[PDF][PDF] Metrics for what, metrics for whom: assessing actionability of bias evaluation metrics in NLP

P Delobelle, G Attanasio, D Nozza… - Proceedings of the …, 2024‏ - iris.unibocconi.it
This paper introduces the concept of actionability in the context of bias measures in natural
language processing (NLP). We define actionability as the degree to which a …

Examining Gender and Racial Bias in Large Vision-Language Models Using a Novel Dataset of Parallel Images

KC Fraser, S Kiritchenko - arxiv preprint arxiv:2402.05779, 2024‏ - arxiv.org
Following on recent advances in large language models (LLMs) and subsequent chat
models, a new wave of large vision-language models (LVLMs) has emerged. Such models …

Are Large Language Models Rational Investors?

Y Zhou, Y Ni, X Liu, J Zhang, S Liu, G Ye… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Large Language Models (LLMs) are progressively being adopted in financial analysis to
harness their extensive knowledge base for interpreting complex market data and trends …

I Think, Therefore I am: Awareness in Large Language Models

Y Li, Y Huang, Y Lin, S Wu, Y Wan, L Sun - arxiv preprint arxiv …, 2024‏ - arxiv.org
Do large language models (LLMs) exhibit any forms of awareness similar to humans? In this
paper, we introduce the concept of awareness to LLMs, arguing that awareness is an …

A taxonomy of stereotype content in large language models

G Nicolas, A Caliskan - arxiv preprint arxiv:2408.00162, 2024‏ - arxiv.org
This study introduces a taxonomy of stereotype content in contemporary large language
models (LLMs). We prompt ChatGPT 3.5, Llama 3, and Mixtral 8x7B, three powerful and …

Towards Bidirectional Human-AI Alignment: A Systematic Review for Clarifications, Framework, and Future Directions

H Shen, T Knearem, R Ghosh, K Alkiek… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Recent advancements in general-purpose AI have highlighted the importance of guiding AI
systems towards the intended goals, ethical principles, and values of individuals and …

Profiling Bias in LLMs: Stereotype dimensions in Contextual word embeddings

CM Schuster, MA Dinisor, S Ghatiwala… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Large language models (LLMs) are the foundation of the current successes of artificial
intelligence (AI), however, they are unavoidably biased. To effectively communicate the risks …

LLMs are Vulnerable to Malicious Prompts Disguised as Scientific Language

Y Ge, N Kirtane, H Peng, D Hakkani-Tür - arxiv preprint arxiv:2501.14073, 2025‏ - arxiv.org
As large language models (LLMs) have been deployed in various real-world settings,
concerns about the harm they may propagate have grown. Various jailbreaking techniques …

Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes

S Jeoung, Y Ge, H Wang, J Diesner - arxiv preprint arxiv:2501.14294, 2025‏ - arxiv.org
Examining the alignment of large language models (LLMs) has become increasingly
important, particularly when these systems fail to operate as intended. This study explores …

GeniL: A Multilingual Dataset on Generalizing Language

AM Davani, S Gubbi, S Dev, S Dave… - arxiv preprint arxiv …, 2024‏ - arxiv.org
LLMs are increasingly transforming our digital ecosystem, but they often inherit societal
biases learned from their training data, for instance stereotypes associating certain attributes …