Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?

Shiyu Ni|Keping Bi|Lulu Yu|Jiafeng Guo


Anthology ID:DBLP:conf/ccir/NiBYG24
Volume:Information Retrieval - 30th China Conference, CCIR 2024, Wuhan, China, October 18-20, 2024, Revised Selected Papers
Year:2024
Venue:China Conference on Information Retrieval (CCIR)
Publisher:Springer
Pages:124-135
URL:https://doi.org/10.1007/978-981-96-1710-4_10
DOI:https://doi.org/10.1007/978-981-96-1710-4_10
DBLP:conf/ccir/NiBYG24
BibTeX:
@inproceedings{ni-2024-large, author = {Shiyu Ni and Keping Bi and Lulu Yu and Jiafeng Guo}, editor = {Xiangnan He and Zhaochun Ren and Ruiming Tang}, title = {{Are Large Language Models More Honest in Their Probabilistic or Verbalized Confidence?}}, booktitle = {{Information Retrieval - 30th China Conference, CCIR 2024, Wuhan, China, October 18-20, 2024, Revised Selected Papers}}, series = {Lecture Notes in Computer Science}, volume = {15418}, pages = {124--135}, publisher = {Springer}, year = {2024}, url = {https://doi.org/10.1007/978-981-96-1710-4_10}, doi = {https://doi.org/10.1007/978-981-96-1710-4_10} }