Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices
Fuente:
arXiv
Saved in:
| Main Authors: | Kostenok, Elizaveta, Cherniavskii, Daniil, Zaytsev, Alexey |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Label Attention Network for Temporal Sets Prediction: You Were Looking at a Wrong Self-Attention
by: Kovtun, Elizaveta, et al.
Published: (2023)
by: Kovtun, Elizaveta, et al.
Published: (2023)
Holistic Uncertainty Estimation For Open-Set Recognition
by: Erlygin, Leonid, et al.
Published: (2024)
by: Erlygin, Leonid, et al.
Published: (2024)
Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting
by: Proskura, Polina, et al.
Published: (2024)
by: Proskura, Polina, et al.
Published: (2024)
Hiding Backdoors within Event Sequence Data via Poisoning Attacks
by: Ermilova, Alina, et al.
Published: (2023)
by: Ermilova, Alina, et al.
Published: (2023)
PINE: Pipeline for Important Node Exploration in Attributed Networks
by: Kovtun, Elizaveta, et al.
Published: (2025)
by: Kovtun, Elizaveta, et al.
Published: (2025)
Parameter-Efficient Neural CDEs via Implicit Function Jacobians
by: Kuleshov, Ilya, et al.
Published: (2025)
by: Kuleshov, Ilya, et al.
Published: (2025)
Uniting contrastive and generative learning for event sequences models
by: Yugay, Aleksandr, et al.
Published: (2024)
by: Yugay, Aleksandr, et al.
Published: (2024)
Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing
by: Serov, Egor, et al.
Published: (2026)
by: Serov, Egor, et al.
Published: (2026)
When an LLM is apprehensive about its answers -- and when its uncertainty is justified
by: Sychev, Petr, et al.
Published: (2025)
by: Sychev, Petr, et al.
Published: (2025)
Complexity-aware fine-tuning
by: Goncharov, Andrey, et al.
Published: (2025)
by: Goncharov, Andrey, et al.
Published: (2025)
Foundation for unbiased cross-validation of spatio-temporal models for species distribution modeling
by: Koldasbayeva, Diana, et al.
Published: (2025)
by: Koldasbayeva, Diana, et al.
Published: (2025)
ALIEN: Aligned Entropy Head for Improving Uncertainty Estimation of LLMs
by: Zabolotnyi, Artem, et al.
Published: (2025)
by: Zabolotnyi, Artem, et al.
Published: (2025)
Strong Linear Baselines Strike Back: Closed-Form Linear Models as Gaussian Process Conditional Density Estimators for TSAD
by: Yugay, Aleksandr, et al.
Published: (2026)
by: Yugay, Aleksandr, et al.
Published: (2026)
InDiD: Instant Disorder Detection via Representation Learning
by: Romanenkova, Evgenia, et al.
Published: (2021)
by: Romanenkova, Evgenia, et al.
Published: (2021)
U-Former ODE: Fast Probabilistic Forecasting of Irregular Time Series
by: Kuleshov, Ilya, et al.
Published: (2026)
by: Kuleshov, Ilya, et al.
Published: (2026)
Accelerating Transformers in Online RL
by: Zelezetsky, Daniil, et al.
Published: (2025)
by: Zelezetsky, Daniil, et al.
Published: (2025)
Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modeling
by: Khalin, Aleksei, et al.
Published: (2026)
by: Khalin, Aleksei, et al.
Published: (2026)
A theoretical framework for self-supervised contrastive learning for continuous dependent data
by: Marusov, Alexander, et al.
Published: (2025)
by: Marusov, Alexander, et al.
Published: (2025)
Normalizing self-supervised learning for provably reliable Change Point Detection
by: Bazarova, Alexandra, et al.
Published: (2024)
by: Bazarova, Alexandra, et al.
Published: (2024)
WWAggr: A Window Wasserstein-based Aggregation for Ensemble Change Point Detection
by: Stepikin, Alexander, et al.
Published: (2025)
by: Stepikin, Alexander, et al.
Published: (2025)
Language steering in latent space to mitigate unintended code-switching
by: Goncharov, Andrey, et al.
Published: (2025)
by: Goncharov, Andrey, et al.
Published: (2025)
Never Skip a Batch: Continuous Training of Temporal GNNs via Adaptive Pseudo-Supervision
by: Panyshev, Alexander, et al.
Published: (2025)
by: Panyshev, Alexander, et al.
Published: (2025)
Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts
by: Tulchinskii, Eduard, et al.
Published: (2023)
by: Tulchinskii, Eduard, et al.
Published: (2023)
From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimation
by: Kotelevskii, Nikita, et al.
Published: (2024)
by: Kotelevskii, Nikita, et al.
Published: (2024)
Concealed Adversarial attacks on neural networks for sequential data
by: Sokerin, Petr, et al.
Published: (2025)
by: Sokerin, Petr, et al.
Published: (2025)
Testing Uncertainty of Large Language Models for Physics Knowledge and Reasoning
by: Reganova, Elizaveta, et al.
Published: (2024)
by: Reganova, Elizaveta, et al.
Published: (2024)
Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes
by: Jenson, Daniel, et al.
Published: (2025)
by: Jenson, Daniel, et al.
Published: (2025)
Collusion Detection with Graph Neural Networks
by: Gomes, Lucas, et al.
Published: (2024)
by: Gomes, Lucas, et al.
Published: (2024)
Uncertainty Estimation for the Open-Set Text Classification systems
by: Erlygin, Leonid, et al.
Published: (2026)
by: Erlygin, Leonid, et al.
Published: (2026)
The Differences Between Direct Alignment Algorithms are a Blur
by: Gorbatovski, Alexey, et al.
Published: (2025)
by: Gorbatovski, Alexey, et al.
Published: (2025)
Surrogate uncertainty estimation for your time series forecasting black-box: learn when to trust
by: Erlygin, Leonid, et al.
Published: (2023)
by: Erlygin, Leonid, et al.
Published: (2023)
Trust-Region Behavior Blending for On-Policy Distillation
by: Plyusov, Daniil, et al.
Published: (2026)
by: Plyusov, Daniil, et al.
Published: (2026)
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
by: Plyusov, Daniil, et al.
Published: (2026)
by: Plyusov, Daniil, et al.
Published: (2026)
Long-term drought prediction using deep neural networks based on geospatial weather data
by: Marusov, Alexander, et al.
Published: (2023)
by: Marusov, Alexander, et al.
Published: (2023)
Selective Adversarial Attacks on LLM Benchmarks
by: Dubrovsky, Ivan, et al.
Published: (2025)
by: Dubrovsky, Ivan, et al.
Published: (2025)
Looking around you: external information enhances representations for event sequences
by: Sokerin, Petr, et al.
Published: (2025)
by: Sokerin, Petr, et al.
Published: (2025)
Conformal Prediction for Uncertainty Estimation in Drug-Target Interaction Prediction
by: Rakhshaninejad, Morteza, et al.
Published: (2025)
by: Rakhshaninejad, Morteza, et al.
Published: (2025)
Effective Interplay between Sparsity and Quantization: From Theory to Practice
by: Harma, Simla Burcu, et al.
Published: (2024)
by: Harma, Simla Burcu, et al.
Published: (2024)
Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors
by: Sinii, Viacheslav, et al.
Published: (2025)
by: Sinii, Viacheslav, et al.
Published: (2025)
Vulnerability Detection via Topological Analysis of Attention Maps
by: Snopov, Pavel, et al.
Published: (2024)
by: Snopov, Pavel, et al.
Published: (2024)
Similar Items
-
Label Attention Network for Temporal Sets Prediction: You Were Looking at a Wrong Self-Attention
by: Kovtun, Elizaveta, et al.
Published: (2023) -
Holistic Uncertainty Estimation For Open-Set Recognition
by: Erlygin, Leonid, et al.
Published: (2024) -
Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting
by: Proskura, Polina, et al.
Published: (2024) -
Hiding Backdoors within Event Sequence Data via Poisoning Attacks
by: Ermilova, Alina, et al.
Published: (2023) -
PINE: Pipeline for Important Node Exploration in Attributed Networks
by: Kovtun, Elizaveta, et al.
Published: (2025)