中文
相关论文

相关论文: CHARP: Conversation History AwaReness Probing for …

200 篇论文

Fact-checking is an essential tool to mitigate the spread of misinformation and disinformation. We introduce the task of fact-checking in dialogue, which is a relatively unexplored area. We construct DialFact, a testing benchmark dataset of…

计算与语言 · 计算机科学 2022-03-25 Prakhar Gupta , Chien-Sheng Wu , Wenhao Liu , Caiming Xiong

Despite growing recognition that responsible AI requires domain knowledge, current work on conversational AI primarily draws on clinical expertise that prioritises diagnosis and intervention. However, much of everyday emotional support…

人机交互 · 计算机科学 2026-04-15 Joel Wester , Samuel Rhys Cox , Henning Pohl , Niels van Berkel

Patient-clinician communication is an asymmetric-information problem: patients often do not disclose fears, misconceptions, or practical barriers unless clinicians elicit them skillfully. Effective medical dialogue therefore requires…

计算与语言 · 计算机科学 2026-04-13 Yikun Han , Joey Chan , Jingyuan Chen , Mengting Ai , Simo Du , Yue Guo

Empowered by the large-scale pretrained language models, existing dialogue systems have demonstrated impressive performance conducting fluent and natural-sounding conversations. However, they are still plagued by the hallucination problem,…

计算与语言 · 计算机科学 2024-04-05 Jifan Yu , Xiaohan Zhang , Yifan Xu , Xuanyu Lei , Zijun Yao , Jing Zhang , Lei Hou , Juanzi Li

Hallucinations, the tendency to produce irrelevant/incorrect responses, are prevalent concerns in generative AI-based tools like ChatGPT. Although hallucinations in ChatGPT are studied for textual responses, it is unknown how ChatGPT…

软件工程 · 计算机科学 2024-11-13 Salma Begum Tamanna , Gias Uddin , Song Wang , Lan Xia , Longyu Zhang

Factuality is a crucial requirement in information seeking dialogue: the system should respond to the user's queries so that the responses are meaningful and aligned with the knowledge provided to the system. However, most modern large…

While recently developed NLP explainability methods let us open the black box in various ways (Madsen et al., 2022), a missing ingredient in this endeavor is an interactive tool offering a conversational interface. Such a dialogue system…

计算与语言 · 计算机科学 2023-10-24 Nils Feldhus , Qianli Wang , Tatiana Anikina , Sahil Chopra , Cennet Oguz , Sebastian Möller

Many studies on dialog emotion analysis focus on utterance-level emotion only. These models hence are not optimized for dialog-level emotion detection, i.e. to predict the emotion category of a dialog as a whole. More importantly, these…

计算与语言 · 计算机科学 2022-03-24 Yequan Wang , Xuying Meng , Yiyi Liu , Aixin Sun , Yao Wang , Yinhe Zheng , Minlie Huang

Large language models (LLMs) continue to hallucinate in retrieval-augmented generation (RAG), producing claims that are unsupported by or conflict with the retrieved context. Detecting such errors remains challenging when faithfulness is…

计算与语言 · 计算机科学 2026-03-31 Boxi Yu , Yuzhong Zhang , Liting Lin , Lionel Briand , Emir Muñoz

Speech-to-text services aim to transcribe input audio as accurately as possible. They increasingly play a role in everyday life, for example in personal voice assistants or in customer-company interactions. We evaluate Open AI's Whisper, a…

计算与语言 · 计算机科学 2024-05-06 Allison Koenecke , Anna Seo Gyeong Choi , Katelyn X. Mei , Hilke Schellmann , Mona Sloane

Large language models in healthcare often produce emotionally flat or opaque responses, failing to provide the transparent reasoning required for clinical trust. We present RECAP (Reflect-Extract-Calibrate-Align-Produce), an inference-time…

计算与语言 · 计算机科学 2026-05-05 Adarsh Srinivasan , Jacob Dineen , Muhammad Umar Afzal , Muhammad Uzair Sarfraz , Irbaz B. Riaz , Ben Zhou

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…

Humans talk in daily conversations while aligning and negotiating the expressed meanings or common ground. Despite the impressive conversational abilities of the large generative language models, they do not consider the individual…

计算与语言 · 计算机科学 2024-05-27 Shuwen Qiu , Mingdian Liu , Hengli Li , Song-Chun Zhu , Zilong Zheng

The onset of the COVID-19 pandemic has brought the mental health of people under risk. Social counselling has gained remarkable significance in this environment. Unlike general goal-oriented dialogues, a conversation between a patient and a…

计算与语言 · 计算机科学 2021-11-15 Ganeshan Malhotra , Abdul Waheed , Aseem Srivastava , Md Shad Akhtar , Tanmoy Chakraborty

The state of the art in human computer conversation leaves something to be desired and, indeed, talking to a computer can be down-right annoying. This paper describes an approach to identifying ``opportunities for improvement'' in these…

计算与语言 · 计算机科学 2023-07-17 Peter Wallis

Clarification questions help conversational search systems resolve ambiguous or underspecified user queries. While prior work has focused on fluency and alignment with user intent, especially through facet extraction, much less attention…

计算与语言 · 计算机科学 2026-01-21 Ahmed Rayane Kebir , Vincent Guigue , Lynda Said Lhadj , Laure Soulier

To build a conversational agent that interacts fluently with humans, previous studies blend knowledge or personal profile into the pre-trained language model. However, the model that considers knowledge and persona at the same time is still…

Matching question-answer relations between two turns in conversations is not only the first step in analyzing dialogue structures, but also valuable for training dialogue systems. This paper presents a QA matching model considering both…

计算与语言 · 计算机科学 2020-11-18 Qi Jia , Mengxue Zhang , Shengyao Zhang , Kenny Q. Zhu

Dialogue summarization is abstractive in nature, making it suffer from factual errors. The factual correctness of summaries has the highest priority before practical applications. Many efforts have been made to improve faithfulness in text…

计算与语言 · 计算机科学 2022-10-24 Bin Wang , Chen Zhang , Yan Zhang , Yiming Chen , Haizhou Li

Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the input source, which…

计算与语言 · 计算机科学 2023-05-15 Ziwei Ji , Zihan Liu , Nayeon Lee , Tiezheng Yu , Bryan Wilie , Min Zeng , Pascale Fung