InfiniteEmo: A Benchmark for Evaluating Emotional Intelligence of LLMs in Long-Context Inference

ACL ARR 2026 January Submission3709 Authors

Keywords: Emotional Intelligence, Long-Context Inference

Abstract: Large language models (LLMs) make significant progress in Emotional Intelligence (EI) and long-context modeling. However, existing benchmarks often overlook the fact that $\textit{emotional information processing unfolds as a continuous long-context process}$. To address the absence of multidimensional EI evaluation in long-context inference and explore model performance under more challenging conditions, we present $\textit{InfiniteEmo}$, a benchmark that encompasses a diverse suite of tasks targeting the assessment of models’ capabilities in $\textbf{Emotion Recognition}$, $\textbf{Knowledge Application}$, and $\textbf{Empathetic Generation}$, with an average context length of 15,341 tokens. To enhance performance under realistic constraints, we introduce the Collaborative Emotional Modeling ($\textit{CoEM}$) framework, which integrates Retrieval-Augmented Generation ($\textit{RAG}$) and multi-agent collaboration to improve models’ EI in long-context scenarios. We conduct a detailed analysis of various models in long-context settings, investigating how reasoning mode activation, RAG-based retrieval strategies, and context-length adaptability influence their EI performance. All of our code and datasets will be open-sourced, which can be viewed at the anonymous repository link https://anonymous.4open.science/r/Anonymous-B5FC/.

Paper Type: Long

Research Area: Linguistic theories, Cognitive Modeling and Psycholinguistics

Research Area Keywords: Emotional Intelligence, Long-Context Inference

Languages Studied: English

Submission Number: 3709