Language model behavior: A comprehensive survey

TA Chang, BK Bergen - Computational Linguistics, 2024 - direct.mit.edu
Transformer language models have received widespread public attention, yet their
generated text is often surprising even to NLP researchers. In this survey, we discuss over …

Bloom: A 176b-parameter open-access multilingual language model

T Le Scao, A Fan, C Akiki, E Pavlick, S Ilić, D Hesslow… - 2023 - inria.hal.science
Large language models (LLMs) have been shown to be able to perform new tasks based on
a few demonstrations or natural language instructions. While these capabilities have led to …

Easily accessible text-to-image generation amplifies demographic stereotypes at large scale

F Bianchi, P Kalluri, E Durmus, F Ladhak… - Proceedings of the …, 2023 - dl.acm.org
Machine learning models that convert user-written text descriptions into images are now
widely available online and used by millions of users to generate millions of images a day …

Foundational challenges in assuring alignment and safety of large language models

U Anwar, A Saparov, J Rando, D Paleka… - arXiv preprint arXiv …, 2024 - arxiv.org
This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Co-writing with opinionated language models affects users' views

M Jakesch, A Bhat, D Buschek, L Zalmanson… - Proceedings of the …, 2023 - dl.acm.org
If large language models like GPT-3 preferably produce a particular point of view, they may
influence people's opinions on an unknown scale. This study investigates whether a …

Trustworthy LLMs: A survey and guideline for evaluating large language models' alignment

Y Liu, Y Yao, JF Ton, X Zhang, RGH Cheng… - arXiv preprint arXiv …, 2023 - arxiv.org
Ensuring alignment, which refers to making models behave in accordance with human
intentions [1, 2], has become a critical task before deploying large language models (LLMs) …

Assessing cross-cultural alignment between ChatGPT and human societies: An empirical study

Y Cao, L Zhou, S Lee, L Cabello, M Chen… - arXiv preprint arXiv …, 2023 - arxiv.org
The recent release of ChatGPT has garnered widespread recognition for its exceptional
ability to generate human-like responses in dialogue. Given its usage by users from various …

Gender bias and stereotypes in large language models

H Kotek, R Dockum, D Sun - Proceedings of the ACM collective …, 2023 - dl.acm.org
Large Language Models (LLMs) have made substantial progress in the past several months,
shattering state-of-the-art benchmarks in many domains. This paper investigates LLMs' …

Probing pre-trained language models for cross-cultural differences in values

A Arora, LA Kaffee, I Augenstein - arXiv preprint arXiv:2203.13722, 2022 - arxiv.org
Language embeds information about social, cultural, and political values people hold. Prior
work has explored social and potentially harmful biases encoded in Pre-Trained Language …

Having beer after prayer? measuring cultural bias in large language models

T Naous, MJ Ryan, A Ritter, W Xu - arXiv preprint arXiv:2305.14456, 2023 - arxiv.org
As the reach of large language models (LMs) expands globally, their ability to cater to
diverse cultural contexts becomes crucial. Despite advancements in multilingual …