Related papers: When to reply? Context Sensitive Models to Predict…

Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response length. Existing inference-time approaches for mitigating these…

Influencer marketing has become a widely used strategy for reaching customers. Despite growing interest among influencers and brand partners in predicting engagement with influencer videos, there has been little research on the relative…

Streaming algorithms are typically analyzed in the oblivious setting, where we assume that the input stream is fixed in advance. Recently, there is a growing interest in designing adversarially robust streaming algorithms that must maintain…

In recent times, online education and the usage of video-conferencing platforms have experienced massive growth. Due to the limited scope of a virtual classroom, it may become difficult for instructors to analyze learners' attention and…

Analyzing individual emotions during group conversation is crucial in developing intelligent agents capable of natural human-machine interaction. While reliable emotion recognition techniques depend on different modalities (text, audio,…

Explicitly alerting users is not always an optimal intervention, especially when they are not motivated to obey. For example, in video-based learning, learners who are distracted from the video would not follow an alert asking them to pay…

Immersive learning environments such as virtual classrooms in Virtual Reality (VR) offer learners unique learning experiences, yet providing effective learner support remains a challenge. While prior HCI research has explored in-lecture…

Advancements in Large Language Models (LLMs), such as ChatGPT, offer significant opportunities to enhance instructional support in introductory programming courses. While extensive research has explored the effectiveness of LLMs in…

As large language models increasingly mediate firm - customer interactions, firms face a tradeoff: the most capable models perform well but are costly and difficult to control at scale. Existing knowledge distillation methods address this…

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

This paper investigates context stickiness in in-context learning (ICL), a phenomenon where earlier examples in a prompt interfere with a transformer's ability to adapt to later tasks. Using synthetic regression tasks over linear and…

When a teacher provides examples for a student to study, these examples must be informative, enabling a student to progress from their current state toward a target concept or skill. Good teachers must therefore simultaneously infer what…

Contextualised word vectors obtained via pre-trained language models encode a variety of knowledge that has already been exploited in applications. Complementary to these language models are probabilistic topic models that learn thematic…

Understanding the inner workings of large language models (LLMs) is crucial for advancing their theoretical foundations and real-world applications. While the attention mechanism and multi-layer perceptrons (MLPs) have been studied…

How to improve the quality of conversations in online communities has attracted considerable attention recently. Having engaged, urbane, and reactive online conversations has a critical effect on the social life of Internet users. In this…

In-context learning is a recent paradigm in natural language understanding, where a large pre-trained language model (LM) observes a test instance and a few training examples as its input, and directly decodes the output without any update…

In-context learning has become a popular paradigm in natural language processing. However, its performance can be significantly influenced by the order of in-context demonstration examples. In this paper, we found that causal language…

Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…

Forum discussion data differ in both structure and properties from generic form of textual data such as news. Henceforth, summarization techniques should, in turn, make use of such differences, and craft models that can benefit from the…

Modern sequential recommender systems commonly use transformer-based models for next-item prediction. While these models demonstrate a strong balance between efficiency and quality, integrating interleaving features - such as the query…