AI hallucinations: a misnomer worth clarifying

N Maleki, B Padmanabhan… - 2024 IEEE conference on …, 2024 - ieeexplore.ieee.org
As large language models continue to advance in Artificial Intelligence (AI), text generation
systems have been shown to suffer from a problematic phenomenon often termed as" …

Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations

YP Chen, N Nishida, H Nakayama… - arxiv preprint arxiv …, 2024 - arxiv.org
Enhancing user engagement through personalization in conversational agents has gained
significance, especially with the advent of large language models that generate fluent …

CloChat: Understanding How People Customize, Interact, and Experience Personas in Large Language Models

J Ha, H Jeon, D Han, J Seo, C Oh - … of the CHI Conference on Human …, 2024 - dl.acm.org
Large language models (LLMs) have facilitated significant strides in generating
conversational agents, enabling seamless, contextually relevant dialogues across diverse …

Target-oriented Proactive Dialogue Systems with Personalization: Problem Formulation and Dataset Curation

J Wang, Y Cheng, D Lin, CT Leong, W Li - arxiv preprint arxiv:2310.07397, 2023 - arxiv.org
Target-oriented dialogue systems, designed to proactively steer conversations toward
predefined targets or accomplish specific system-side goals, are an exciting area in …

Beyond Candidates: Adaptive Dialogue Agent Utilizing Persona and Knowledge

J Lim, M Kang, J Kim, J Kim, Y Hur… - Findings of the …, 2023 - aclanthology.org
To build ultimate dialogue agents, previous studies suggest models that ground both
persona and knowledge. However, applying the dialogue system directly to the usual …

Multi-level adaptive contrastive learning for knowledge internalization in dialogue generation

C Yang, Z Lin, L Wang, C Tian, L Pang, J Li… - arxiv preprint arxiv …, 2023 - arxiv.org
Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by
incorporating external knowledge to supplement the context. However, the model often fails …

Post-hoc Utterance Refining Method by Entity Mining for Faithful Knowledge Grounded Conversations

Y Jang, S Son, J Lee, J Son, Y Hur, J Lim… - arxiv preprint arxiv …, 2024 - arxiv.org
Despite the striking advances in recent language generation performance, model-generated
responses have suffered from the chronic problem of hallucinations that are either untrue or …

Persona-Identified Chatbot through Small-Scale Modeling and Data Transformation

B Keum, J Sun, W Lee, S Park, H Kim - Electronics, 2024 - mdpi.com
Research on chatbots aimed at facilitating more natural and engaging conversations is
actively underway. With the growing recognition of the significance of personas in this …

K-PERM: Personalized Response Generation Using Dynamic Knowledge Retrieval and Persona-Adaptive Queries

K Raj, K Roy, V Bonagiri, P Govil… - Proceedings of the …, 2024 - ojs.aaai.org
Personalizing conversational agents can enhance the quality of conversations and increase
user engagement. However, they often lack external knowledge to appropriately tend to a …

Persona-centric Metamorphic Relation guided Robustness Evaluation for Multi-turn Dialogue Modelling

Y Chen, L Li, X Tao, D Zhou - arxiv preprint arxiv:2401.12483, 2024 - arxiv.org
Recently there has been significant progress in the field of dialogue system thanks to the
introduction of training paradigms such as fine-tune and prompt learning. Persona can …