Related papers: Exploring the Escalation of Source Bias in User, D…

Large language models (LLMs) have the potential to transform our lives and work through the content they generate, known as AI-Generated Content (AIGC). To harness this transformation, we need to understand the limitations of LLMs. Here, we…

Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing preference learning methods rely heavily on curated data from…

The rapid proliferation of Artificial Intelligence-Generated Content (AIGC) is fundamentally restructuring online content ecologies, necessitating a rigorous examination of its behavioral and distributional implications. Leveraging a…

Recommender systems continually retrain on user reactions to their own predictions, creating AI feedback loops that amplify biases and diminish fairness over time. Despite this well-known risk, most bias mitigation techniques are tested…

Large language model-based agents are increasingly applied in the recommendation field due to their extensive knowledge and strong planning capabilities. While prior research has primarily focused on enhancing either the recommendation…

An increasing reliance on recommender systems has led to concerns about the creation of filter bubbles on social media, especially on short video platforms like TikTok. However, their formation is still not entirely understood due to the…

Attributing answers to source documents is an approach used to enhance the verifiability of a model's output in retrieval augmented generation (RAG). Prior work has mainly focused on improving and evaluating the attribution quality of large…

Recently, the emergence of large language models (LLMs) has revolutionized the paradigm of information retrieval (IR) applications, especially in web search, by generating vast amounts of human-like texts on the Internet. As a result, IR…

Selection bias is prevalent in the data for training and evaluating recommendation systems with explicit feedback. For example, users tend to rate items they like. However, when rating an item concerning a specific user, most of the…

Traditional recommender systems (RecSys) primarily infer user preferences from implicit signals (such as clicks, watches, and purchases), often neglecting the rich explicit contextual feedback users provide through verbal text, like…

To address the challenges of digital intelligence in the digital economy, artificial intelligence-generated content (AIGC) has emerged. AIGC uses artificial intelligence to assist or replace manual content generation by generating content…

As generative AI models, particularly large language models (LLMs), transform educational feedback practices in higher education (HE) contexts, understanding students' perceptions of different sources of feedback becomes crucial for their…

Recommendation algorithms are known to suffer from popularity bias; a few popular items are recommended frequently while the majority of other items are ignored. These recommendations are then consumed by the users, their reaction will be…

Recommender systems are indispensable because they influence our day-to-day behavior and decisions by giving us personalized suggestions. Services like Kindle, Youtube, and Netflix depend heavily on the performance of their recommender…

Recommender systems play a key role in shaping modern web ecosystems. These systems alternate between (1) making recommendations (2) collecting user responses to these recommendations, and (3) retraining the recommendation algorithm based…

With the advancement of generation models, AI-generated content (AIGC) is becoming more realistic, flooding the Internet. A recent study suggests that this phenomenon causes source bias in text retrieval for web search. Specifically, neural…

User simulation is increasingly vital to develop and evaluate recommender systems (RSs). While Large Language Models (LLMs) offer promising avenues to simulate user behavior, they often struggle with the absence of specific task alignment…

Artificial Intelligence-Generated Content (AIGC) refers to the use of AI to automate the information creation process while fulfilling the personalized requirements of users. However, due to the instability of AIGC models, e.g., the…

This paper explores the evolving relationship between clinician trust in LLMs, the transformation of data sources from predominantly human-generated to AI-generated content, and the subsequent impact on the precision of LLMs and clinician…

Prediction-based decision-making systems are becoming increasingly prevalent in various domains. Previous studies have demonstrated that such systems are vulnerable to runaway feedback loops, e.g., when police are repeatedly sent back to…