Related papers: "I'd rather just go to bed": Understanding Indirec…

We investigate the problem of generating informative questions in information-asymmetric conversations. Unlike previous work on question generation which largely assumes knowledge of what the answer might be, we are interested in the…

Large language models often respond to ambiguous requests by implicitly committing to one interpretation, frustrating users and creating safety risks when that interpretation is wrong. We propose generating a single structured response that…

Intimacy is a fundamental aspect of how we relate to others in social settings. Language encodes the social information of intimacy through both topics and other more subtle cues (such as linguistic hedging and swearing). Here, we introduce…

This paper presents a dataset collected from natural dialogs which enables to test the ability of dialog systems to learn new facts from user utterances throughout the dialog. This interactive learning will help with one of the most…

Indirectness is a common feature of daily communication, yet is underexplored in NLP research for both low-resource as well as high-resource languages. Indirect Question Answering (IQA) aims at classifying the polarity of indirect answers.…

Human communication relies on common ground (CG), the mutual knowledge and beliefs shared by participants, to produce coherent and interesting conversations. In this paper, we demonstrate that current response generation (RG) models produce…

We investigate the task of modeling open-domain, multi-turn, unstructured, multi-participant, conversational dialogue. We specifically study the effect of incorporating different elements of the conversation. Unlike previous efforts, which…

Encoder-decoder based neural architectures serve as the basis of state-of-the-art approaches in end-to-end open domain dialog systems. Since most of such systems are trained with a maximum likelihood~(MLE) objective they suffer from issues…

This paper studies a fundamental mechanism of how to detect a conflict between arguments given sentiments regarding acceptability of the arguments. We introduce a concept of the inverse problem of the abstract argumentation to tackle the…

Effective dialogue involves grounding, the process of establishing mutual knowledge that is essential for communication between people. Modern dialogue systems are not explicitly trained to build common ground, and therefore overlook this…

While improving neural dialogue agents' factual accuracy is the object of much research, another important aspect of communication, less studied in the setting of neural dialogue, is transparency about ignorance. In this work, we analyze to…

We introduce a comprehensive benchmark for conversational memory evaluation containing 75,336 question-answer pairs across diverse categories including user facts, assistant recall, abstention, preferences, temporal changes, and implicit…

Large language models hold significant promise in multilingual applications. However, inherent biases stemming from predominantly English-centric pre-training have led to the widespread practice of pre-translation, i.e., translating…

Language is a popular resource to mine speakers' attitude bias, supposing that speakers' statements represent their bias on concepts. However, psychology studies show that people's explicit bias in statements can be different from their…

Metaphor pervades everyday language, allowing speakers to express abstract concepts via concrete domains. While prior work has studied metaphors cognitively and psycholinguistically, large-scale comparisons with literal language remain…

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…

The overall objective of 'social' dialogue systems is to support engaging, entertaining, and lengthy conversations on a wide variety of topics, including social chit-chat. Apart from raw dialogue data, user-provided ratings are the most…

We implement a divide-and-concur iterative projection approach to context-free grammar inference. Unlike most state-of-the-art models of natural language processing, our method requires a relatively small number of discrete parameters,…

We explore unconstrained natural language feedback as a learning signal for artificial agents. Humans use rich and varied language to teach, yet most prior work on interactive learning from language assumes a particular form of input (e.g.,…

Smooth and effective communication requires the ability to perform latent or explicit commonsense inference. Prior commonsense reasoning benchmarks (such as SocialIQA and CommonsenseQA) mainly focus on the discriminative task of choosing…