paper-with-me

홈 › Papers

The Art of Saying No: Contextual Noncompliance in Language Models

2024-07-02 · Faeze Brahman, Sachin Kumar, Vidhisha Balachandran, Pradeep Dasigi, Valentina Pyatkin, Abhilasha Ravichander, Sarah Wiegreffe, Nouha Dziri, Khyathi Chandu, Jack Hessel, Yulia Tsvetkov, Noah A. Smith, Yejin Choi, Hannaneh Hajishirzi

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.

📄 PDF Abstract BibTeX arXiv:2407.12043

Code (1)

allenai/compred pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Thompson Sampling for Noncompliant Bandits

2018-12-03 · Andrew Stirn, Tony Jebara

Thompson sampling, a Bayesian method for balancing exploration and exploitation in bandit problems, has theoretical guarantees and exhibits strong empirical performance in many domains. Traditional Thompson sampling, how…

Thompson Sampling

Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings

2023-09-15 · Chen Cecilia Liu, Fajri Koto, Timothy Baldwin, Iryna Gurevych

Large language models (LLMs) are highly adept at question answering and reasoning tasks, but when reasoning in a situational context, human expectations vary depending on the relevant cultural common ground. As languages…

Question Answering

UMUTeam at SemEval-2021 Task 7: Detecting and Rating Humor and Offense with Linguistic Features and Word Embeddings

2021-08-01 · SEMEVAL 2021 · Jos{\'e} Antonio Garc{\'\i}a-D{\'\i}az, Rafael Valencia-Garc{\'\i}a

In writing, humor is mainly based on figurative language in which words and expressions change their conventional meaning to refer to something without saying it directly. This flip in the meaning of the words prevents N…

Sentiment AnalysisWord Embeddings

Exploring Chinese Humor Generation: A Study on Two-Part Allegorical Sayings

2024-03-16 · Rongwu Xu

Humor, a culturally nuanced aspect of human language, poses challenges for computational understanding and generation, especially in Chinese humor, which remains relatively unexplored in the NLP community. This paper inv…

Contrastive LearningLanguage ModelingLanguage Modelling

"Ge Shu Zhi Zhi": Towards Deep Understanding about Worlds

2018-12-19 · Bao-Gang Hu, Wei-Ming Dong

"Ge She Zhi Zhi" is a novel saying in Chinese, stated as "To investigate things from the underlying principle(s) and to acquire knowledge in the form of mathematical representations". The saying is adopted and modified b…

Position