activity
20232026
most citedQuantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

51 citations · 89 across the 20 of their papers we have counts for

collaborators
Showing 2024 · cs.CLShow all

7 papers · 2 filters

cs.CL2024★ 1 cited

CulturalBench: A Robust, Diverse, and Challenging Cultural Benchmark by Human-AI CulturalTeaming

Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin +8

Robust, diverse, and challenging cultural knowledge benchmarks are essential for measuring our progress towards making LMs that are helpful across diverse cultures. We introduce Cu…

cs.CL2024★ 2 cited

The Art of Saying No: Contextual Noncompliance in Language Models

Faeze Brahman, Sachin Kumar, Vidhisha Balachandran +11

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…

cs.CL2024

ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions

Chan Young Park, Shuyue Stella Li, Hayoung Jung +4

This study introduces ValueScope, a framework leveraging language models to quantify social norms and values within online communities, grounded in social science perspectives on n…

cs.CL2024★ 1 cited

CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledge

Yu Ying Chiu, Liwei Jiang, Maria Antoniak +7

Frontier large language models (LLMs) are developed by researchers and practitioners with skewed cultural backgrounds and on datasets with skewed sources. However, LLMs' (lack of)…

cs.CL2024★ 1 cited

Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs

Aly M. Kassem, Omar Mahmoud, Niloofar Mireshghallah +5

In this paper, we introduce a black-box prompt optimization method that uses an attacker LLM agent to uncover higher levels of memorization in a victim agent, compared to what is r…

cs.CL2024★ 10 cited

Do Membership Inference Attacks Work on Large Language Models?

Michael Duan, Anshuman Suri, Niloofar Mireshghallah +7

Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model's training data. Despite extensive research on traditional machi…