Search Results for author:
Found 7 papers, 5 papers with code
Universal Adversarial Triggers Are Not Universal
On the other hand, while AFT models may appear safe on the surface, exhibiting refusals to a range of unsafe instructions, we show that they are highly susceptible to adversarial triggers.
Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering
Guided by human evaluation and analysis, we highlight the shortcomings of traditional metrics for both correctness and faithfulness.
StarCoder: may the source be with you!
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15. 5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention.
Ranked #43 on
Code Generation
on MBPP
Using In-Context Learning to Improve Dialogue Safety
For instance, using automatic evaluation, we find our best fine-tuned baseline only generates safe responses to unsafe dialogue contexts from DiaSafety 4. 04% more than our approach.
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on.
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
The principle is that this should result in worse model performance compared to masking random tokens.
Exploring Conditioning for Generative Music Systems with Human-Interpretable Controls
Performance RNN is a machine-learning system designed primarily for the generation of solo piano performances using an event-based (rather than audio) representation.
