Picture for Nicholas Meade

Nicholas Meade

Exploiting Instruction-Following Retrievers for Malicious Information Retrieval

Add code
Mar 11, 2025
Viaarxiv icon

SafeArena: Evaluating the Safety of Autonomous Web Agents

Add code
Mar 06, 2025
Viaarxiv icon

Universal Adversarial Triggers Are Not Universal

Add code
Apr 24, 2024
Viaarxiv icon

Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering

Add code
Jul 31, 2023
Viaarxiv icon

StarCoder: may the source be with you!

Add code
May 09, 2023
Viaarxiv icon

Using In-Context Learning to Improve Dialogue Safety

Add code
Feb 02, 2023
Figure 1 for Using In-Context Learning to Improve Dialogue Safety
Figure 2 for Using In-Context Learning to Improve Dialogue Safety
Figure 3 for Using In-Context Learning to Improve Dialogue Safety
Figure 4 for Using In-Context Learning to Improve Dialogue Safety
Viaarxiv icon

An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-Trained Language Models

Add code
Oct 16, 2021
Figure 1 for An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-Trained Language Models
Figure 2 for An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-Trained Language Models
Figure 3 for An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-Trained Language Models
Figure 4 for An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-Trained Language Models
Viaarxiv icon

Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining

Add code
Oct 15, 2021
Figure 1 for Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Figure 2 for Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Figure 3 for Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Figure 4 for Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Viaarxiv icon

Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls

Add code
Aug 04, 2019
Figure 1 for Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls
Figure 2 for Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls
Figure 3 for Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls
Figure 4 for Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls
Viaarxiv icon