collaborators

5 papers

cs.CL2026

RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules

Ádám Kovács, Nadia Verdha, Gábor Recski

We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER), or r…

cs.CL2026

Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents

Ádám Kovács, Bowei He, Xue Liu +3

Hallucination detection for retrieval-augmented generation (RAG) is usually evaluated on natural-language document evidence. However, grounded generation systems increasingly rely…

cs.CL2026

ACL-Verbatim: hallucination-free question answering for research

Gábor Recski, Szilveszter Tóth, Nadia Verdha +2

Academic researchers need efficient and reliable methods for collecting high-quality information from trusted sources, but modern tools for AI-assisted research still suffer from t…

cs.CL2025

Relation Extraction or Pattern Matching? Unravelling the Generalisation Limits of Language Models for Biographical RE

Varvara Arzt, Allan Hanbury, Michael Wiegand +2

Analysing the generalisation capabilities of relation extraction (RE) models is crucial for assessing whether they learn robust relational patterns or rely on spurious correlations…

cs.CL2025

LettuceDetect: A Hallucination Detection Framework for RAG Applications

Ádám Kovács, Gábor Recski

Retrieval Augmented Generation (RAG) systems remain vulnerable to hallucinated answers despite incorporating external knowledge sources. We present LettuceDetect a framework that a…