Related papers: Large-scale Hybrid Approach for Predicting User Sa…
Recently, large language models have facilitated the emergence of highly intelligent conversational AI capable of engaging in human-like dialogues. However, a notable distinction lies in the fact that these AI models predominantly generate…
State-of-the-art conversational agents have advanced significantly in conjunction with the use of large transformer-based language models. However, even with these advancements, conversational agents still lack the ability to produce…
Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. They can also be used to introduce a diverse group discussion step in chatbot pipelines, enhancing the cultural…
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why…
Popular conversational agents frameworks such as Alexa Skills Kit (ASK) and Google Actions (gActions) offer unprecedented opportunities for facilitating the development and deployment of voice-enabled AI solutions in various verticals.…
Enhancing fuel efficiency in public transportation requires the integration of complex multimodal data into interpretable, decision-relevant insights. However, traditional analytics and visualization methods often yield fragmented outputs…
Consumer applications provide ample opportunities to surface and communicate various forms of content to users. From promotional campaigns for new features or subscriptions, to evergreen nudges for engagement, or personalised…
Active learning can play an important role in low-resource settings (i.e., where annotated data is scarce), by selecting which instances may be more worthy to annotate. Most active learning approaches for Machine Translation assume the…
As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated datasets, are limited by their…
LLM implementations are failing in highly regulated industries owing to instability issues, inconsistent reasoning, hallucinations and performance variability, especially in workflows. These reliability issues restrict safe use of LLM in…
Learning rewards from preference feedback has become an important tool in the alignment of agentic models. Preference-based feedback, often implemented as a binary comparison between multiple completions, is an established method to acquire…
Developing robots that can assist humans efficiently, safely, and adaptively is crucial for real-world applications such as healthcare. While previous work often assumes a centralized system for co-optimizing human-robot interactions, we…
Evaluating recommender systems remains challenging due to the gap between offline metrics and real user behavior, as well as the scarcity of interaction data. Recent work explores large language model (LLM) agents as synthetic users, yet…
A long-standing challenge in developing accurate recommendation models is simulating user behavior, mainly due to the complex and stochastic nature of user interactions. Towards this, one promising line of work has been the use of Large…
Many computer scientists use the aggregated answers of online workers to represent ground truth. Prior work has shown that aggregation methods such as majority voting are effective for measuring relatively objective features. For subjective…
Players in the online ad ecosystem are struggling to acquire the user data required for precise targeting. Audience look-alike modeling has the potential to alleviate this issue, but models' performance strongly depends on quantity and…
A major challenge in Natural Language Processing is obtaining annotated data for supervised learning. An option is the use of crowdsourcing platforms for data annotation. However, crowdsourcing introduces issues related to the annotator's…
Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We…
Recommender systems rely heavily on the predictive accuracy of the learning algorithm. Most work on improving accuracy has focused on the learning algorithm itself. We argue that this algorithmic focus is myopic. In particular, since…
Today, a large proportion of end user information systems have their Graphical User Interfaces (GUI) built with web-based technology (JavaScript, CSS, and HTML). Some of these web-based systems include: Internet of Things (IOT),…