NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries
This addresses challenges for language beginners and non-expert users in real-world EQA applications, but it is incremental as it builds on existing benchmarks with new noise types and a prompting method.
The authors tackled the problem of Embodied Question Answering (EQA) agents struggling with noisy queries in real-world scenarios by introducing the NoisyEQA benchmark, which includes four types of noise and a Self-Correction prompting mechanism, resulting in improved answer accuracy.
The rapid advancement of Vision-Language Models (VLMs) has significantly advanced the development of Embodied Question Answering (EQA), enhancing agents' abilities in language understanding and reasoning within complex and realistic scenarios. However, EQA in real-world scenarios remains challenging, as human-posed questions often contain noise that can interfere with an agent's exploration and response, bringing challenges especially for language beginners and non-expert users. To address this, we introduce a NoisyEQA benchmark designed to evaluate an agent's ability to recognize and correct noisy questions. This benchmark introduces four common types of noise found in real-world applications: Latent Hallucination Noise, Memory Noise, Perception Noise, and Semantic Noise generated through an automated dataset creation framework. Additionally, we also propose a 'Self-Correction' prompting mechanism and a new evaluation metric to enhance and measure both noise detection capability and answer quality. Our comprehensive evaluation reveals that current EQA agents often struggle to detect noise in questions, leading to responses that frequently contain erroneous information. Through our Self-Correct Prompting mechanism, we can effectively improve the accuracy of agent answers.