# Decoding the Flow: CauseMotion for Emotional Causality Analysis in Long-form Conversations

arXiv: https://arxiv.org/abs/2501.00778 · HTML: https://mlsanity.com/paper/2501.00778/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning.
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 1 Jan 2025.

## Placed in

- LLM reasoning / [Audio-language model reasoning](https://mlsanity.com/lr/audio-language-model-reasoning/)

## Builds on (most cited first, 13 of 13)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [Span-based Joint Entity and Relation Extraction with Transformer Pre-training](https://mlsanity.com/paper/1909.07755/) (2019)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Aspect Sentiment Quad Prediction as Paraphrase Generation](https://mlsanity.com/paper/2110.00796/) (2021)
- [Effective LSTMs for Target-Dependent Sentiment Classification](https://mlsanity.com/paper/1512.01100/) (2015)
- [Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2107.12214/) (2021)
- [SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis](https://mlsanity.com/paper/2005.05635/) (2020)
- [EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognition](https://mlsanity.com/paper/2203.13504/) (2022)
- [Aspect Term Extraction with History Attention and Selective Transformation](https://mlsanity.com/paper/1805.00760/) (2018)
- [DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis](https://mlsanity.com/paper/2211.05705/) (2022)
- [PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2408.09481/) (2024)

## Built on by (most cited first, 2 of 2)

- [DeepGB-TB: A Risk-Balanced Cross-Attention Gradient-Boosted Convolutional Network for Rapid, Interpretable Tuberculosis Screening](https://mlsanity.com/paper/2508.02741/) (2025)
- [Confidence-Aware Self-Distillation for Multimodal Sentiment Analysis with Incomplete Modalities](https://mlsanity.com/paper/2506.01490/) (2025)

## Abstract (arXiv)

Long-sequence causal reasoning seeks to uncover causal relationships within extended time series data but is hindered by complex dependencies and the challenges of validating causal links. To address the limitations of large-scale language models (e.g., GPT-4) in capturing intricate emotional causality within extended dialogues, we propose CauseMotion, a long-sequence emotional causal reasoning framework grounded in Retrieval-Augmented Generation (RAG) and multimodal fusion. Unlike conventional methods relying only on textual information, CauseMotion enriches semantic representations by incorporating audio-derived features-vocal emotion, emotional intensity, and speech rate-into textual modalities. By integrating RAG with a sliding window mechanism, it effectively retrieves and leverages contextually relevant dialogue segments, thus enabling the inference of complex emotional causal chains spanning multiple conversational turns. To evaluate its effectiveness, we constructed the first benchmark dataset dedicated to long-sequence emotional causal reasoning, featuring dialogues with over 70 turns. Experimental results demonstrate that the proposed RAG-based multimodal integrated approach, the efficacy of substantially enhances both the depth of emotional understanding and the causal inference capabilities of large-scale language models. A GLM-4 integrated with CauseMotion achieves an 8.7% improvement in causal accuracy over the original model and surpasses GPT-4o by 1.2%. Additionally, on the publicly available DiaASQ dataset, CauseMotion-GLM-4 achieves state-of-the-art results in accuracy, F1 score, and causal reasoning accuracy.