Related papers: EthicMind: A Risk-Aware Framework for Ethical-Emot…

Emotional support (ES) systems alleviate users' mental distress by generating strategic supportive dialogues based on diverse user situations. However, ES systems are limited in their ability to generate effective ES dialogues that include…

Language Model Models (LLMs) have improved dramatically in the past few years, increasing their adoption and the scope of their capabilities over time. A significant amount of work is dedicated to ``model alignment'', i.e., preventing LLMs…

The reasoning capability of large language models (LLMs), defined as their ability to analyze, infer, and make decisions based on input information, is essential for building intelligent task-oriented dialogue systems. However, existing…

This study establishes a novel framework for systematically evaluating the moral reasoning capabilities of large language models (LLMs) as they increasingly integrate into critical societal domains. Current assessment methodologies lack the…

Reasoning-oriented language models typically expose explicit reasoning as a long, front-loaded chain of "thinking" tokens before the main output, either always enabled or externally toggled at inference time. Although this can help on…

Dialogue models falter in noisy, multi-speaker environments, often producing irrelevant responses and awkward turn-taking. We present AV-Dialog, the first multimodal dialog framework that uses both audio and visual cues to track the target…

The ethics of emerging technologies faces an anticipation dilemma: engaging too early risks overly speculative concerns, while engaging too late may forfeit the chance to shape a technology's trajectory. Despite various methods to address…

This research develops advanced methodologies for Large Language Models (LLMs) to better manage linguistic behaviors related to emotions and ethics. We introduce DIKE, an adversarial framework that enhances the LLMs' ability to internalize…

Artificial Intelligence (AI) systems are increasingly placed in positions where their decisions have real consequences, e.g., moderating online spaces, conducting research, and advising on policy. Ensuring they operate in a safe and…

Conversational agents have come increasingly closer to human competence in open-domain dialogue settings; however, such models can reflect insensitive, hurtful, or entirely incoherent viewpoints that erode a user's trust in the moral…

Generative AI systems (ChatGPT, DALL-E, etc) are expanding into multiple areas of our lives, from art Rombach et al. [2021] to mental health Rob Morris and Kareem Kouddous [2022]; their rapidly growing societal impact opens new…

Ethics has become a major concern to the information management community, as both algorithms and data should satisfy ethical rules that guarantee not to generate dishonourable behaviours when they are used. However, these ethical rules may…

Dialogue safety remains a pervasive challenge in open-domain human-machine interaction. Existing approaches propose distinctive dialogue safety taxonomies and datasets for detecting explicitly harmful responses. However, these taxonomies…

Enhancing user engagement through interactions plays an essential role in socially-driven dialogues. While prior works have optimized models to reason over relevant knowledge or plan a dialogue act flow, the relationship between user…

This article offers several contributions to the interdisciplinary project of responsible research and innovation in data science and AI. First, it provides a critical analysis of current efforts to establish practical mechanisms for…

Intelligent dialogue systems are increasingly used in modern education and psychological counseling fields, but most existing systems are limited to a single domain, cannot deal with both educational and psychological issues, and often lack…

Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined…

Demand for mental health support through AI chatbots is surging, though current systems present several limitations, like sycophancy or overvalidation, and reinforcement of maladaptive beliefs. A core obstacle to the creation of better…

We propose a novel preference alignment framework for improving spoken dialogue models on real-time conversations from user interactions. Current preference learning methods primarily focus on text-based language models, and are not…

Ethics review is a foundational mechanism of modern research governance, yet contemporary systems face increasing strain as ethical risks arise as structural consequences of large-scale, interdisciplinary scientific practice. The demand for…