Related papers: Red Teaming Language Models for Processing Contrad…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability. In this paper, we propose a novel framework to pre-train language models for enhancing…

In this paper, we introduce the task of learning unsupervised dialogue embeddings. Trivial approaches such as combining pre-trained word or sentence embeddings and encoding through pre-trained language models (PLMs) have been shown to be…

Recent research has explored using Large Language Models for recommendation tasks by transforming user interaction histories and item metadata into text prompts, then having the LLM produce rankings or recommendations. A promising approach…

Transformer-based pre-trained models have achieved great improvements in semantic matching. However, existing models still suffer from insufficient ability to capture subtle differences. The modification, addition and deletion of words in…

Real-world decision-making often begins with identifying which modality contains the most relevant information for a given query. While recent multimodal models have made impressive progress in processing diverse inputs, it remains unclear…

Contrastive explanations for understanding the behavior of black box models has gained a lot of attention recently as they provide potential for recourse. In this paper, we propose a method Contrastive Attributed explanations for Text (CAT)…

To promote constructive discussion of controversial topics online, we propose automatic reframing of disagreeing responses to signal receptiveness to a preceding comment. Drawing on research from psychology, communications, and linguistics,…

While Large Language Models have transformed how we interact with AI systems, they suffer from a critical flaw: they confidently generate false information that sounds entirely plausible. This hallucination problem has become a major…

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…

This perspective calls for scholars across disciplines to address the challenge of audio deepfake detection and discernment through an interdisciplinary lens across Artificial Intelligence methods and linguistics. With an avalanche of tools…

Model diffing is the study of how fine-tuning changes a model's representations and internal algorithms. Many behaviors of interest are introduced during fine-tuning, and model diffing offers a promising lens to interpret such behaviors.…

Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and text. However, their performance in handling conflicting…

We present a multi-task learning framework to enable the training of one universal incremental dialogue processing model with four tasks of disfluency detection, language modelling, part-of-speech tagging, and utterance segmentation in a…

In this paper, we propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems to avoid generic responses and model dialogue history better. In contrast to standard adversarial training algorithms, IAT…

We identify agreement and disagreement between utterances that express stances towards a topic of discussion. Existing methods focus mainly on conversational settings, where dialogic features are used for (dis)agreement inference. We extend…

The development of sophisticated artificial intelligence (AI) conversational agents based on large language models raises important questions about the relationship between human norms, values, and practices and AI design and performance.…

Assessing the trustworthiness of artificial intelligence systems requires knowledge from many different disciplines. These disciplines do not necessarily share concepts between them and might use words with different meanings, or even use…

We consider the paradigm of a black box AI system that makes life-critical decisions. We propose an "arguing machines" framework that pairs the primary AI system with a secondary one that is independently trained to perform the same task.…

Text-to-image diffusion models excel at generating high-quality, diverse images from natural language prompts. However, they often fail to produce semantically accurate results when the prompt contains concept combinations that contradict…