arXiv AI
Disentangling Topology and Diversity in Multi-Agent LLMs for Multilingual Low-Resource Emotion Detection
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 1
Cross-lingual Functional Vectors for Emotion Detection in Large Language Models
arXiv:2608.29613v1 Announce Type: cross Abstract: Function vectors (FVs) have recently emerged as a promising mechanism for steering the behavior of large language models (LLMs) by injecting task-spe...
arXiv AI
Jun 29
Do Speech Emphasis Models Generalize across Languages and Emotions?
arXiv:2606. 27717v1 Announce Type: cross Abstract: Prosodic emphasis varies across languages, emotions, and speaking styles, yet existing emphasis detection models are largely trained and evaluated on monolingual neutral read speech.
Hugging Face Trending Papers
Sep 16
When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI
Emotion recognition in conversation (ERC) is a production capability behind agent-assist prompts, escalation routing, and post-call analytics in contact-center-as-a-service (CCaaS) platforms, where co...
arXiv AI
Sep 17
When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI
The paper evaluates three approaches for emotion recognition in conversation— a low‑cost stacked ensemble, an off‑the‑shelf LLM prompt, and a confidence‑gated hybrid that escalates only uncertain ensemble predictions to the LLM. Across three datasets (IEMOCAP, MELD, CMU‑MOSI), the hybrid consistently outperforms each pure system, achieving higher weighted F1 scores while routing most traffic through the inexpensive ensemble. This results in significant cost savings (≈$10‑85 per million utterances) and provides an interpretable escalation signal tied to emotion or sentiment shifts.
arXiv Computation and Language
Nov 4
Steering with Multilingual Lexicons for Sentiment Control in Low-Resource Languages
The paper proposes using multilingual sentiment lexicons to steer language models for sentiment control, especially in low-resource languages. It finds that aggregated multilingual lexicons outperform English-derived steering vectors for mid- and low-resource languages, while monolingual lexicons are still best for languages the model was pre-trained on. The study also explains how representational density, pre-training priors, and architectural biases affect steering effectiveness, noting that large English vectors can cause linguistic collapse in low-resource settings but this is mitigated by norm-dampening in multilingual aggregation.
arXiv AI
Sep 10
MVFA: A Multi-View Text-Guided Multimodal Fusion LLM Adapter for Sentiment Analysis and Emotion Recognition
arXiv:2609.06188v1 Announce Type: new Abstract: Multimodal sentiment analysis and emotion recognition in conversations demand effective modeling of heterogeneous interactions across textual, acoustic...