31 citations · 52 across the 12 of their papers we have counts for
12 papers
CodeTD: Topology of Attention Detects Hallucinations in Code LLMs
Daria Voronkova, Ilya Trofimov, Anton Dmitriev +3
As AI-code assistant tools become widespread, automatic assessment of the correctness of generated code becomes a significant challenge. Code LLMs are prone to hallucinations, whic…
Edge-wise Topological Divergence Gaps: Guiding Search in Combinatorial Optimization
Ilya Trofimov, Daria Voronkova, Alexander Mironenko +4
We introduce a topological feedback mechanism for the Travelling Salesman Problem (TSP) by analyzing the divergence between a tour and the minimum spanning tree (MST). Our key cont…
Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story
Vladislav Pedashenko, Laida Kushnareva, Yana Khassan Nibal +5
Intrinsic dimension (ID) is an important tool in modern LLM analysis, informing studies of training dynamics, scaling behavior, and dataset structure, yet its textual determinants…
RTD-Lite: Scalable Topological Analysis for Comparing Weighted Graphs in Learning Tasks
Eduard Tulchinskii, Daria Voronkova, Ilya Trofimov +2
Topological methods for comparing weighted graphs are valuable in various learning tasks but often suffer from computational inefficiency on large datasets. We introduce RTD-Lite,…
Quantifying Logical Consistency in Transformers via Query-Key Alignment
Eduard Tulchinskii, Anastasia Voznyuk, Laida Kushnareva +4
Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi-step logical reasoning remain…
Robust AI-Generated Text Detection by Restricted Embeddings
Kristian Kuznetsov, Eduard Tulchinskii, Laida Kushnareva +4
Growing amount and quality of AI-generated texts makes detecting such content more difficult. In most real-world scenarios, the domain (style and topic) of generated data and the g…
Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models
Eduard Tulchinskii, Laida Kushnareva, Kristian Kuznetsov +5
Large language models (LLMs) routinely fail to output the correct option in multiple-choice question answering (MCQA) while encoding the answer internally. We expose this latent kn…
Scalar Function Topology Divergence: Comparing Topology of 3D Objects
Ilya Trofimov, Daria Voronkova, Eduard Tulchinskii +2
We propose a new topological tool for computer vision - Scalar Function Topology Divergence (SFTD), which measures the dissimilarity of multi-scale topology between sublevel sets o…
Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts
Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva +5
Rapidly increasing quality of AI-generated content makes it difficult to distinguish between human and AI-generated texts, which may lead to undesirable consequences for society. T…
Learning Topology-Preserving Data Representations
Ilya Trofimov, Daniil Cherniavskii, Eduard Tulchinskii +3
We propose a method for learning topology-preserving data representations (dimensionality reduction). The method aims to provide topological similarity between the data manifold an…
Topological Data Analysis for Speech Processing
Eduard Tulchinskii, Kristian Kuznetsov, Laida Kushnareva +5
We apply topological data analysis (TDA) to speech classification problems and to the introspection of a pretrained speech model, HuBERT. To this end, we introduce a number of topo…
Acceptability Judgements via Examining the Topology of Attention Maps
Daniil Cherniavskii, Eduard Tulchinskii, Vladislav Mikhailov +7
The role of the attention mechanism in encoding linguistic knowledge has received special interest in NLP. However, the ability of the attention heads to judge the grammatical acce…