Papers by Nicholas Meade
Exploiting Instruction-Following Retrievers for Malicious Information Retrieval (2025.findings-acl)
Copied to clipboard
| Challenge: | Instruction-following retrievers are increasingly used in real-world applications, but little research has investigated the safety risks associated with their increasing search capabilities. |
| Approach: | They investigate the ability of retrievers to satisfy malicious queries . they find that for >50% of queries, retrievers can select harmful passages . |
| Outcome: | The findings highlight the safety risks associated with instruction-following retrievers . they show that even safety-aligned LLMs can satisfy malicious requests . |
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. |
| Approach: | They propose to use Counterfactual Data Augmentation, Dropout, Iterative Nullspace Projection, Self-Debias, and SentenceDebia as bias mitigation techniques to quantify their effectiveness. |
| Outcome: | The proposed techniques are Counterfactual Data Augmentation (CDA), Dropout, Iterative Nullspace Projection, Self-Debias, and SentenceDebia. |
Using In-Context Learning to Improve Dialogue Safety (2023.findings-emnlp)
Copied to clipboard
Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tur
| Challenge: | Recent work has highlighted safety issues with large neural-based conversational models. |
| Approach: | They propose a retrieval-based approach for reducing bias and toxicity in chatbot responses . they retrieve demonstrations of safe responses to similar dialogue contexts to generate a response . |
| Outcome: | The proposed method reduces bias and toxicity in three chatbot models . it can be used in compliment to existing dialogue safety approaches, such as RLHF. |
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining (2022.findings-emnlp)
Copied to clipboard
| Challenge: | To explain NLP models, importance measures are often used to inform input tokens are important for making a prediction. |
| Approach: | They propose a faithfulness metric that masks allegedly important tokens and retrains the model. |
| Outcome: | The proposed metric is based on LSTM-attention models and RoBERTa models. |