相关论文: The Phantom Steering Effect in Q&A Websites
Human-AI collaboration is often proposed to improve high-stakes decision-making, yet the influence of increased stakes and imperfect AI on decision-making strategies is not fully understood. Studying such behavior in realistic settings is…
People assume different and important roles within social networks. Some roles have received extensive study: that of influencers who are well-connected, and that of brokers who bridge unconnected parts of the network. However, very little…
Fads, product adoption, mobs, rumors, memes, and emergent norms are diverse social contagions that have been modeled as network cascades. Empirical study of these cascades is vulnerable to what we describe as the "opacity problem": the…
In this paper we consider an online recommendation setting, where a platform recommends a sequence of items to its users at every time period. The users respond by selecting one of the items recommended or abandon the platform due to…
Opinionated users often seek information that aligns with their preexisting beliefs while dismissing contradictory evidence due to confirmation bias. This conduct hinders their ability to consider alternative stances when searching the web.…
Community-based question answering platforms can be rich sources of information on a variety of specialized topics, from finance to cooking. The usefulness of such platforms depends heavily on user contributions (questions and answers), but…
People often stick to their existing beliefs, ignoring contradicting evidence or only interacting with those who reinforce their views. Social media platforms often facilitate such tendencies of homophily and echo-chambers as they promote…
Many human-facing algorithms -- including those that power recommender systems or hiring decision tools -- are trained on data provided by their users. The developers of these algorithms commonly adopt the assumption that the data…
Are rewards or penalties more effective in influencing user behavior? This work compares the effectiveness of subsidies and tolls in incentivizing users in congestion games. The predominantly studied method of influencing user behavior in…
We have conducted three empirical studies of the effects of friend recommendations and general ratings on how online users make choices. These two components of social influence were investigated through user studies on Mechanical Turk. We…
A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at hand and perturbs representations along…
The Web has enabled one of the most visible recent developments in education---the deployment of massive open online courses. With their global reach and often staggering enrollments, MOOCs have the potential to become a major new mechanism…
In recent years, Blockchain-based Online Social Media (BOSM) platforms have evolved fast due to the advancement of blockchain technology. BOSM can effectively overcome the problems of traditional social media platforms, such as a single…
For their attractiveness, comprehensiveness and dynamic coverage of relevant topics, community-based question answering sites such as Stack Overflow heavily rely on the engagement of their communities: Questions on new technologies,…
Online comments significantly influence users' judgments, yet their presentation, often determined by platform algorithms, can introduce biases, such as anchoring effects, which distort reasoning. While existing research emphasizes…
Software testing is an integral part of modern software engineering practice. Past research has not only underlined its significance, but also revealed its multi-faceted nature. The practice of software testing and its adoption is…
Learning from the crowd has become increasingly popular in the Web and social media. There is a wide variety of crowdlearning sites in which, on the one hand, users learn from the knowledge that other users contribute to the site, and, on…
We study the effect of different persona on \textbf{sycophancy}: model's agreement with users even when the user is incorrect. The standard mitigation, Contrastive Activation Addition (CAA), derives a steering direction from labelled pairs…
A growing number of software-intensive systems are being accused of violating or ignoring human values (e.g., privacy, inclusion, and social responsibility), and this poses great difficulties to individuals and society. Such violations…
Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…