Picture for Alessandro Sordoni

Alessandro Sordoni

Efficient Adversarial Training in LLMs with Continuous Attacks

Add code
May 24, 2024
Viaarxiv icon

Towards Modular LLMs by Building and Reusing a Library of LoRAs

Add code
May 18, 2024
Viaarxiv icon

V-STaR: Training Verifiers for Self-Taught Reasoners

Add code
Feb 09, 2024
Viaarxiv icon

Guiding Language Model Reasoning with Planning Tokens

Add code
Oct 09, 2023
Figure 1 for Guiding Language Model Reasoning with Planning Tokens
Figure 2 for Guiding Language Model Reasoning with Planning Tokens
Figure 3 for Guiding Language Model Reasoning with Planning Tokens
Figure 4 for Guiding Language Model Reasoning with Planning Tokens
Viaarxiv icon

Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference

Add code
Jun 21, 2023
Figure 1 for Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference
Figure 2 for Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference
Figure 3 for Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference
Figure 4 for Deep Language Networks: Joint Prompt Training of Stacked LLMs using Variational Inference
Viaarxiv icon

On the Compositional Generalization Gap of In-Context Learning

Add code
Nov 15, 2022
Figure 1 for On the Compositional Generalization Gap of In-Context Learning
Figure 2 for On the Compositional Generalization Gap of In-Context Learning
Figure 3 for On the Compositional Generalization Gap of In-Context Learning
Figure 4 for On the Compositional Generalization Gap of In-Context Learning
Viaarxiv icon

Multi-Head Adapter Routing for Data-Efficient Fine-Tuning

Add code
Nov 07, 2022
Figure 1 for Multi-Head Adapter Routing for Data-Efficient Fine-Tuning
Figure 2 for Multi-Head Adapter Routing for Data-Efficient Fine-Tuning
Figure 3 for Multi-Head Adapter Routing for Data-Efficient Fine-Tuning
Figure 4 for Multi-Head Adapter Routing for Data-Efficient Fine-Tuning
Viaarxiv icon

Expressiveness and Learnability: A Unifying View for Evaluating Self-Supervised Learning

Add code
Jun 02, 2022
Figure 1 for Expressiveness and Learnability: A Unifying View for Evaluating Self-Supervised Learning
Figure 2 for Expressiveness and Learnability: A Unifying View for Evaluating Self-Supervised Learning
Figure 3 for Expressiveness and Learnability: A Unifying View for Evaluating Self-Supervised Learning
Figure 4 for Expressiveness and Learnability: A Unifying View for Evaluating Self-Supervised Learning
Viaarxiv icon

Evaluating Distributional Distortion in Neural Language Modeling

Add code
Mar 24, 2022
Figure 1 for Evaluating Distributional Distortion in Neural Language Modeling
Figure 2 for Evaluating Distributional Distortion in Neural Language Modeling
Figure 3 for Evaluating Distributional Distortion in Neural Language Modeling
Figure 4 for Evaluating Distributional Distortion in Neural Language Modeling
Viaarxiv icon

Better Language Model with Hypernym Class Prediction

Add code
Mar 21, 2022
Figure 1 for Better Language Model with Hypernym Class Prediction
Figure 2 for Better Language Model with Hypernym Class Prediction
Figure 3 for Better Language Model with Hypernym Class Prediction
Figure 4 for Better Language Model with Hypernym Class Prediction
Viaarxiv icon