4 papers
RESPONSE: Benchmarking the Ability of Language Models to Undertake Commonsense Reasoning in Crisis Situation
Aissatou Diallo, Antonis Bikakis, Luke Dickens +2
An interesting class of commonsense reasoning problems arises when people are faced with natural disasters. To investigate this topic, we present \textsf{RESPONSE}, a human-curated…
Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models
Aissatou Diallo, Antonis Bikakis, Luke Dickens +2
In this paper, we introduce Rule-Guided Feedback (RGF), a framework designed to enhance Large Language Model (LLM) performance through structured rule adherence and strategic infor…
IAO Prompting: Making Knowledge Flow Explicit in LLMs through Structured Reasoning Templates
Aissatou Diallo, Antonis Bikakis, Luke Dickens +2
While Large Language Models (LLMs) demonstrate impressive reasoning capabilities, understanding and validating their knowledge utilization remains challenging. Chain-of-thought (Co…
PizzaCommonSense: Learning to Model Commonsense Reasoning about Intermediate Steps in Cooking Recipes
Aissatou Diallo, Antonis Bikakis, Luke Dickens +2
Understanding procedural texts, such as cooking recipes, is essential for enabling machines to follow instructions and reason about tasks, a key aspect of intelligent reasoning. In…