Related papers: CoDial: Interpretable Task-Oriented Dialogue Syste…

Large language models (LLMs)-based code generation for robotic manipulation has recently shown promise by directly translating human instructions into executable code, but existing methods remain noisy, constrained by fixed primitives and…

Large language models (LLMs) excel at generating code from natural language (NL) descriptions. However, the plain textual descriptions are inherently ambiguous and often fail to capture complex requirements like intricate system behaviors,…

Collaborative dialogue relies on participants incrementally establishing common ground, yet in asymmetric settings they may believe they agree while referring to different entities. We introduce a perspectivist annotation scheme for the…

In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's requests (\textit{a.k.a} dialogue state tracking) is key to a smooth interaction. Traditionally, TOD systems perform this update in three…

Large models have achieved remarkable performance across a range of reasoning and understanding tasks. Prior work often utilizes model ensembles or multi-agent systems to collaboratively generate responses, effectively operating in a…

Human computer interaction is shifting from screen-based systems to multimodal interfaces where artificial intelligence powered systems increasingly interpret user intent through speech, gesture, and gaze. Yet users rarely understand how…

Most previous studies integrate cognitive language processing signals (e.g., eye-tracking or EEG data) into neural models of natural language processing (NLP) just by directly concatenating word embeddings with cognitive features, ignoring…

Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing methods employ a fixed communication topology during inference, which falls short in many…

A significant application of Large Language Models (LLMs), like ChatGPT, is their deployment as chat agents, which respond to human inquiries across a variety of domains. While current LLMs proficiently answer general questions, they often…

Recent advances in test-time scaling have enabled Large Language Models (LLMs) to display sophisticated reasoning abilities via extended Chain-of-Thought (CoT) generation. Despite their potential, these Reasoning LLMs (RLMs) often…

Code-switching, alternating between languages within a conversation, is natural for multilingual users, yet poses fundamental challenges for large language models (LLMs). When a user code-switches in their prompt to an LLM, they typically…

Mechanism design has long been a cornerstone of economic theory, with traditional approaches relying on mathematical derivations. Recently, automated approaches, including differentiable economics with neural networks, have emerged for…

This study investigated effective strategies for developing a custom GPT to code classroom dialogue. While classroom dialogue is widely recognised as a crucial element of education, its analysis remains challenging due to the need for a…

COBOL remains a critical language for mainframe systems, yet existing large language models (LLMs) struggle to generate and translate COBOL code correctly. This paper reports our experience in developing and evaluating domain-adapted LLMs…

Integrating reasoning in large language models and large vision-language models has recently led to significant improvement of their capabilities. However, the generalization of reasoning models is still vaguely defined and poorly…

Recent advancements in large language models (LLMs) have led to significant progress in text-based dialogue systems. These systems can now generate high-quality responses that are accurate and coherent across a wide range of topics and…

We demonstrate experimental results with LLMs that address robotics task planning problems. Recently, LLMs have been applied in robotics task planning, particularly using a code generation approach that converts complex high-level…

Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains multiple ML models, including natural language understanding,…

Tool-augmented large language models (LLMs), hereafter LLM agents, leverage external tools to solve diverse tasks and interface with the real world. However, current training practices largely rely on supervised fine-tuning (SFT) over…

Visual dialog is a vision-language task where an agent needs to answer a series of questions grounded in an image based on the understanding of the dialog history and the image. The occurrences of coreference relations in the dialog makes…