2025
HALLUCANA: Fixing LLM Hallucination with A Canary Lookahead
NAACL 2025findings
In this paper, we present HALLUCANA, a canary lookahead to detect and correct factual hallucinations of Large Language Models (LLMs) in long-form generation. HALLUCANA detects and intervenes as soon as traces of hallucination emerge, during and even before generation. To support timely detection, we…