5 citations · 8 across the 7 of their papers we have counts for
5 papers · 1 filter
Grounding Probes: Generator-Independent Hallucination Detection from Observer Model Hidden States
Michael Rathmayr, Ádám Kovács, Gábor Recski
Detecting responses that retrieval-augmented generation does not ground in its context trades speed against accuracy: surface checks miss paraphrased fabrication, sampling-based me…
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…
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…
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…
Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents
Ádám Kovács
Coding agents repeatedly consume long tool observations even though only a small fraction of each observation matters for the next step. We study task-conditioned tool-output pruni…