相关论文: UniPCM: Universal Pre-trained Conversation Model w…

There is a wide variety of speech processing tasks ranging from extracting content information from speech signals to generating speech signals. For different tasks, model networks are usually designed and tuned separately. If a universal…

The use of large language models (LLMs) in natural language processing (NLP) tasks is rapidly increasing, leading to changes in how researchers approach problems in the field. To fully utilize these models' abilities, a better understanding…

Vision-language models have recently shown great potential on many tasks in computer vision. Meanwhile, prior work demonstrates prompt tuning designed for vision-language models could acquire superior performance on few-shot image…

Prompts are how humans communicate with LLMs. Informative prompts are essential for guiding LLMs to produce the desired output. However, prompt engineering is often tedious and time-consuming, requiring significant expertise, limiting its…

We present Multi-expert Prompting, a novel enhancement of ExpertPrompting (Xu et al., 2023), designed to improve the large language model (LLM) generation. Specifically, it guides an LLM to fulfill an input instruction by simulating…

Sentiment analysis is a crucial task that aims to understand people's emotional states and predict emotional categories based on multimodal information. It consists of several subtasks, such as emotion recognition in conversation (ERC),…

The task of visual dialog requires a multimodal chatbot to answer sequential questions from humans about image content. Prior work performs the standard likelihood training for answer generation on the positive instances (involving correct…

LLMs have shown promising results in task planning due to their strong natural language understanding and reasoning capabilities. However, issues such as hallucinations, ambiguities in human instructions, environmental constraints, and…

Based on the recently proposed transferable dialogue state generator (TRADE) that predicts dialogue states from utterance-concatenated dialogue context, we propose a multi-task learning model with a simple yet effective utterance tagging…

The emergence of instruction-tuned large language models (LLMs) has advanced the field of dialogue systems, enabling both realistic user simulations and robust multi-turn conversational agents. However, existing research often evaluates…

Classic pipeline models for task-oriented dialogue system require explicit modeling the dialogue states and hand-crafted action spaces to query a domain-specific knowledge base. Conversely, sequence-to-sequence models learn to map dialogue…

Large language models are increasingly deployed in multi-turn settings such as tutoring, support, and counseling, where reliability depends on preserving consistent roles, personas, and goals across long horizons. This requirement becomes…

Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate…

Training conversational question-answering (QA) systems requires a substantial amount of in-domain data, which is often scarce in practice. A common solution to this challenge is to generate synthetic data. Traditional methods typically…

Large Language Models (LLMs) have shown remarkable capabilities, with optimizing their input prompts playing a pivotal role in maximizing their performance. However, while LLM prompts consist of both the task-agnostic system prompts and…

We demonstrate, in this study, that an open-domain conversational system trained on idioms or figurative language generates more fitting responses to prompts containing idioms. Idioms are part of everyday speech in many languages, across…

Spontaneous spoken dialogue is often disfluent, containing pauses, hesitations, self-corrections and false starts. Processing such phenomena is essential in understanding a speaker's intended meaning and controlling the flow of the…

For task-oriented dialog systems to be maximally useful, it must be able to process conversations in a way that is (1) generalizable with a small number of training examples for new task domains, and (2) robust to user input in various…

Spoken dialogue systems promise efficient and natural access to a large variety of information sources and services from any phone. However, current spoken dialogue systems are deficient in their strategies for preventing, identifying and…

Although Multimodal Large Language Models (MLLMs) have demonstrated promising versatile capabilities, their performance is still inferior to specialized models on downstream tasks, which makes adaptation necessary to enhance their utility.…