Large Language Models for Conversational Information Processing and Retrieval

Dear Colleagues,

Large Language Models (LLMs) have revolutionized the field of conversational information processing and retrieval, marking a significant leap in how machines understand and generate human language. Rooted in natural language processing (NLP) and information retrieval (IR), these models are trained on vast datasets, enabling them to predict and generate text with remarkable coherence and context relevance. The importance of this research area is profound, as it underpins advancements in virtual assistants, customer service bots, and sophisticated tools for information retrieval. LLMs like GPT-4 have become indispensable in interpreting queries, providing accurate information, and maintaining engaging dialogues with users. They not only enhance user experience by offering more intuitive and natural interactions but also drive efficiency and accessibility in information retrieval across various domains. As such, the ongoing research and development in LLMs are crucial for pushing the boundaries of artificial intelligence and making technology more responsive and useful to human needs.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but may not be limited to) the following.

• LLMs for dialogue and interactive systems:
  • Task-oriented dialogue systems;
  • Open-domain dialogue systems;
  • Conversational information-seeking systems (conversational question answering, conversational search, conversational recommendation, etc.);
  • Document-grounded dialogue systems;
  • Proactive dialogue systems;
  • Negotiation and non-collaborative dialogue systems;
  • Spoken dialogue systems;
  • Multimodal and situated dialogue systems;
  • Multilingual and multicultural dialogue systems;
  • Dialogue systems for low-resource languages;
  • Domain-specific dialogue systems.
• LLMs for dialogue resources and evaluation:
  • Dialogue data resources;
  • Dialogue data augmentation;
  • Generative AI for dialogue data annotations;
  • Human–AI collaborative dialogue data annotations;
  • Dialogue data quality control;
  • Dialogue evaluation.
• LLMs for user modeling and simulation in conversations:
  • Personalization in dialogue systems;
  • User simulation in dialogue systems;
  • User intent and behaviour modeling in dialogue systems;
  • User satisfaction estimation in dialogue systems;
  • User engagement and emotion in dialogue systems;
  • Human-centered designs in dialogue systems.
• LLMs for the conversational interface of NLP tasks:
  • Conversational information extraction;
  • Conversational semantic role labeling;
  • Conversational semantic parsing;
  • Conversational summarization;
  • Conversational machine translation;
  • Conversational sentiment analysis.
• LLMs for interactive information retrieval:
  • Recommender systems;
  • Search systems;
  • Question answering systems;
  • Data management systems;
  • Knowledge management systems.

We look forward to receiving your contributions.

Dr. Yang Deng
Dr. Yifei Yuan
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• dialogue systems
• large language models
• information retrieval
• human–computer interactions
• natural language processing