AI & ML interests
Explainable AI, Rule-based models, Rule learning with LLMs, Hallucination detection, Fact checking LLMs
Recent Activity
Papers
ACL-Verbatim: hallucination-free question answering for research
Squeez: Task-Conditioned Tool-Output Pruning for Coding Agents
Organization Card
KR Labs develops transparent and trustworthy AI solutions for natural language processing (NLP) tasks. KR Labs was founded by NLP researchers Ádám Kovács and Gábor Recski. Between 2023 and 2024, KR Labs was incubated in the TU Wien i²ncubator at the TU Wien Innovation Incubation Center (i²c)..
Hallucination free RAG and out SOTA state-of-the-art extractors
LettuceDetect v1. Trained ModernBERT (base and large) for detection hallucinations in LLM responses. The models are trained as token classifications.
-
KRLabsOrg/lettucedect-base-modernbert-en-v1
Token Classification • 0.1B • Updated • 9.09k • • 19 -
KRLabsOrg/lettucedect-large-modernbert-en-v1
Token Classification • 0.4B • Updated • 4.06k • 30 -
LettuceDetect: A Hallucination Detection Framework for RAG Applications
Paper • 2502.17125 • Published • 14 -
LettuceDetect
🥬7Let Us Detect your hallucinations! Demo for our framework.
Hallucination free RAG and out SOTA state-of-the-art extractors
LettuceDetect v1. Trained ModernBERT (base and large) for detection hallucinations in LLM responses. The models are trained as token classifications.
-
KRLabsOrg/lettucedect-base-modernbert-en-v1
Token Classification • 0.1B • Updated • 9.09k • • 19 -
KRLabsOrg/lettucedect-large-modernbert-en-v1
Token Classification • 0.4B • Updated • 4.06k • 30 -
LettuceDetect: A Hallucination Detection Framework for RAG Applications
Paper • 2502.17125 • Published • 14 -
LettuceDetect
🥬7Let Us Detect your hallucinations! Demo for our framework.
models 28
KRLabsOrg/acl-verbatim-modernbert
Token Classification • 0.1B • Updated • 31 • 2
KRLabsOrg/verbatim-rag-modern-bert-v2
Token Classification • 0.1B • Updated • 333 • 5
KRLabsOrg/verbatim-rag-modern-bert-v1
Text Classification • 0.1B • Updated • 151 • • 15
KRLabsOrg/squeez-2b
Text Generation • 2B • Updated • 523 • 4
KRLabsOrg/lettucedect-mmbert-small-hu-v1
Token Classification • 0.1B • Updated • 3
KRLabsOrg/lettucedect-mmbert-base-hu-v1
Token Classification • 0.3B • Updated
KRLabsOrg/tinylettuce-ettin-68m-en
Token Classification • 68.4M • Updated • 131 • 2
KRLabsOrg/tinylettuce-ettin-17m-en
Token Classification • 16.9M • Updated • 180 • 2
KRLabsOrg/tinylettuce-ettin-68m-en-bioasq
Token Classification • 68.4M • Updated • 74 • 2
KRLabsOrg/tinylettuce-ettin-32m-en
Token Classification • 32M • Updated • 14 • 1
datasets 17
KRLabsOrg/acl-anthology-md
Viewer • Updated • 235k • 1.24k • 1
KRLabsOrg/acl-verbatim-spans
Viewer • Updated • 46.6k • 182
KRLabsOrg/verbatim-spans
Viewer • Updated • 391k • 215
KRLabsOrg/lettucedetect-prose-hallucination
Viewer • Updated • 87.8k • 20
KRLabsOrg/lettucedetect-code-hallucination
Viewer • Updated • 79.6k • 141 • 1
KRLabsOrg/tool-output-extraction-swebench-gliner2-v2
Viewer • Updated • 13.1k • 313
KRLabsOrg/tool-output-extraction-swebench-gliner
Viewer • Updated • 64.1k • 817
KRLabsOrg/tool-output-extraction-swebench
Viewer • Updated • 11.4k • 703 • 2
KRLabsOrg/rag-bioasq-lettucedetect
Viewer • Updated • 3.6k • 40 • 1
KRLabsOrg/ragtruth-de-translated-manual-300
Viewer • Updated • 300 • 14