Related papers: Aligning Spoken Dialogue Models from User Interact…

Preference tuning is a crucial process for aligning deep generative models with human preferences. This survey offers a thorough overview of recent advancements in preference tuning and the integration of human feedback. The paper is…

Conversational recommendation frameworks have gained prominence as a dynamic paradigm for delivering personalized suggestions via interactive dialogues. The incorporation of advanced language understanding techniques has substantially…

As large language models (LLMs) demonstrate increasingly advanced capabilities, aligning their behaviors with human values and preferences becomes crucial for their wide adoption. While previous research focuses on general alignment to…

AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a…

End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceiling in expressiveness and perceptual ability than cascaded systems. However, the intelligence and expressiveness of current…

While textless Spoken Language Models (SLMs) have shown potential in end-to-end speech-to-speech modeling, they still lag behind text-based Large Language Models (LLMs) in terms of semantic coherence and relevance. This work introduces the…

Multi-turn user interactions are among the most abundant data produced by language models, yet we lack effective methods to learn from them. While typically discarded, these interactions often contain useful information: follow-up user…

Smart assistants increasingly act proactively, yet mistimed or intrusive behavior often causes users to lose trust and disable these features. Learning user preferences for proactive assistance is difficult because real-world studies are…

A major bottleneck for building statistical spoken dialogue systems for new domains and applications is the need for large amounts of training data. To address this problem, we adopt the multi-dimensional approach to dialogue management and…

As large language models (LLMs) enter the mainstream, aligning them to foster constructive dialogue rather than exacerbate societal divisions is critical. Using an individualized and multicultural alignment dataset of over 7,500…

Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these…

The deployment of Large Language Models (LLMs) in interactive systems necessitates a deep alignment with the nuanced and dynamic preferences of individual users. Current alignment techniques predominantly address universal human values or…

Learning from human feedback has become a pivot technique in aligning large language models (LLMs) with human preferences. However, acquiring vast and premium human feedback is bottlenecked by time, labor, and human capability, resulting in…

An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate…

In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. Dialogue systems are increasingly being designed to move beyond just imitating conversation and also…

As large language models (LLMs) increasingly permeate daily lives, there is a growing demand for real-time interactions that mirror human conversations. Traditional turn-based chat systems driven by LLMs prevent users from verbally…

Learning from human preferences is important for language models to match human needs and to align with human and social values. Prior works have achieved remarkable successes by learning from human feedback to understand and follow…

The proliferation of AI agents, with their complex and context-dependent actions, renders conventional privacy paradigms obsolete. This position paper argues that the current model of privacy management, rooted in a user's unilateral…

Multi-turn dialogues are characterized by their extended length and the presence of turn-taking conversations. Traditional language models often overlook the distinct features of these dialogues by treating them as regular text. In this…

Existing open-domain dialog models are generally trained to minimize the perplexity of target human responses. However, some human replies are more engaging than others, spawning more followup interactions. Current conversational models are…