success of an open source software (OSS) project requires effective communication among its members. Given that OSS projects often have established social status systems, much communication may happen between individuals of different statuses, particularly, elite developers who have project management privileges and ordinary project contributors. Since sociolinguistics literature and our prior work have found that groups in different status would be likely develop different language styles, which may hinder critical cross status communication, and hereby influence the outcomes of the project. We seek to develop an understanding of cross status communication, as well as its impacts on the outcomes of an OSS project in terms of productivity and quality. The anticipated results describe the linguistic similarities and differences of cross status communication and reveal the relationships between these linguistic similarities and differences and project outcomes.

Zhendong Wang, Yang Feng, Yi Wang et al.

Open-source developers, particularly the elite developers, maintain a diverse portfolio of contributing activities. They do not only commit source code but also spend a significant amount of effort on other communicative, organizational, and supportive activities. However, almost all prior research focuses on a limited number of specific activities and fails to analyze elite developers' activities in a comprehensive way. To bridge this gap, we conduct an empirical study with fine-grained event data from 20 large open-source projects hosted on GitHub. Thus, we investigate elite developers' contributing activities and their impacts on project outcomes. Our analyses reveal three key findings: (1) they participate in a variety of activities while technical contributions (e.g., coding) accounting for a small proportion only; (2) they tend to put more effort into supportive and communicative activities and less effort into coding as the project grows; (3) their participation in non-technical activities is negatively associated with the project's outcomes in term of productivity and software quality. These results provide a panoramic view of elite developers' activities and can inform an individual's decision making about effort allocation, thus leading to finer project outcomes. The results also provide implications for supporting these elite developers.

Cheng-Han Chiang, Xiaofei Wang, Linjie Li et al. · microsoft-research

Spoken Language Models (SLMs) are designed to take speech inputs and produce spoken responses. However, current SLMs lack the ability to perform an internal, unspoken thinking process before responding. In contrast, humans typically engage in complex mental reasoning internally, enabling them to communicate ideas clearly and concisely. Thus, integrating an unspoken thought process into SLMs is highly desirable. While naively generating a complete chain-of-thought (CoT) reasoning before starting to talk can enable thinking for SLMs, this induces additional latency for the speech response, as the CoT reasoning can be arbitrarily long. To solve this issue, we propose Stitch, a novel generation method that alternates between the generation of unspoken reasoning chunks and spoken response chunks. Since the audio duration of a chunk of spoken response is much longer than the time to generate the tokens in a chunk of spoken response, we use the remaining free time to generate the unspoken reasoning tokens. When a chunk of audio is played to the user, the model continues to generate the next unspoken reasoning chunk, achieving simultaneous thinking and talking. Remarkably, Stitch matches the latency of baselines that cannot generate unspoken CoT by design while outperforming those baselines by 15% on math reasoning datasets; Stitch also performs equally well on non-reasoning datasets as those baseline models. Some animations and demonstrations are on the project page: https://d223302.github.io/STITCH.

Cheng-Han Chiang, Xiaofei Wang, Linjie Li et al.

Current large language models (LLMs) and spoken language models (SLMs) begin thinking and taking actions only after the user has finished their turn. This prevents the model from interacting during the user's turn and can lead to high response latency while it waits to think. Consequently, thinking after receiving the full input is not suitable for speech-to-speech interaction, where real-time, low-latency exchange is important. We address this by noting that humans naturally "think while listening." In this paper, we propose SHANKS, a general inference framework that enables SLMs to generate unspoken chain-of-thought reasoning while listening to the user input. SHANKS streams the input speech in fixed-duration chunks and, as soon as a chunk is received, generates unspoken reasoning based on all previous speech and reasoning, while the user continues speaking. SHANKS uses this unspoken reasoning to decide whether to interrupt the user and to make tool calls to complete the task. We demonstrate that SHANKS enhances real-time user-SLM interaction in two scenarios: (1) when the user is presenting a step-by-step solution to a math problem, SHANKS can listen, reason, and interrupt when the user makes a mistake, achieving 37.1% higher interruption accuracy than a baseline that interrupts without thinking; and (2) in a tool-augmented dialogue, SHANKS can complete 56.9% of the tool calls before the user finishes their turn. Overall, SHANKS moves toward models that keep thinking throughout the conversation, not only after a turn ends. Animated illustrations of Shanks can be found at https://d223302.github.io/SHANKS/