Built on

Perspective api
Google · 2017
Earlier work this paper cites.
Counterfactual fairness
M. J. Kusner, J. Loftus, C. Russell, and R. Silva · 2017
Earlier work this paper cites.
Active learning for convolutional neural networks: A core-set approach
Original
O. Sener and S. Savarese · 2017
Earlier work this paper cites.
Bert: Pre-training of deep bidirectional transformers for language understanding
Original
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova · 2018
Earlier work this paper cites.
Mix-and-match tuning for self-supervised semantic segmentation
X. Zhan, Z. Liu, P. Luo, X. Tang, and C. Loy · 2018
Earlier work this paper cites.
Deep batch active learning by diverse, uncertain gradient lower bounds
Original
J. T. Ash, C. Zhang, A. Krishnamurthy, J. Langford, and A. Agarwal · 2019
Earlier work this paper cites.
Batch active learning at scale
G. Citovsky, G. DeSalvo, C. Gentile, L. Karydas, A. Rajagopalan, A. Rostamizadeh, and S. Kumar · 2021
Earlier work this paper cites.
Training a helpful and harmless assistant with reinforcement learning from human feedback
Original
Y. Bai, A. Jones, K. Ndousse, A. Askell, A. Chen, N. DasSarma, D. Drain, S. Fort, D. Ganguli, T. Henighan, et al · 2022
Earlier work this paper cites.
Self-guided noise-free data generation for efficient zero-shot learning
Original
J. Gao, R. Pi, Y. Lin, H. Xu, J. Ye, Z. Wu, W. Zhang, X. Liang, Z. Li, and L. Kong · 2022
Earlier work this paper cites.
Ask me what you need: Product retrieval using knowledge from gpt-3
Original
S. Y. Kim, H. Park, K. Shin, and K.-M. Kim · 2022
Earlier work this paper cites.
Data augmentation for intent classification with off-the-shelf large language models
Original
G. Sahu, P. Rodriguez, I. H. Laradji, P. Atighehchian, D. Vazquez, and D. Bahdanau · 2022
Earlier work this paper cites.
" i’m sorry to hear that": Finding new biases in language models with a holistic descriptor dataset
Original
E. M. Smith, M. Hall, M. Kambadur, E. Presani, and A. Williams · 2022
Earlier work this paper cites.

Similar

Gpt-4 technical report
Original
J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al · 2023
Cited alongside, same era.
Rethinking conversational agents in the era of llms: Proactivity, non-collaborativity, and beyond
Y. Deng, W. Lei, M. Huang, and T.-S. Chua · 2023
Cited alongside, same era.
Llama guard: Llm-based input-output safeguard for human-ai conversations
Original
H. Inan, K. Upasani, J. Chi, R. Rungta, K. Iyer, Y. Mao, M. Tontchev, Q. Hu, B. Fuller, D. Testuggine, et al · 2023
Cited alongside, same era.
Beavertails: Towards improved safety alignment of llm via a human-preference dataset, 2023
Original
J. Ji, M. Liu, J. Dai, X. Pan, C. Zhang, C. Bian, C. Zhang, R. Sun, Y. Wang, and Y. Yang · 2023
Cited alongside, same era.
Harnessing large-language models to generate private synthetic text

Then

Humans or llms as the judge? a study on judgement biases
Original
G. H. Chen, S. Chen, Z. Liu, F. Jiang, and B. Wang · 2024
Closest in time.
Aegis: Online adaptive ai content safety moderation with ensemble of llm experts
Original
S. Ghosh, P. Varshney, E. Galinkin, and C. Parisien · 2024
Closest in time.
Responsible generative ai toolkit: https://ai.google.dev/responsible/principles, 2024
Google · 2024
Closest in time.
Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms
Original
S. Han, K. Rao, A. Ettinger, L. Jiang, B. Y. Lin, N. Lambert, Y. Choi, and N. Dziri · 2024
Closest in time.
An empirical study of llm-as-a-judge for llm evaluation: Fine-tuned judge models are task-specific classifiers
Original

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…

2024

ShieldGemma: Generative AI Content Moderation Based on Gemma

Zeng, Wenjun, Liu, Yuchi, Mullins, Ryan et al.

Understand

We present ShieldGemma, a comprehensive suite of LLM-based safety content moderation models built upon Gemma2.

These models provide robust, state-of-the-art predictions of safety risks across key harm types (sexually explicit, dangerous content, harassment, hate speech) in both user input and LLM-generated output.
By evaluating on both public and internal benchmarks, we demonstrate superior performance compared to existing models, such as Llama Guard (+10.8\% AU-PRC on public benchmarks) and WildCard (+4.3\%).
Additionally, we present a novel LLM-based data curation pipeline, adaptable to a variety of safety-related tasks and beyond.

Built on

Perspective api
Google · 2017
Earlier work this paper cites.
Counterfactual fairness
M. J. Kusner, J. Loftus, C. Russell, and R. Silva · 2017
Earlier work this paper cites.
Active learning for convolutional neural networks: A core-set approach
Original
O. Sener and S. Savarese · 2017
Earlier work this paper cites.
Bert: Pre-training of deep bidirectional transformers for language understanding
Original
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova · 2018
Earlier work this paper cites.
Mix-and-match tuning for self-supervised semantic segmentation
X. Zhan, Z. Liu, P. Luo, X. Tang, and C. Loy · 2018
Earlier work this paper cites.
Deep batch active learning by diverse, uncertain gradient lower bounds
Original
J. T. Ash, C. Zhang, A. Krishnamurthy, J. Langford, and A. Agarwal · 2019
Earlier work this paper cites.
Batch active learning at scale
G. Citovsky, G. DeSalvo, C. Gentile, L. Karydas, A. Rajagopalan, A. Rostamizadeh, and S. Kumar · 2021
Earlier work this paper cites.
Training a helpful and harmless assistant with reinforcement learning from human feedback
Original
Y. Bai, A. Jones, K. Ndousse, A. Askell, A. Chen, N. DasSarma, D. Drain, S. Fort, D. Ganguli, T. Henighan, et al · 2022
Earlier work this paper cites.
Self-guided noise-free data generation for efficient zero-shot learning
Original
J. Gao, R. Pi, Y. Lin, H. Xu, J. Ye, Z. Wu, W. Zhang, X. Liang, Z. Li, and L. Kong · 2022
Earlier work this paper cites.
Ask me what you need: Product retrieval using knowledge from gpt-3
Original
S. Y. Kim, H. Park, K. Shin, and K.-M. Kim · 2022
Earlier work this paper cites.
Data augmentation for intent classification with off-the-shelf large language models
Original
G. Sahu, P. Rodriguez, I. H. Laradji, P. Atighehchian, D. Vazquez, and D. Bahdanau · 2022
Earlier work this paper cites.
" i’m sorry to hear that": Finding new biases in language models with a holistic descriptor dataset
Original
E. M. Smith, M. Hall, M. Kambadur, E. Presani, and A. Williams · 2022
Earlier work this paper cites.

Similar

Gpt-4 technical report
Original
J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al · 2023
Cited alongside, same era.
Rethinking conversational agents in the era of llms: Proactivity, non-collaborativity, and beyond
Y. Deng, W. Lei, M. Huang, and T.-S. Chua · 2023
Cited alongside, same era.
Llama guard: Llm-based input-output safeguard for human-ai conversations
Original
H. Inan, K. Upasani, J. Chi, R. Rungta, K. Iyer, Y. Mao, M. Tontchev, Q. Hu, B. Fuller, D. Testuggine, et al · 2023
Cited alongside, same era.
Beavertails: Towards improved safety alignment of llm via a human-preference dataset, 2023
Original
J. Ji, M. Liu, J. Dai, X. Pan, C. Zhang, C. Bian, C. Zhang, R. Sun, Y. Wang, and Y. Yang · 2023
Cited alongside, same era.
Harnessing large-language models to generate private synthetic text