6 papers
SIRIN: A Unified Toolkit for Detecting Contextual Hallucinations in Retrieval-Augmented and Memory-Grounded LLM Systems
Julia Belikova, Rauf Parchiev, Mikhail Filimonov +3
SIRIN (Semantic Inconsistency Recognition and Inspection Nexus) is a unified toolkit and interactive web UI for detecting contextual hallucinations (fluent, plausible responses uns…
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…
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…
Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control
Anton Klenitskiy, Konstantin Polev, Daria Denisova +3
Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important…
Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation
Julia Belikova, Danila Rozhevskii, Dennis Svirin +2
Efficient long-context processing remains a crucial challenge for contemporary large language models (LLMs), especially in resource-constrained environments. Soft compression archi…
Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs
Julia Belikova, Konstantin Polev, Rauf Parchiev +1
Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly deployed in industry applications, yet their reliability remains hampered by challeng…