@inproceedings{brahman2024the,
author = {Brahman, Faeze and Kumar, Sachin and Balachandran, Vidhisha and Dasigi, Pradeep and Pyatkin, Valentina and Ravichander, Abhilasha and Wiegreffe, Sarah and Dziri, Nouha and Chandu, K. and Hessel, Jack and Tsvetkov, Yulia and Smith, Noah A. and Choi, Yejin and Hajishirzi, Hanna and Balachandran, Vidhisha},
title = {The Art of Saying No: Contextual Noncompliance in Language Models},
booktitle = {NeurIPS 2024},
year = {2024},
month = {July},
abstract = {Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of"unsafe"queries, we posit that the scope of noncompliance should be broadened. We introduce a comprehensive taxonomy of contextual noncompliance describing when and how models should not comply with user requests. Our taxonomy spans a wide range of categories including incomplete, unsupported, indeterminate, and humanizing requests (in addition to unsafe requests). To test noncompliance capabilities of language models, we use this taxonomy to develop a new evaluation suite of 1000 noncompliance prompts. We find that most existing models show significantly high compliance rates in certain previously understudied categories with models like GPT-4 incorrectly complying with as many as 30% of requests. To address these gaps, we explore different training strategies using a synthetically-generated training set of requests and expected noncompliant responses. Our experiments demonstrate that while direct finetuning of instruction-tuned models can lead to both over-refusal and a decline in general capabilities, using parameter efficient methods like low rank adapters helps to strike a good balance between appropriate noncompliance and other capabilities.},
url = {http://approjects.co.za/?big=en-us/research/publication/the-art-of-saying-no-contextual-noncompliance-in-language-models/},
}