Related papers: Enhancing the Preference Extractor in Multi-turn D…
Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing…
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…
Preference optimization is a standard approach to fine-tuning large language models to align with human preferences. The quantity, diversity, and representativeness of the preference dataset are critical to the effectiveness of preference…
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…
Recent studies have shown that large language models' (LLMs) mathematical problem-solving capabilities can be enhanced by integrating external tools, such as code interpreters, and employing multi-turn Chain-of-Thought (CoT) reasoning.…
Alignment with human preferences is an important step in developing accurate and safe large language models. This is no exception in machine translation (MT), where better handling of language nuances and context-specific variations leads…
Proactively predicting a users next utterance in human-machine dialogue can streamline interaction and improve user experience. Existing commercial API-based solutions are subject to privacy concerns while deploying general-purpose LLMs…
With the improvements in speech recognition and voice generation technologies over the last years, a lot of companies have sought to develop conversation understanding systems that run on mobile phones or smart home devices through natural…
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…
The use of propagandistic techniques in online content has increased in recent years aiming to manipulate online audiences. Fine-grained propaganda detection and extraction of textual spans where propaganda techniques are used, are…
Dialogue data has been a key source for understanding learning processes, offering critical insights into how students engage in collaborative discussions and how these interactions shape their knowledge construction. The advent of Large…
Multi-turn response selection is a task designed for developing dialogue agents. The performance on this task has a remarkable improvement with pre-trained language models. However, these models simply concatenate the turns in dialogue…
Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems. However, collecting a large amount of turn-by-turn annotated dialogue data is costly and inefficient. In this paper, we propose a novel turn-level…
Preference optimization methods have been successfully applied to improve not only the alignment of large language models (LLMs) with human values, but also specific natural language tasks such as summarization and stylistic continuations.…
The development of largely human-annotated benchmarks has driven the success of deep neural networks in various NLP tasks. To enhance the effectiveness of existing benchmarks, collecting new additional input-output pairs is often too costly…
Pairwise preference data have played an important role in the alignment of large language models (LLMs). Each sample of such data consists of a prompt, two different responses to the prompt, and a binary label indicating which of the two…
In this paper, we study the problem of data augmentation for language understanding in task-oriented dialogue system. In contrast to previous work which augments an utterance without considering its relation with other utterances, we…
Tool-Augmented Larage Language Models (TA-LLMs) have shown promise in real-world applications, but face challenges in handling incomplete queries and out-of-scope requests. While existing approaches rely mainly on Supervised Fine-Tuning…
Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information…
In sequential recommendation, models recommend items based on user's interaction history. To this end, current models usually incorporate information such as item descriptions and user intent or preferences. User preferences are usually not…