arXiv subjects

Konstantin Polev

Publications and source records attributed to Konstantin Polev.

7 recordsLinked to original sources

arXiv2026

SIRIN: A Unified Toolkit for Detecting Contextual Hallucinations in Retrieval-Augmented and Memory-Grounded LLM Systems

SIRIN (Semantic Inconsistency Recognition and Inspection Nexus) is a unified toolkit and interactive web UI for detecting contextual hallucinations (fluent, plausible responses unsupported by the provided evidence) in retrieval-augmented, agentic, and memory-grounded LLM systems. SIRIN unifies three detector paradigms (representation probing, uncertainty estimation, and judge-style verification) and the complementary task of pre-generation query answerability under one interface, configuration system, and evaluation pipeline, supporting response- and span-level inspection in both white-box and black-box settings. The web UI enables live analysis of user-supplied context-query-answer triples through hallucination scores, unsupported-span highlighting, and side-by-side detector comparison, with a lightweight plug-in design for adding new detectors. We demonstrate SIRIN on hallucination detection, query answerability, and as a faithfulness gate within long-term memory systems. The source code is publicly available at https://github.com/sb-ai-lab/SIRIN.

cs.AI↗

arXiv2026

Hallucination Detection in LLMs with Topological Divergence on Attention Graphs

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.

cs.CL↗

arXiv2026

Probabilistic distances-based hallucination detection in LLMs with RAG

Detecting hallucinations in large language models (LLMs) is critical for their safety in many applications. Without proper detection, these systems often provide harmful, unreliable answers. In recent years, LLMs have been actively used in retrieval-augmented generation (RAG) settings. However, hallucinations remain even in this setting, and while numerous hallucination detection methods have been proposed, most approaches are not specifically designed for RAG systems. To overcome this limitation, we introduce a hallucination detection method based on estimating the distances between the distributions of prompt token embeddings and language model response token embeddings. The method examines the geometric structure of token hidden states to reliably extract a signal of factuality in text, while remaining friendly to long sequences. Extensive experiments demonstrate that our method achieves state-of-the-art or competitive performance. It also has transferability from solving the NLI task to the hallucination detection task, making it a fully unsupervised and efficient method with a competitive performance on the final task.

cs.CL↗

arXiv2026

Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control

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 to extract interpretable features from neural networks. In this work, we extend SAE to sequential recommender systems and propose a framework for interpreting and controlling model representations. We show that this approach can be successfully applied to the transformer trained on a sequential recommendation task: directions learned in such an unsupervised regime turn out to be more interpretable and monosemantic than the original hidden state dimensions. Further, we demonstrate a straightforward way to effectively and flexibly control the model's behavior, giving developers and users of recommendation systems the ability to adjust their recommendations to various custom scenarios and contexts.

cs.IR↗

arXiv2026

Detecting Overflow in Compressed Token Representations for Retrieval-Augmented Generation

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.

cs.CL↗

arXiv2025

Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs

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.

cs.CL↗

arXiv2023

AlphaFold2 can predict single-mutation effects

AlphaFold2 (AF) is a promising tool, but is it accurate enough to predict single mutation effects? Here, we report that the localized structural deformation between protein pairs differing by only 1-3 mutations -- as measured by the effective strain -- is correlated across \num{3901} experimental and AF-predicted structures. Furthermore, analysis of ${\sim} 11000$ proteins shows that the local structural change correlates with various phenotypic changes. These findings suggest that AF can predict the range and magnitude of single-mutation effects on average, and we propose a method to improve precision of AF predictions and to indicate when predictions are unreliable.

q-bio.BM↗