- Academic Search

A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions

O Shorinwa, Z Mei, J Lidard, AZ Ren… - arxiv preprint arxiv …, 2024 - arxiv.org

The remarkable performance of large language models (LLMs) in content generation,
coding, and common-sense reasoning has spurred widespread integration into many facets …

Enregistrer Citer Cité 1 fois Autres articles Version HTML

Atomic Calibration of LLMs in Long-Form Generations

C Zhang, R Yang, Z Zhang, X Huang, S Yang… - arxiv preprint arxiv …, 2024 - arxiv.org

Large language models (LLMs) often suffer from hallucinations, posing significant
challenges for real-world applications. Confidence calibration, which estimates the …

Enregistrer Citer Cité 3 fois Autres articles Les 2 versions Free GPT-4 Version HTML

LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models

E Stengel-Eskin, P Hase, M Bansal - arxiv preprint arxiv:2405.21028, 2024 - arxiv.org

When answering questions, LLMs can convey not only an answer, but a level of confidence
about the answer being correct. This includes explicit confidence markers (eg giving a …

Enregistrer Citer Autres articles Les 3 versions Free GPT-4 Version HTML

Neural Topic Modeling with Large Language Models in the Loop

X Yang, H Zhao, W Xu, Y Qi, J Lu, D Phung… - arxiv preprint arxiv …, 2024 - arxiv.org

Topic modeling is a fundamental task in natural language processing, allowing the
discovery of latent thematic structures in text corpora. While Large Language Models (LLMs) …

Graph-based Confidence Calibration for Large Language Models

Y Li, S Wang, L Huang, LP Liu - arxiv preprint arxiv:2411.02454, 2024 - arxiv.org

One important approach to improving the reliability of large language models (LLMs) is to
provide accurate confidence estimations regarding the correctness of their answers …

Enregistrer Citer Autres articles Les 2 versions Free GPT-4 Version HTML

-calibration of Language Model Confidence Scores for Generative QA

P Manggala, A Mastakouri, E Kirschbaum… - arxiv preprint arxiv …, 2024 - arxiv.org

To use generative question-and-answering (QA) systems for decision-making and in any
critical application, these systems need to provide well-calibrated confidence scores that …

Calibrating Verbalized Probabilities for Large Language Models

C Wang, G Szarvas, G Balazs, P Danchenko… - arxiv preprint arxiv …, 2024 - arxiv.org

Calibrating verbalized probabilities presents a novel approach for reliably assessing and
leveraging outputs from black-box Large Language Models (LLMs). Recent methods have …

[PDF] openreview.net

LACIE: Listener-Aware Finetuning for Calibration in Large Language Models

E Stengel-Eskin, P Hase, M Bansal - The Thirty-eighth Annual Conference … - openreview.net

When answering questions, large language models (LLMs) can convey not only an answer
to the question, but a level of confidence about the answer being correct. This includes …