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.
By Sai Babu Udayagiri, Arjun Chouhan, Ravisekhar Kanagala, Trishala Pavagada
The paper proposes an agentic framework for multimodal emotion reasoning that uses frozen models to avoid costly instruction tuning. It employs modality‑specific perception agents, an integration agent, and an MLLM critic to generate emotion predictions with evidence citations, followed by an evidence‑grounded verification stage that identifies errors and applies targeted prompt patches without updating model weights. On the MER2025 dataset, this approach improves F‑score across several large language‑vision models, outperforming static pipelines and matching or exceeding reflection baselines.
By Elyas Rashno, Farhana Zulkernine
arXiv:2606. 24941v2 Announce Type: replace-cross Abstract: Reviewing recorded interviews for affective cues such as composure and agitation is slow and subjective, and cloud services that could automate the task require sensitive audio to leave the device.
By Wai Laam Mak, Isibor Kennedy Ihianle, Pedro Machado
SpeechEQ is a new benchmark that evaluates the sociolinguistic reasoning of Speech‑Language Models (SLMs) by using a dataset of 2,265 dialogues covering 15 Emotional Quotient (EQ) subscales from EQ‑i 2.0 theory. The framework introduces a multi‑turn evaluation protocol and a Spoken EQ (SEQ) score inspired by human EQ assessments. Experiments reveal that current multimodal models suffer from a text‑reliant shortcut, an alignment‑induced safety trap, and contextual amnesia, limiting their emotional awareness in spoken interaction.
By Liang-Yuan Wu, Zih-Ching Chen, Tongshuang Wu, Chao-Han Huck Yang, Hua Shen
arXiv:2609.14570v1 Announce Type: cross
Abstract: Multi-agent LLM systems combine multiple inference calls, but prior work often confounds how calls are connected with how they are diversified. We st...
By Ulugbek Shernazarov, Charitha Ruwansiri Weerakon Basnayake, Abdelkhaleq El Jarjini, Noel Crespi, Praboda Rajapaksha
DialFork is a new benchmark that evaluates procedural hallucination in conversational agents, a failure mode where agents produce fluent, factually plausible utterances but deviate from the intended dialogue process. The benchmark consists of 36,278 dialogues across 24 tasks in 12 domains, created by forking conformant dialogues and injecting one of four hallucination types, with validation by 30 human annotators. Three evaluation tasks are defined—monitoring overall deviation, procedural retrieval of a single dialogue, and real‑time detection of off‑track turns—using dialog‑flow‑aware metrics FlowKL and FlowScore, which outperform baseline semantic similarity metrics.
By Sergio Burdisso, Esa\'u Villatoro-Tello, Dairazalia S\'anchez-Cort\'es, Yanis Labrak, Jordi Luque, Milos Cernak, Petr Motlicek
Social influence dialogue changes user behavior by altering internal cognitive states. The central evaluation question is whether the user's beliefs, desires, intentions, and emotions measurably change over the course of conversation, a process-oriented criterion that neither surface-level text metrics (BLEU/ROUGE) nor single-score LLM judgments can capture.
arXiv:2606. 29495v1 Announce Type: new Abstract: Social influence dialogue changes user behavior by altering internal cognitive states.
By Minghui Ma, Bin Guo, Han Wang, Mengqi Chen, Jingqi Liu, Yan Liu, Zhiwen Yu
arXiv:2609.05806v1 Announce Type: new
Abstract: Emotion Recognition in Conversations (ERC) aims to identify speakers' emotions in multi-turn dialogue. Accurate emotion recognition can support a wide...
By Amir Ben Khalifa, Fanny Bezancon, Amine Trabelsi, Bessam Abdulrazak
arXiv:2607. 16712v1 Announce Type: new Abstract: We describe DS@GT's submission to the eRisk 2026 Task 1 challenge on conversational depression screening, in which systems interview LLM personas that simulate individuals with varying depression profiles and produce a Beck Depression Inventory II (BDI-II) score plus four key symptoms per persona, without directly asking sensitive mental health questions.
By Victor Gong, David Guecha
arXiv:2601.14172v4 Announce Type: replace-cross
Abstract: We study neural multi-label classification under severe label imbalance through sentence-level detection of the 19 refined Schwartz human val...
By V\'ictor Yeste, Paolo Rosso
Online A/B experiments are the decision standard for user engagement, but traffic and readout time limit how many conversational-AI changes can be tested. We ask whether an offline signal designed to...