VCB Bench: An Evaluation Benchmark for Audio-Grounded Large Language Model Conversational Agents
This work addresses the need for a standardized evaluation framework for Chinese voice conversational models, though it is incremental as it builds on existing benchmarking efforts.
The authors tackled the lack of comprehensive benchmarks for audio-grounded large language models by introducing VCB Bench, a high-quality Chinese benchmark based on real human speech, which revealed notable performance gaps in existing models across multiple dimensions.
Recent advances in large audio language models (LALMs) have greatly enhanced multimodal conversational systems. However, existing benchmarks remain limited -- they are mainly English-centric, rely on synthetic speech, and lack comprehensive, discriminative evaluation across multiple dimensions. To address these gaps, we present Voice Chat Bot Bench (VCB Bench) -- a high-quality Chinese benchmark built entirely on real human speech. VCB Bench evaluates LALMs from three complementary perspectives: instruction following (including speech-level control beyond text commands), knowledge understanding (general knowledge, reasoning, and daily dialogue), and robustness (stability under perturbations in content, environment, and speaker traits). Experiments on representative LALMs reveal notable performance gaps and highlight future directions for improvement. VCB Bench provides a reproducible and fine-grained evaluation framework, offering standardized methodology and practical insights for advancing Chinese voice conversational models.