hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
DialogueLLM: Context and emotion knowledge-tuned large language models for emotion recognition in conversations
Tianjin University, Tianjin, China; Hong Kong Polytechnic University, Hong Kong, Hong Kong.ORCID iD: 0000-0002-5699-0176
Zhengzhoug University of Light Industry, Zhengzhou, China.
Hebei University of Technology, Tianjin, China.
Halmstad University, School of Information Technology.ORCID iD: 0000-0002-2851-4260
Show others and affiliations
2025 (English)In: Neural Networks, ISSN 0893-6080, E-ISSN 1879-2782, Vol. 192, p. 1-15, article id 107901Article in journal (Refereed) In press
Abstract [en]

Large language models (LLMs) and their variants have shown extraordinary efficacy across numerous downstream natural language processing tasks. Despite their remarkable performance in natural language generating, LLMs lack a distinct focus on the emotion understanding domain. As a result, using LLMs for emotion recognition may lead to suboptimal and inadequate precision. Another limitation of the current LLMs is that they are typically trained without leveraging multi-modal information. To overcome these limitations, we formally model emotion recognition as text generation tasks, and thus propose DialogueLLM, a context and emotion knowledge tuned LLM that is obtained by fine-tuning foundation large language models. In particular, it is a context-aware model, which can accurately capture the dynamics of emotions throughout the dialogue. We also prompt ERNIE Bot with expert-designed prompts to generate the textual descriptions of the videos. To support the training of emotional LLMs, we create a large scale dataset of over 24K utterances to serve as a knowledge corpus. Finally, we offer a comprehensive evaluation of DialogueLLM on three benchmarking datasets and significantly outperform 15 state-of-the-art baselines and 3 state-of-the-art LLMs. The emotion intelligence test shows that DialogueLLM achieves 109 score and surpasses 72 % humans. Additionally, DialogueLLM-7B can be easily reproduced using LoRA on a 40GB A100 GPU in 5 hours. © 2025 Elsevier Ltd

Place, publisher, year, edition, pages
Oxford: Elsevier, 2025. Vol. 192, p. 1-15, article id 107901
Keywords [en]
Context modeling, Emotion recognition, Large language models, Natural language processing
National Category
Natural Language Processing
Identifiers
URN: urn:nbn:se:hh:diva-57201DOI: 10.1016/j.neunet.2025.107901ISI: 001544939300003Scopus ID: 2-s2.0-105012239350OAI: oai:DiVA.org:hh-57201DiVA, id: diva2:2001473
Available from: 2025-09-26 Created: 2025-09-26 Last updated: 2025-10-01Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Tiwari, Prayag

Search in DiVA

By author/editor
Zhang, YazhouTiwari, PrayagWang, BenyouQin, Jing
By organisation
School of Information Technology
In the same journal
Neural Networks
Natural Language Processing

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 10 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf