Konstantin Polev

Julia Belikova, Danila Rozhevskii, Dennis Svirin et al.

Efficient long-context processing remains a crucial challenge for contemporary large language models (LLMs), especially in resource-constrained environments. Soft compression architectures promise to extend effective context length by replacing long token sequences with smaller sets of learned compressed tokens. Yet, the limits of compressibility -- and when compression begins to erase task-relevant content -- remain underexplored. In this paper, we define token overflow as a regime in which compressed representations no longer contain sufficient information to answer a given query, and propose a methodology to characterize and detect it. In the xRAG soft-compression setting, we find that query-agnostic saturation statistics reliably separate compressed from uncompressed token representations, providing a practical tool for identifying compressed tokens but showing limited overflow detection capability. Lightweight probing classifiers over both query and context xRAG representations detect overflow with 0.72 AUC-ROC on average on HotpotQA, SQuADv2, and TriviaQA datasets, demonstrating that incorporating query information improves detection performance. These results advance from query-independent diagnostics to query-aware detectors, enabling low-cost pre-LLM gating to mitigate compression-induced errors.

Alexandra Bazarova, Aleksandr Yugay, Andrey Shulga et al.

Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting, which leverages a topological divergence metric to quantify the structural properties of graphs induced by attention matrices. Examining the topological divergence between prompt and response subgraphs reveals consistent patterns: higher divergence values in specific attention heads correlate with hallucinated outputs, independent of the dataset. Extensive experiments - including evaluation on question answering and summarization tasks - show that our approach achieves state-of-the-art or competitive results on several benchmarks while requiring minimal annotated data and computational resources. Our findings suggest that analyzing the topological structure of attention matrices can serve as an efficient and robust indicator of factual reliability in LLMs.

Anton Klenitskiy, Konstantin Polev, Daria Denisova et al.

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 research question, as a better understanding of their internals can help understand, influence, and control their behavior, which is very important in a variety of real-world applications. Recently sparse autoencoders (SAE) have been shown to be a promising unsupervised approach for extracting interpretable features from language models. These autoencoders learn to reconstruct hidden states of the transformer's internal layers from sparse linear combinations of directions in their activation space. This paper is focused on the application of SAE to the sequential recommendation domain. We show that this approach can be successfully applied to the transformer trained on a sequential recommendation task: learned directions turn out to be more interpretable and monosemantic than the original hidden state dimensions. Moreover, we demonstrate that the features learned by SAE can be used to effectively and flexibly control the model's behavior, providing end-users with a straightforward method to adjust their recommendations to different custom scenarios and contexts.

Julia Belikova, Konstantin Polev, Rauf Parchiev et al.

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly deployed in industry applications, yet their reliability remains hampered by challenges in detecting hallucinations. While supervised state-of-the-art (SOTA) methods that leverage LLM hidden states -- such as activation tracing and representation analysis -- show promise, their dependence on extensively annotated datasets limits scalability in real-world applications. This paper addresses the critical bottleneck of data annotation by investigating the feasibility of reducing training data requirements for two SOTA hallucination detection frameworks: Lookback Lens, which analyzes attention head dynamics, and probing-based approaches, which decode internal model representations. We propose a methodology combining efficient classification algorithms with dimensionality reduction techniques to minimize sample size demands while maintaining competitive performance. Evaluations on standardized question-answering RAG benchmarks show that our approach achieves performance comparable to strong proprietary LLM-based baselines with only 250 training samples. These results highlight the potential of lightweight, data-efficient paradigms for industrial deployment, particularly in annotation-constrained scenarios.