collaborators

5 papers

cs.AI2026

Signal or Spurious Cue? A Randomized Audit of Survey-Country Metadata in LLM Social Inference

Yifan Lyu, Xinran Li, Jiaqi Qiao +1

Survey-country metadata can improve an LLM's forecast of an individual response when informative, yet the same cue may redirect the forecast when assigned at random. A within-recor…

cs.CL2026

TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis

Xinran Li, Xinze Che, Yifan Lyu +2

Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) needs to capture the complex interrelationships in multiple rounds of dialogues. Existing methods usually employ s…

cs.CL2026

Expert-Guided Multimodal Fusion for Unified Emotion and Sentiment Analysis

Jiaqi Qiao, Xiujuan Xu, Xinran Li +3

Multimodal emotion understanding requires the integration of heterogeneous data sources, including text, audio, and visual modalities, while simultaneously addressing discrete emot…

cs.AI2025

Do LLMs Feel? Teaching Emotion Recognition with Prompts, Retrieval, and Curriculum Learning

Xinran Li, Yu Liu, Jiaqi Qiao +1

Emotion Recognition in Conversation (ERC) is a crucial task for understanding human emotions and enabling natural human-computer interaction. Although Large Language Models (LLMs)…

cs.LG2025

Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation

Xinran Li, Xiujuan Xu, Jiaqi Qiao

Emotion Recognition in Conversation (ERC) is a practical and challenging task. This paper proposes a novel multimodal approach, the Long-Short Distance Graph Neural Network (LSDGNN…