Home
Catalogue search
Refine your search:
Keyword
Creator / Publisher:
Dathathri, Sumanth (4)
Glaese, Amelia (4)
The 2021 Conference on Empirical Methods in Natural Language Processing 2021 (3)
Anderson, Kirsty (1)
Coppin, Ben (1)
Hendricks, Lisa Anne (1)
Huang, Po-Sen (1)
Kohli, Pushmeet (1)
Mellor, John (1)
Uesato, Jonathan (1)
more
Year:
2021 (4)
Medium:
Online (4)
Type:
Article (3)
Miscellaneous (1)
BLLDB-Access
Search in the Catalogues and Directories
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
Sort by
creator [A → Z]
'
creator [Z → A]
'
publishing year ↑ (asc)
'
publishing year ↓ (desc)
'
title [A → Z]
'
title [Z → A]
'
Simple Search
Hits 1 – 4 of 4
1
Challenges in Detoxifying Language Models ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Dathathri, Sumanth
;
Glaese, Amelia
. - : Underline Science Inc., 2021
BASE
Show details
2
Challenges in Detoxifying Language Models ...
Welbl, Johannes
;
Glaese, Amelia
;
Uesato, Jonathan
;
Dathathri, Sumanth
;
Mellor, John
;
Hendricks, Lisa Anne
;
Anderson, Kirsty
;
Kohli, Pushmeet
;
Coppin, Ben
;
Huang, Po-Sen
. - : arXiv, 2021
Abstract:
Large language models (LM) generate remarkably fluent text and can be efficiently adapted across NLP tasks. Measuring and guaranteeing the quality of generated text in terms of safety is imperative for deploying LMs in the real world; to this end, prior work often relies on automatic evaluation of LM toxicity. We critically discuss this approach, evaluate several toxicity mitigation strategies with respect to both automatic and human evaluation, and analyze consequences of toxicity mitigation in terms of model bias and LM quality. We demonstrate that while basic intervention strategies can effectively optimize previously established automatic metrics on the RealToxicityPrompts dataset, this comes at the cost of reduced LM coverage for both texts about, and dialects of, marginalized groups. Additionally, we find that human raters often disagree with high automatic toxicity scores after strong toxicity reduction interventions -- highlighting further the nuances involved in careful evaluation of LM toxicity. ... : 23 pages, 6 figures, published in Findings of EMNLP 2021 ...
Keyword:
Artificial Intelligence cs.AI
;
Computation and Language cs.CL
;
Computers and Society cs.CY
;
FOS Computer and information sciences
;
I.2.6; I.2.7
;
Machine Learning cs.LG
URL:
https://dx.doi.org/10.48550/arxiv.2109.07445
https://arxiv.org/abs/2109.07445
BASE
Hide details
3
Challenges in Detoxifying Language Models ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Dathathri, Sumanth
;
Glaese, Amelia
. - : Underline Science Inc., 2021
BASE
Show details
4
Challenges in Detoxifying Language Models ...
The 2021 Conference on Empirical Methods in Natural Language Processing 2021
;
Dathathri, Sumanth
;
Glaese, Amelia
. - : Underline Science Inc., 2021
BASE
Show details
Mobile view
All
Catalogues
UB Frankfurt Linguistik
0
IDS Mannheim
0
OLC Linguistik
0
UB Frankfurt Retrokatalog
0
DNB Subject Category Language
0
Institut für Empirische Sprachwissenschaft
0
Leibniz-Centre General Linguistics (ZAS)
0
Bibliographies
BLLDB
0
BDSL
0
IDS Bibliografie zur deutschen Grammatik
0
IDS Bibliografie zur Gesprächsforschung
0
IDS Konnektoren im Deutschen
0
IDS Präpositionen im Deutschen
0
IDS OBELEX meta
0
MPI-SHH Linguistics Collection
0
MPI for Psycholinguistics
0
Linked Open Data catalogues
Annohub
0
Online resources
Link directory
0
Journal directory
0
Database directory
0
Dictionary directory
0
Open access documents
BASE
4
Linguistik-Repository
0
IDS Publikationsserver
0
Online dissertations
0
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern