相关论文: Causal Document-Grounded Dialogue Pre-training

There is an increasing demand for task-oriented dialogue systems which can assist users in various activities such as booking tickets and restaurant reservations. In order to complete dialogues effectively, dialogue policy plays a key role…

Causality has the potential to truly transform the way we solve a large number of real-world problems. Yet, so far, its potential largely remains to be unlocked as causality often requires crucial assumptions which cannot be tested in…

We present DMCD (DataMap Causal Discovery), a two-phase causal discovery framework that integrates LLM-based semantic drafting from variable metadata with statistical validation on observational data. In Phase I, a large language model…

In this paper, we initiate an attempt of developing an end-to-end chat-centric video understanding system, coined as VideoChat. It integrates video foundation models and large language models via a learnable neural interface, excelling in…

Using offline datasets to evaluate conversational agents often fails to cover rare scenarios or to support testing new policies. This has motivated the use of controllable user simulators for targeted, counterfactual evaluation, typically…

Task-oriented dialogue is difficult in part because it involves understanding user intent, collecting information from the user, executing API calls, and generating helpful and fluent responses. However, for complex tasks one must also…

Instruction tuning is an emergent paradigm in NLP wherein natural language instructions are leveraged with language models to induce zero-shot performance on unseen tasks. Instructions have been shown to enable good performance on unseen…

Task-oriented dialog(TOD) aims to assist users in achieving specific goals through multi-turn conversation. Recently, good results have been obtained based on large pre-trained models. However, the labeled-data scarcity hinders the…

To facilitate zero-shot generalization in taskoriented dialog, this paper proposes Language Models as Data (LAD). LAD is a paradigm for creating diverse and accurate synthetic data which conveys the necessary structural constraints and can…

Text-based dialogues are now widely used to solve real-world problems. In cases where solution strategies are already known, they can sometimes be codified into workflows and used to guide humans or artificial agents through the task of…

Dialogue segmentation is a crucial task for dialogue systems allowing a better understanding of conversational texts. Despite recent progress in unsupervised dialogue segmentation methods, their performances are limited by the lack of…

Large Language Models (LLMs) have shown their success in language understanding and reasoning on general topics. However, their capability to perform inference based on user-specified structured data and knowledge in corpus-rare concepts,…

Understanding what leads to effective conversations can aid the design of better computer-mediated communication platforms. In particular, prior observational work has sought to identify behaviors of individuals that correlate to their…

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…

Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets. However, written dialogues are not sufficient to fully capture the nature of spoken conversations as well as the potential speech…

Visually-grounded dialog systems, which integrate multiple modes of communication such as text and visual inputs, have become an increasingly popular area of investigation. However, the absence of a standardized evaluation framework poses a…

While most conversational AI systems focus on textual dialogue only, conditioning utterances on visual context (when it's available) can lead to more realistic conversations. Unfortunately, a major challenge for incorporating visual context…

Perceiving multi-modal information and fulfilling dialogues with humans is a long-term goal of artificial intelligence. Pre-training is commonly regarded as an effective approach for multi-modal dialogue. However, due to the limited…

Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text…

Current efficient fine-tuning methods (e.g., adapters, prefix-tuning, etc.) have optimized conditional text generation via training a small set of extra parameters of the neural language model, while freezing the rest for efficiency. While…