Models
Datasets
Spaces
Docs
Enterprise
Pricing
Log In
Sign Up

Collections

Discover the best community collections!

Collections including paper arxiv:2308.09662

Our AI Safety Research

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique

Paper • 2408.10701 • Published Aug 20, 2024 • 12
Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming

Paper • 2406.11654 • Published Jun 17, 2024 • 6
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

Paper • 2409.11242 • Published Sep 17, 2024 • 7
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Paper • 2308.09662 • Published Aug 18, 2023 • 3

Large Language Model Alignment: A Survey

Paper • 2309.15025 • Published Sep 26, 2023 • 2
Aligning Large Language Models with Human: A Survey

Paper • 2307.12966 • Published Jul 24, 2023 • 1
Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Paper • 2305.18290 • Published May 29, 2023 • 64
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF

Paper • 2310.05344 • Published Oct 9, 2023 • 1

Moral Foundations of Large Language Models

Paper • 2310.15337 • Published Oct 23, 2023 • 1
Specific versus General Principles for Constitutional AI

Paper • 2310.13798 • Published Oct 20, 2023 • 3
Contrastive Prefence Learning: Learning from Human Feedback without RL

Paper • 2310.13639 • Published Oct 20, 2023 • 25
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Paper • 2309.00267 • Published Sep 1, 2023 • 52

Our research on LLM safety

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Paper • 2402.11746 • Published Feb 19, 2024 • 2
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Paper • 2308.09662 • Published Aug 18, 2023 • 3
Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases

Paper • 2310.14303 • Published Oct 22, 2023 • 1
Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming

Paper • 2406.11654 • Published Jun 17, 2024 • 6

LTD: Low Temperature Distillation for Robust Adversarial Training

Paper • 2111.02331 • Published Nov 3, 2021 • 1
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy

Paper • 1906.06784 • Published Jun 16, 2019 • 1
Pruning Adversarially Robust Neural Networks without Adversarial Examples

Paper • 2210.04311 • Published Oct 9, 2022 • 1
Mitigating the Accuracy-Robustness Trade-off via Multi-Teacher Adversarial Distillation

Paper • 2306.16170 • Published Jun 28, 2023 • 1

Our AI Safety Research

Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique

Paper • 2408.10701 • Published Aug 20, 2024 • 12
Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming

Paper • 2406.11654 • Published Jun 17, 2024 • 6
Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

Paper • 2409.11242 • Published Sep 17, 2024 • 7
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Paper • 2308.09662 • Published Aug 18, 2023 • 3

Our research on LLM safety

Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic

Paper • 2402.11746 • Published Feb 19, 2024 • 2
Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Paper • 2308.09662 • Published Aug 18, 2023 • 3
Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases

Paper • 2310.14303 • Published Oct 22, 2023 • 1
Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming

Paper • 2406.11654 • Published Jun 17, 2024 • 6

Large Language Model Alignment: A Survey

Paper • 2309.15025 • Published Sep 26, 2023 • 2
Aligning Large Language Models with Human: A Survey

Paper • 2307.12966 • Published Jul 24, 2023 • 1
Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Paper • 2305.18290 • Published May 29, 2023 • 64
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF

Paper • 2310.05344 • Published Oct 9, 2023 • 1

LTD: Low Temperature Distillation for Robust Adversarial Training

Paper • 2111.02331 • Published Nov 3, 2021 • 1
Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy

Paper • 1906.06784 • Published Jun 16, 2019 • 1
Pruning Adversarially Robust Neural Networks without Adversarial Examples

Paper • 2210.04311 • Published Oct 9, 2022 • 1
Mitigating the Accuracy-Robustness Trade-off via Multi-Teacher Adversarial Distillation

Paper • 2306.16170 • Published Jun 28, 2023 • 1

Moral Foundations of Large Language Models

Paper • 2310.15337 • Published Oct 23, 2023 • 1
Specific versus General Principles for Constitutional AI

Paper • 2310.13798 • Published Oct 20, 2023 • 3
Contrastive Prefence Learning: Learning from Human Feedback without RL

Paper • 2310.13639 • Published Oct 20, 2023 • 25
RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Paper • 2309.00267 • Published Sep 1, 2023 • 52

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs