Papers by Maxim Panov

13 papers
Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Uncertainty quantification (UQ) is a prominent approach for eliciting truthful answers from large language models (LLMs).
Approach: They propose to use a well-established method for text generation to extract token embeddings from multiple layers of LLMs and compute MD scores for each token.
Outcome: The proposed method improves on existing methods and provides accurate and computationally efficient uncertainty scores for sequence-level selective generation and claim-level fact-checking tasks.
How Certain is Your Transformer? (2021.eacl-main)

Copied to clipboard

Challenge: Obtaining reliable uncertainty estimations for such neural networks (NNs) is challenging due to the huge number of parameters in these deep learning models.
Approach: They propose to use Monte Carlo dropout to estimate uncertainty for Transformer-based models and construct inexpensive estimates using Determinantal Point Processes.
Outcome: The proposed estimates improve the quality of detection of error-prone instances.
UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) generate misleading or outright incorrect information.
Approach: They propose a method that debiases uncertainty scores on output length and uses residuals as corrected, length-invariant estimates.
Outcome: The proposed method improves over nominally length-normalized methods on machine translation, summarization, and question-answering tasks.
Hybrid Uncertainty Quantification for Selective Text Classification in Ambiguous Tasks (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for text classification tasks are inherently ambiguous and can cause errors.
Approach: They propose a method that combines epistemic and aleatoric uncertainty to estimate toxicity detection errors.
Outcome: The proposed method outperforms existing methods for toxicity detection and other ambiguous text classification tasks.
LM-Polygraph: Uncertainty Estimation for Language Models (2023.emnlp-demo)

Copied to clipboard

Challenge: Large language models often "hallucinate" i.e., fabricate facts without providing users an apparent means to discern the veracity of their statements.
Approach: They propose a framework with implementations of state-of-the-art UE methods for LLMs with unified program interfaces in Python.
Outcome: The proposed framework implements state-of-the-art UE methods for LLMs with unified program interfaces in Python and an extendable benchmark for consistent evaluation by researchers.
Uncertainty Estimation of Transformer Predictions for Misclassification Detection (2022.acl-long)

Copied to clipboard

Challenge: Uncertainty estimation (UE) of model predictions is crucial step for a variety of tasks such as active learning, misclassification detection, adversarial attack detection, etc.
Approach: They propose to modify UE methods for Transformer models for misclassification detection in named entity recognition and text classification tasks to improve model expressiveness and computational performance.
Outcome: The proposed methods outperform computationally intensive methods on misclassification detection tasks and are based on a large dataset of simulated datasets.
Uncertainty Quantification for Large Language Models (2025.acl-tutorials)

Copied to clipboard

Challenge: Large language models (LLMs) produce hallucinations, which undermine user trust and reliability.
Approach: This tutorial offers the first systematic introduction to uncertainty quantification (UQ) for LLMs in text generation tasks.
Outcome: The proposed framework provides tools for communicating the reliability of a model answer.
Efficient Out-of-Domain Detection for Sequence to Sequence Models (2023.findings-acl)

Copied to clipboard

Challenge: Sequence-to-sequence (seq2sequ) models are a ubiquitous tool for text generation but they are not suitable for many other tasks.
Approach: They propose to use UE techniques to identify out-of-domain (OOD) inputs where the model is susceptible to errors.
Outcome: The proposed methods outperform heavyweight ensembles on the task of OOD detection.
Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Uncertainty quantification (UQ) is a promising approach for detecting hallucinations and low-quality outputs of Large Language Models (LLMs).
Approach: They propose to learn conditional dependency between autoregressive LLM generation steps from attention-based features and a two-staged training procedure to incorporate recurrent features.
Outcome: The proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
Active Learning for Abstractive Text Summarization (2022.findings-emnlp)

Copied to clipboard

Challenge: Abstractive text summarization (ATS) requires a long document and short summaries.
Approach: They propose a query strategy for AL in abstractive text summarization that uses uncertainty estimation to reduce model performance.
Outcome: The proposed query strategy improves ROUGE and consistency scores for annotated datasets . it also increases the performance of the model, compared to passive annotation.
Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification (2024.findings-acl)

Copied to clipboard

Challenge: Large language models are notorious for producing erroneous claims in their output.
Approach: They propose a fact-checking and hallucination detection pipeline based on token-level uncertainty quantification that removes the impact of uncertainty about what claim to generate on the current step and what surface form to use.
Outcome: The proposed method can fact-check the atomic claims in the output of large language models.
Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to mitigating hallucinations conflate factuality with faithfulness to the retrieved evidence, incorrectly labeling factually correct statements as hallucinos . Existing methods to mitigate hallucinics rely on a lack of training data coverage, input ambiguity, and architectural constraints.
Approach: They propose a method for hallucination detection in Large Language Models enhanced with knowledge retrieval based on faithfulness to the retrieved context.
Outcome: The proposed method outperforms unsupervised UQ baselines, RAG-specific methods, and supervised classifiers across multiple tasks and LLMs.
Reference-free Hallucination Detection for Large Vision-Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Large vision-language models exhibit excellent ability in language understanding, question answering, and conversations of visual inputs, but they are prone to producing hallucinations.
Approach: They propose to use supervised uncertainty quantification methods to detect hallucinations in large vision-language models.
Outcome: The proposed methods outperform the others in detecting hallucinations on four representative LVLMs across two different tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations