Diallo, Aissatou; Bikakis, Antonios; Dickens, Luke; Hunter, Anthony; Miller, Rob; (2025) RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation. In: Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025). ECAI: Bologna, Italy. (In press).

Text m2352.pdf - Accepted Version Access restricted to UCL open access staff until 18 March 2026. Download (559kB)

Abstract

Commonsense reasoning is a key aspect of human intelligence. If we are to develop robust and deep intelligent systems, then we need to understand the diversity and complexity of commonsense reasoning across the gamut of human activities. An interesting class of commonsense reasoning problems arises when people are faced with natural disasters. To investigate this topic, we present RESPONSE, a human-curated dataset containing 1789 annotated instances featuring 6037 sets of questions designed to assess LLMs’ commonsense reasoning in disaster situations across different time frames. The dataset includes problem descriptions, missing resources, time-sensitive solutions, and their justifications, with a subset validated by environmental engineers. Through both automatic metrics and human evaluation, we compare LLM-generated recommendations against human responses. Our findings show that even state-of-the-art models like GPT-4 achieve only 37% human-evaluated correctness for immediate response actions, highlighting significant room for improvement in LLMs’ ability for commonsense reasoning in crises.

Download activity - last month

Export as XMLCSVJSON

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as CSVXMLJSON

Archive Staff Only

View Item