Related papers: Preference Discovery in Large Product Lines
The recent increase in the volume of online meetings necessitates automated tools for managing and organizing the material, especially when an attendee has missed the discussion and needs assistance in quickly exploring it. In this work, we…
We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for evaluating AI code review quality. Evaluated against an LLM-as-judge framework validated at kappa=0.75, 8 frontier models detect only 15-31% of…
We propose a novel prompt design paradigm that challenges conventional wisdom in large language model (LLM) prompting. While conventional wisdom prioritizes well-crafted instructions and demonstrations for in-context learning (ICL), we show…
Mixup linearly interpolates pairs of examples to form new samples, which is easy to implement and has been shown to be effective in image classification tasks. However, there are two drawbacks in mixup: one is that more training epochs are…
As artificial intelligence becomes more powerful and a ubiquitous presence in daily life, it is imperative to understand and manage the impact of AI systems on our lives and decisions. Modern ML systems often change user behavior (e.g.…
Large Language Models (LLMs) have advanced recommendation capabilities through enhanced reasoning, but pose significant challenges for real-world deployment due to high inference costs. Conversely, while Small Language Models (SLMs) offer…
Large language models (LLMs) have shown the potential to be integrated into human daily lives. Therefore, user preference is the most critical criterion for assessing LLMs' performance in real-world scenarios. However, existing benchmarks…
Generative models are increasingly powerful, yet users struggle to guide them through prompts. The generative process is difficult to control and unpredictable, and user instructions may be ambiguous or under-specified. Prior prompt…
Conversational assistants are being progressively adopted by the general population. However, they are not capable of handling complicated information-seeking tasks that involve multiple turns of information exchange. Due to the limited…
Recommender systems are one of the most applied methods in machine learning and find applications in many areas, ranging from economics to the Internet of things. This article provides a general overview of modern approaches to recommender…
As large language models (LLMs) become integral to intelligent user interfaces (IUIs), their role as decision-making agents raises critical concerns about alignment. Although extensive research has addressed issues such as factuality, bias,…
Current recommender systems employ large-sized embedding tables with uniform dimensions for all features, leading to overfitting, high computational cost, and suboptimal generalizing performance. Many techniques aim to solve this issue by…
Large language models struggle to accumulate evidence across multiple rounds of user interaction, failing to update their beliefs in a manner consistent with Bayesian inference. Existing solutions require fine-tuning on sensitive user…
Modern machine learning algorithms are increasingly computationally demanding, requiring specialized hardware and distributed computation to achieve high performance in a reasonable time frame. Many hyperparameter search algorithms have…
Aspects such as limited resources, frequently changing market demands, and different technical restrictions regarding the implementation of software requirements (features) often demand for the prioritization of requirements. The task of…
Since software performance requirements are documented in natural language, quantifying them into mathematical forms is essential for software engineering. Yet, the vagueness in performance requirements and uncertainty of human cognition…
Generative query suggestion using large language models offers a powerful way to enhance conversational systems, but aligning outputs with nuanced user preferences remains a critical challenge. To address this, we introduce a multi-stage…
A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the…
With the expansion of business scales and scopes on online platforms, multi-scenario matching has become a mainstream solution to reduce maintenance costs and alleviate data sparsity. The key to effective multi-scenario recommendation lies…
Trust between humans and multi-agent robotic swarms may be analyzed using human preferences. These preferences are expressed by an individual as a sequence of ordered comparisons between pairs of swarm behaviors. An individual's preference…