Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering

TL;DR

This paper introduces a novel approach for generating and evaluating complex situational queries in embodied question answering within household environments, highlighting the strengths and limitations of large language models in this context.

Contribution

It presents the first method for generating situational queries for EQA using a Prompt-Generate-Evaluate scheme and evaluates LLM performance in both virtual and real-world settings.

Findings

LLMs can generate high-answerability situational data (97.26%).

LLMs show low correlation (46.2%) with human consensus in answering.

LLMs often contradict commonsense reasoning when justifying answers.

Abstract

We present and tackle the problem of Embodied Question Answering (EQA) with Situational Queries (S-EQA) in a household environment. Unlike prior EQA work tackling simple queries that directly reference target objects and properties ("What is the color of the car?"), situational queries (such as "Is the house ready for sleeptime?") are challenging as they require the agent to correctly identify multiple object-states (Doors: Closed, Lights: Off, etc.) and reach a consensus on their states for an answer. Towards this objective, we first introduce a novel Prompt-Generate-Evaluate (PGE) scheme that wraps around an LLM's output to generate unique situational queries and corresponding consensus object information. PGE is used to generate 2K datapoints in the VirtualHome simulator, which is then annotated for ground truth answers via a large scale user-study conducted on M-Turk. With a high rate of answerability (97.26%) on this study, we establish that LLMs are good at generating situational data. However, in evaluating the data using an LLM, we observe a low correlation of 46.2% with the ground truth human annotations; indicating that while LLMs are good at generating situational data, they struggle to answer them according to consensus. When asked for reasoning, we observe the LLM often goes against commonsense in justifying its answer. Finally, we utilize PGE to generate situational data in a real-world environment, exposing LLM hallucination in generating reliable object-states when a structured scene graph is unavailable. To the best of our knowledge, this is the first work to introduce EQA in the context of situational queries and also the first to present a generative approach for query creation. We aim to foster research on improving the real-world usability of embodied agents through this work.