43 citations · 75 across the 7 of their papers we have counts for
8 papers
Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps
Jonas Waldendorf, Bashar Awwad Shiekh Hasan, Evgenii Tsymbalov
Hallucinations in Speech Large Language Models (SpeechLLMs) pose significant risks, yet existing detection methods typically rely on gold-standard outputs that are costly or imprac…
Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification
Ekaterina Fadeeva, Aleksandr Rubashevskii, Artem Shelmanov +9
Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccura…
ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change
David Thulke, Yingbo Gao, Petrus Pelser +23
This paper introduces ClimateGPT, a model family of domain-specific large language models that synthesize interdisciplinary research on climate change. We trained two 7B models fro…
Dropout Strikes Back: Improved Uncertainty Estimation via Diversity Sampling
Kirill Fedyanin, Evgenii Tsymbalov, Maxim Panov
Uncertainty estimation for machine learning models is of high importance in many scenarios such as constructing the confidence intervals for model predictions and detection of out-…
Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning
Evgenii Tsymbalov, Sergei Makarychev, Alexander Shapeev +1
Active learning methods for neural networks are usually based on greedy criteria which ultimately give a single new design point for the evaluation. Such an approach requires eithe…
Dropout-based Active Learning for Regression
Evgenii Tsymbalov, Maxim Panov, Alexander Shapeev
Active learning is relevant and challenging for high-dimensional regression models when the annotation of the samples is expensive. Yet most of the existing sampling methods cannot…
Compact difference scheme for parabolic and Schrödinger-type equations with variable coefficients
Vladimir Gordin, Evgenii Tsymbalov
We develop a new compact scheme for second-order PDE (parabolic and Schrödinger type) with a variable time-independent coefficient. It has a higher order and smaller error than cla…
Compact difference schemes for weakly-nonlinear parabolic and Schrodinger-type equations and systems
Vladimir Gordin, Evgenii Tsymbalov
The implicit compact finite-difference scheme was developed for evolutionary partial differential parabolic and Schrödinger-type equations and systems with a weak nonlinearity. To…