Picture for Nithum Thain

Nithum Thain

Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics

Add code
Mar 13, 2024
Figure 1 for Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
Figure 2 for Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
Figure 3 for Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
Figure 4 for Detecting Hallucination and Coverage Errors in Retrieval Augmented Generation for Controversial Topics
Viaarxiv icon

Gemma: Open Models Based on Gemini Research and Technology

Add code
Mar 13, 2024
Figure 1 for Gemma: Open Models Based on Gemini Research and Technology
Figure 2 for Gemma: Open Models Based on Gemini Research and Technology
Figure 3 for Gemma: Open Models Based on Gemini Research and Technology
Figure 4 for Gemma: Open Models Based on Gemini Research and Technology
Viaarxiv icon

ConstitutionalExperts: Training a Mixture of Principle-based Prompts

Add code
Mar 07, 2024
Figure 1 for ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Figure 2 for ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Figure 3 for ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Figure 4 for ConstitutionalExperts: Training a Mixture of Principle-based Prompts
Viaarxiv icon

Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals

Add code
May 22, 2023
Figure 1 for Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals
Figure 2 for Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals
Figure 3 for Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals
Figure 4 for Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals
Viaarxiv icon

Towards Agile Text Classifiers for Everyone

Add code
Feb 13, 2023
Figure 1 for Towards Agile Text Classifiers for Everyone
Figure 2 for Towards Agile Text Classifiers for Everyone
Figure 3 for Towards Agile Text Classifiers for Everyone
Figure 4 for Towards Agile Text Classifiers for Everyone
Viaarxiv icon

Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning

Add code
Feb 13, 2023
Figure 1 for Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Figure 2 for Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Figure 3 for Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Figure 4 for Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning
Viaarxiv icon

Plex: Towards Reliability using Pretrained Large Model Extensions

Add code
Jul 15, 2022
Figure 1 for Plex: Towards Reliability using Pretrained Large Model Extensions
Figure 2 for Plex: Towards Reliability using Pretrained Large Model Extensions
Figure 3 for Plex: Towards Reliability using Pretrained Large Model Extensions
Figure 4 for Plex: Towards Reliability using Pretrained Large Model Extensions
Viaarxiv icon

Measuring Recommender System Effects with Simulated Users

Add code
Jan 12, 2021
Figure 1 for Measuring Recommender System Effects with Simulated Users
Figure 2 for Measuring Recommender System Effects with Simulated Users
Figure 3 for Measuring Recommender System Effects with Simulated Users
Figure 4 for Measuring Recommender System Effects with Simulated Users
Viaarxiv icon

Six Attributes of Unhealthy Conversation

Add code
Oct 14, 2020
Figure 1 for Six Attributes of Unhealthy Conversation
Figure 2 for Six Attributes of Unhealthy Conversation
Figure 3 for Six Attributes of Unhealthy Conversation
Figure 4 for Six Attributes of Unhealthy Conversation
Viaarxiv icon

Fairness without Demographics through Adversarially Reweighted Learning

Add code
Jun 24, 2020
Figure 1 for Fairness without Demographics through Adversarially Reweighted Learning
Figure 2 for Fairness without Demographics through Adversarially Reweighted Learning
Figure 3 for Fairness without Demographics through Adversarially Reweighted Learning
Figure 4 for Fairness without Demographics through Adversarially Reweighted Learning
Viaarxiv icon