Related papers: Instruct Once, Chat Consistently in Multiple Round…

Aligning large language models (LLMs) with human expectations requires high-quality instructional dialogues, which usually require instructions that are diverse and in-depth. Existing methods leverage two LLMs to interact for automatic…

Open large language models (LLMs) have significantly advanced the field of natural language processing, showcasing impressive performance across various tasks.Despite the significant advancements in LLMs, their effective operation still…

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…

The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. However, the core of these systems has not changed much since…

Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks. However, both discrete prompting and continuous prompting assume fixed prompts for all data…

Current instruction data synthesis methods primarily focus on single-turn instructions and often neglect cross-turn coherence, resulting in context drift and reduced task completion rates in extended conversations. To address this…

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…

Large language models (LLMs), due to their advanced natural language capabilities, have seen significant success in applications where the user interface is usually a conversational artificial intelligence (AI) agent and engages the user…

Despite the multi-turn open-domain dialogue systems have attracted more and more attention and made great progress, the existing dialogue systems are still very boring. Nearly all the existing dialogue models only provide a response when…

Large language models (LLMs) are powerful dialogue agents, but specializing them towards fulfilling a specific function can be challenging. Instructing tuning, i.e. tuning models on instruction and sample responses generated by humans…

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…

Accurate multi-turn intent classification is essential for advancing conversational AI systems. However, challenges such as the scarcity of comprehensive datasets and the complexity of contextual dependencies across dialogue turns hinder…

Ever since the successful application of sequence to sequence learning for neural machine translation systems, interest has surged in its applicability towards language generation in other problem domains. Recent work has investigated the…

While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the…

In neural dialogue modeling, a neural network is trained to predict the next utterance, and at inference time, an approximate decoding algorithm is used to generate next utterances given previous ones. While this autoregressive framework…

Automatic translation systems offer a powerful solution to bridge language barriers in scenarios where participants do not share a common language. However, these systems can introduce errors leading to misunderstandings and conversation…

Recent advancements in instruction-tuning datasets have predominantly focused on specific tasks like mathematical or logical reasoning. There has been a notable gap in data designed for aligning language models to maintain topic relevance…

Unified multimodal models (UMMs) have achieved remarkable progress yet remain constrained by a single-turn interaction paradigm, effectively functioning as solvers for independent requests rather than assistants in continuous dialogue. To…

Conversational agents have traditionally been developed for either task-oriented dialogue (TOD) or open-ended chitchat, with limited progress in unifying the two. Yet, real-world conversations naturally involve fluid transitions between…

Open-domain conversation models have become good at generating natural-sounding dialogue, using very large architectures with billions of trainable parameters. The vast training data required to train these architectures aggregates many…