6 papers
ASK-NN: An Asymmetric Nearest-Neighbor Test that detects Distribution Drifts in Natural Language
Sergey Zakharov, Rodion Oblovatny, Alexey Zaytsev
Hallucinations and artificial text in LLM-generated outputs often appear as distributional deviations between prompt and response hidden-state distributions. Since prompts or retri…
Benchmarking on Tasks That Matter: Dataset Selection for Preserving Model Rankings
Rostislav Gusev, Alexey Zaytsev
Benchmarks of machine learning models often include many datasets, making evaluation expensive. For efficiency, it is preferable to perform evaluations on small, representative dat…
Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probing
Amina Miftakhova, Alexey Zaytsev
Detecting hallucination risk before generation enables abstention, retrieval augmentation, and routing decisions without incurring the cost of decoding. While prior work has shown…
Hallucination Detection in LLMs with Topological Divergence on Attention Graphs
Alexandra Bazarova, Andrei Volodichev, Aleksandr Yugay +10
Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOpology-based HAllucination detect…
INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation
Alexandra Bazarova, Andrei Volodichev, Daria Kotova +1
While retrieval-augmented generation (RAG) significantly improves the factual reliability of LLMs, it does not eliminate hallucinations, so robust uncertainty quantification (UQ) r…
Probabilistic distances-based hallucination detection in LLMs with RAG
Rodion Oblovatny, Alexandra Kuleshova, Konstantin Polev +1
Detecting hallucinations in large language models (LLMs) is critical for their safety in many applications. Without proper detection, these systems often provide harmful, unreliabl…