相关论文: CantTalkAboutThis: Aligning Language Models to Sta…

Current medical AI systems often fail to replicate real-world clinical reasoning, as they are predominantly trained and evaluated on static text and question-answer tasks. These tuning methods and benchmarks overlook critical aspects like…

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…

Instructions-tuned Large Language Models (LLMs) gained recently huge popularity thanks to their ability to interact with users through conversation. In this work we aim to evaluate their ability to complete multi-turn tasks and interact…

Continual learning (CL) is a paradigm that aims to replicate the human ability to learn and accumulate knowledge continually without forgetting previous knowledge and transferring it to new tasks. Recent instruction tuning (IT) involves…

Goal-oriented dialogue systems face a trade-off between fluent language generation and task-specific control. While supervised learning with large language models is capable of producing realistic text, how to steer such responses towards…

Large language models (LLMs) have demonstrated impressive capabilities in mathematical problem solving, particularly in single turn question answering formats. However, real world scenarios often involve mathematical question answering that…

Multi-turn interaction in the dialogue system research refers to a system's ability to maintain context across multiple dialogue turns, enabling it to generate coherent and contextually relevant responses. Recent advancements in large…

Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role…

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…

The recent development of language models has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models. In task-oriented dialogue (ToD) systems, language models can…

In recent research on dialogue systems and corpora, there has been a significant focus on two distinct categories: task-oriented (TOD) and open-domain (chit-chat) dialogues. TOD systems aim to satisfy specific user goals, such as finding a…

Conversational agents based on Large Language Models (LLMs) have recently emerged as powerful tools for human-computer interaction. Nevertheless, their black-box nature implies challenges in predictability and a lack of personalization,…

Machine Learning (ML) models are increasingly used to make critical decisions in real-world applications, yet they have become more complex, making them harder to understand. To this end, researchers have proposed several techniques to…

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…

Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks. Recent studies demonstrate that open-sourced smaller foundational…

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), particularly those similar to ChatGPT, have significantly influenced the field of Natural Language Processing (NLP). While these models excel in general language tasks, their performance in domain-specific…

In spoken dialogue, even if two current turns are the same sentence, their responses might still differ when they are spoken in different styles. The spoken styles, containing paralinguistic and prosodic information, mark the most…

Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still…

The growing use of large language model (LLM)-based chatbots has raised concerns about fairness. Fairness issues in LLMs can lead to severe consequences, such as bias amplification, discrimination, and harm to marginalized communities.…