Verfahren und System zur Referenzfreien Halluzinationsdetektion in Grossen Sprachmodellen

Details

Veröffentlichungs-Nr.

EP4752782

Anmeldetag

16. September 2025

Veröffentlichung

3. Juni 2026

Rechtsraum

EP

IPC

G06F40/30

Abstract

Hallucinations in LLMs pose significant challenges and it is hard to accurately identify hallucinated predictions of LLMs in the absence of references. The present disclosure utilizes sample responses from LLMs and classifies them using a model trained on Natural Language Inference (NLI) scores. The plurality of NLI scores include an entailment, a neutrality and a plurality of contradiction scores. Post computing NLI scores, an average NLI score is computed based on the plurality of NLI scores. Further, a plurality of individual response predictions are obtained by classifying the plurality of responses based on the NLI scores using a hallucination classifier. Simultaneously, overall response predictions are obtained and a confidence score is computed for the overall prediction of hallucination classifier Finally, an optimal response is predicted based on the confidence score associated with the overall prediction of the hallucination classifier and the plurality of NLI scores.

Anmelder

Firma

Tata Consultancy Services Limited

Land

🇮🇳 Indien