mlsanityData to 14 Oct 2026

Task-Routed Mixture-of-Experts with Cognitive Appraisal for Implicit Sentiment Analysis

arXiv 2605.20916 ↗First posted 20 May 2026cs.CLcited by 0

On the map: Mixture-of-experts → Multimodal MoE models

Abstract (arXiv)

Implicit sentiment analysis is challenging because sentiment toward an aspect is often inferred from events rather than expressed through explicit opinion words. Existing models typically learn from the final polarity label, which provides limited guidance for reasoning about sentiment from the context. Motivated by cognitive appraisal theory, we propose an appraisal-aware multi-task learning (MTL) framework for implicit sentiment analysis that provides polarity prediction with two complementary auxiliary tasks: implicit sentiment detection and cognitive rationale generation. However, training several objectives with different targets and sharing a single backbone across tasks in MTL limits flexibility and can lead to task interference. To reduce interference among these related but distinct objectives, we adopt task-level mixture-of-experts models in which all tasks share a common set of experts, and task identity controls the sparse combination of these experts. Our method builds on an encoder-decoder architecture and replaces a subset of encoder and decoder blocks with these sparse mixtures. We use a task-conditioned router to select sparse expert mixtures for each task, and a task-separated routing objective to encourage different tasks to learn distinct expert-selection patterns. Experimental results show that our model outperforms recently proposed approaches, with strong gains on the implicit sentiment subset. Our code is available at https://github.com/yaping166/TRMoE-ISA.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts. Builds on 24 of its 34 references that are in the map. First posted on arXiv 20 May 2026.

Builds on

24 of 34 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts18 May

Other references · 23

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  4. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  5. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  6. 2025OpenAI GPT-5 System Cardcited by 989
  7. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
  8. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 375
  9. 2024A Survey on Mixture of Experts in Large Language Modelscited by 237
  10. 2020Relational Graph Attention Network for Aspect-based Sentiment Analysiscited by 104
  11. 2025A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applicationscited by 91
  12. 2023Reasoning Implicit Sentiment with Chain-of-Thought Promptingcited by 80
11 more
  1. 2019Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classificationcited by 63
  2. 2021Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Trainingcited by 37
  3. 2023InstructABSA: Instruction Learning for Aspect Based Sentiment Analysiscited by 23
  4. 2025Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunitiescited by 22
  5. 2023Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitivescited by 18
  6. 2022Causal Intervention Improves Implicit Sentiment Analysiscited by 16
  7. 2022A Contrastive Cross-Channel Data Augmentation Framework for Aspect-based Sentiment Analysiscited by 12
  8. 2022Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Expertscited by 12
  9. 2023Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentationscited by 7
  10. 2024Implicit Sentiment Analysis Based on Chain of Thought Promptingcited by 2
  11. 2024Beyond Text: Leveraging Multi-Task Learning and Cognitive Appraisal Theory for Post-Purchase Intention Analysiscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Multi-Task Learning with LLMs for Implicit Sentiment Analysis: Data-level and Task-level Automatic Weight Learning
  2. 2025Multimodal Mixture of Low-Rank Experts for Sentiment Analysis and Emotion Recognition
  3. 2025Text-Routed Sparse Mixture-of-Experts Model with Explanation and Temporal Alignment for Multi-Modal Sentiment Analysis
  4. 2026From Prediction to Justification: Aligning Sentiment Reasoning with Human Rationale via Reinforcement Learning
  5. 2026Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysis
  6. 2025Causal Prompting for Implicit Sentiment Analysis with Large Language Models
  7. 2025Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition
  8. 2026Multimodal Adaptive Expert Selection with Text Routing and Ordinal Prototype Optimization for Sentiment Analysis