← Search

Erenay Dayanik

2 accepted papers

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…

2022

Improving Neural Political Statement Classification with Class Hierarchical Information

ACL 2022findings

Many tasks in text-based computational social science (CSS) involve the classification of political statements into categories based on a domain-specific codebook. In order to be useful for CSS analysis, these categories must be fine-grained. The typically skewed distribution of fine-grained categor…