Large language models (LLMs) often generate hallucinations — unsupported content that undermines reliability. While most prior works frame hallucination detection as a binary task, many real-world applications require identifying hallucinated spans, which is a multi-step decision making process. This naturally raises the question of whether explicit reasoning can help the complex task of detecting hallucination spans. To answer this question, we first evaluate pretrained models with and without Chain-of-Thought (CoT) reasoning, and show that CoT reasoning has the potential to generate at least… Read More
Learning to Reason for Hallucination Span Detection
Large language models (LLMs) often generate hallucinations — unsupported content that undermines reliability. While most prior works frame hallucination detection as a binary task, many real-world applications require identifying hallucinated spans, which is a multi-step decision making process. This naturally raises the question of whether explicit reasoning can help the complex task of detecting hallucination spans. To answer this question, we first evaluate pretrained models with and without Chain-of-Thought (CoT) reasoning, and show that CoT reasoning has the potential to generate at least…
Related Posts
Enabling small language models to solve complex reasoning tasks
The “self-steering” DisCIPL system directs small models to work together on tasks with constraints, like…
Learn more about AI in the workplace in our new research report.
A new global survey of executives, decision makers and knowledge workers reveals that organizations truly…
Synthetic Bootstrapped Pretraining
We introduce Synthetic Bootstrapped Pretraining (SBP), a language model (LM) pretraining procedure that first learns…