The paper reports the first Turing test for speech‑to‑speech systems, gathering 2,968 human judgments on conversations between nine state‑of‑the‑art S2S systems and 28 humans. None of the evaluated systems passed the test, highlighting a clear gap in human‑likeness. The authors diagnose the failure with an 18‑dimension taxonomy, finding that paralinguistic cues, emotional expressivity, and conversational persona—not semantic understanding—are the main bottlenecks, and they propose an interpretable model for automatic human‑vs‑machine discrimination.
By Xiang Li, Jiabao Gao, Sipei Lin, Xuan Zhou, Chi Zhang, Bo Cheng, Jiale Han, Benyou Wang
The paper introduces UPHELD, a large benchmark of human-to-human dialogues written by professional script writers, featuring realistic turn densities and over 36,000 per-turn human annotations. It evaluates existing automatic metrics and LLM-as-a-judge methods, finding them unreliable against expert human judgment. Using UPHELD, the authors develop a Mixture-of-Judges framework that improves correlation with human assessments by about 30%.
By Ilija Subasic, Andrew Rabinovich, Zhao Chen
Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However, existing judgment approaches often rely on trained judgers using fixed preference data, which tend to overlook diverse user preferences and struggle to adapt to real-world human-AI dialogue scenarios.
IRWOZ 2.0 is a refined dialogue dataset for industrial human‑robot interaction, expanding to 390 dialogues across four domains—Assembly, Delivery, Position, and Relocation. The dataset was improved using large language models (Mistral and Claude‑3.5) for generation and quality refinement, including manual corrections and automated typo removal. Benchmark tests show a substantial boost in dialogue state‑tracking performance, with GPT‑2’s BLEU‑4 score rising from 0.1651 to 0.5604 compared to the original IRWOZ.
By Chen Li, Dimitrios Chrysostomou
The article surveys multi‑turn conversational AI, highlighting its shift from isolated text prompts to sustained, multimodal interactions that involve clarifying goals, revising requests, and switching topics. It reviews literature across text‑only dialogue, AudioLLMs, multimodal and omni‑modal systems, and tool‑augmented agents, organizing findings around datasets, models, training, evaluation, and cross‑cutting challenges. The analysis reveals that while multimodal perception and action have progressed rapidly, systems still struggle with persistent memory, cross‑turn grounding, full‑duplex interaction, robust evaluation, and cultural alignment.
By Syeda Faiza Ahmed, Zien Sheikh Ali, Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury
arXiv:2305.12474v4 Announce Type: replace
Abstract: Large Language Models(LLMs) have demonstrated remarkable performance across various natural language processing tasks; however, how to comprehensiv...
By Xiaotian Zhang, Chunyang Li, Yi Zong, Zhengyu Ying, Liang He, Xipeng Qiu, Tianxiang Sun, Peng Li, Shiqiao Meng, Yanjun Zheng, Jun Zhan, Zhangyue Yin, Xiannian Hu, Guofeng Quan, Qixiang Wang