Su Lin Blodgett

Emily Corvi

P. A. Dow

Jean Garcia-Gathright

A.R. Olteanu

Stefanie Reed

Emily Sheng

Dan Vann

Jennifer Wortman Vaughan

Matthew Vogel

Hannah Washington

Abigail Z. Jacobs … (voir 1 de plus)

Microsoft Research

Across academia, industry, and government, there is an increasing awareness that the measurement tasks involved in evaluating generative AI … (voir plus)(GenAI) systems are especially difficult. We argue that these measurement tasks are highly reminiscent of measurement tasks found throughout the social sciences. With this in mind, we present a framework, grounded in measurement theory from the social sciences, for measuring concepts related to the capabilities, impacts, opportunities, and risks of GenAI systems. The framework distinguishes between four levels: the background concept, the systematized concept, the measurement instrument(s), and the instance-level measurements themselves. This four-level approach differs from the way measurement is typically done in ML, where researchers and practitioners appear to jump straight from background concepts to measurement instruments, with little to no explicit systematization in between. As well as surfacing assumptions, thereby making it easier to understand exactly what the resulting measurements do and do not mean, this framework has two important implications for evaluating evaluations: First, it can enable stakeholders from different worlds to participate in conceptual debates, broadening the expertise involved in evaluating GenAI systems. Second, it brings rigor to operational debates by offering a set of lenses for interrogating the validity of measurement instruments and their resulting measurements.

2024-11-16

ArXiv (prépublication)

How different mental models of AI-based writing assistants impact writers’ interactions with them

Shalaleh Rismani

A.R. Olteanu

Q. Vera Liao

AJung Moon

2024-10-14

Proceedings of the Third Workshop on Intelligent and Interactive Writing Assistants (publié)

"I Am the One and Only, Your Cyber BFF": Understanding the Impact of GenAI Requires Understanding the Impact of Anthropomorphic AI

Myra Cheng

Alicia DeVrio

Lisa Egede

A.R. Olteanu

Many state-of-the-art generative AI (GenAI) systems are increasingly prone to anthropomorphic behaviors, i.e., to generating outputs that ar… (voir plus)e perceived to be human-like. While this has led to scholars increasingly raising concerns about possible negative impacts such anthropomorphic AI systems can give rise to, anthropomorphism in AI development, deployment, and use remains vastly overlooked, understudied, and underspecified. In this perspective, we argue that we cannot thoroughly map the social impacts of generative AI without mapping the social impacts of anthropomorphic AI, and outline a call to action.

2024-10-10

ArXiv (prépublication)

What is Your Favorite Gender, MLM? Gender Bias Evaluation in Multilingual Masked Language Models

Emily M. Bender

Jeongrok Yu

Timnit Gebru

Seong Ug Kim

Angelina McMillan-642

Jacob Choi

Jinho D. Choi

Solon Barocas

Hal Daumé III

Gilsinia Lopez

A.R. Olteanu

Robert Sim

Hanna Wallach. 2021

Stereotyp-657

Bias is a disproportionate prejudice in favor of one side against another. Due to the success of transformer-based Masked Language Models (M… (voir plus)LMs) and their impact on many NLP tasks, a systematic evaluation of bias in these models is needed more than ever. While many studies have evaluated gender bias in English MLMs, only a few works have been conducted for the task in other languages. This paper proposes a multilingual approach to estimate gender bias in MLMs from 5 languages: Chinese, English, German, Portuguese, and Spanish. Unlike previous work, our approach does not depend on parallel corpora coupled with English to detect gender bias in other languages using multilingual lexicons. Moreover, a novel model-based method is presented to generate sentence pairs for a more robust analysis of gender bias, compared to the traditional lexicon-based method. For each language, both the lexicon-based and model-based methods are applied to create two datasets respectively, which are used to evaluate gender bias in an MLM specifically trained for that language using one existing and 3 new scoring metrics. Our results show that the previous approach is data-sensitive and not stable as it does not remove contextual dependencies irrelevant to gender. In fact, the results often flip when different scoring metrics are used on the same dataset, suggesting that gender bias should be studied on a large dataset using multiple evaluation metrics for best practice.

2024-09-06

Information (publié)

ECBD: Evidence-Centered Benchmark Design for NLP

Yu Lu Liu

Jackie Chi

Jackie CK Cheung

Kit Cheung

Q. Vera Liao

A.R. Olteanu

Ziang Xiao

Benchmarking is seen as critical to assessing progress in NLP. However, creating a benchmark involves many design decisions (e.g., which dat… (voir plus)asets to include, which metrics to use) that often rely on tacit, untested assumptions about what the benchmark is intended to measure or is actually measuring. There is currently no principled way of analyzing these decisions and how they impact the validity of the benchmark's measurements. To address this gap, we draw on evidence-centered design in educational assessments and propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes the benchmark design process into five modules. ECBD specifies the role each module plays in helping practitioners collect evidence about capabilities of interest. Specifically, each module requires benchmark designers to describe, justify, and support benchmark design choices -- e.g., clearly specifying the capabilities the benchmark aims to measure or how evidence about those capabilities is collected from model responses. To demonstrate the use of ECBD, we conduct case studies with three benchmarks: BoolQ, SuperGLUE, and HELM. Our analysis reveals common trends in benchmark design and documentation that could threaten the validity of benchmarks' measurements.

2024-07-31

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (publié)

"One-Size-Fits-All"? Examining Expectations around What Constitute"Fair"or"Good"NLG System Behaviors

Li Lucy

Milad Shokouhi

Hanna Wallach

A.R. Olteanu

Fairness-related assumptions about what constitute appropriate NLG system behaviors range from invariance, where systems are expected to beh… (voir plus)ave identically for social groups, to adaptation, where behaviors should instead vary across them. To illuminate tensions around invariance and adaptation, we conduct five case studies, in which we perturb different types of identity-related language features (names, roles, locations, dialect, and style) in NLG system inputs. Through these cases studies, we examine people's expectations of system behaviors, and surface potential caveats of these contrasting yet commonly held assumptions. We find that motivations for adaptation include social norms, cultural differences, feature-specific information, and accommodation; in contrast, motivations for invariance include perspectives that favor prescriptivism, view adaptation as unnecessary or too difficult for NLG systems to do appropriately, and are wary of false assumptions. Our findings highlight open challenges around what constitute"fair"or"good"NLG system behaviors.

2024-05-31

Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) (publié)

Responsible AI Considerations in Text Summarization Research: A Review of Current Practices

Yu Lu Liu

Meng Cao

Jackie CK Cheung

A.R. Olteanu

Adam Trischler

2023-11-30

Findings of the Association for Computational Linguistics: EMNLP 2023 (publié)

openreview.net

FairPrism: Evaluating Fairness-Related Harms in Text Generation

Eve Fleisig

Aubrie Amstutz

Chad Atalla

Hal Daumé III

A.R. Olteanu

Emily Sheng

Dan Vann

Hanna Wallach

It is critical to measure and mitigate fairness-related harms caused by AI text generation systems, including stereotyping and demeaning har… (voir plus)ms. To that end, we introduce FairPrism, a dataset of 5,000 examples of AI-generated English text with detailed human annotations covering a diverse set of harms relating to gender and sexuality. FairPrism aims to address several limitations of existing datasets for measuring and mitigating fairness-related harms, including improved transparency, clearer specification of dataset coverage, and accounting for annotator disagreement and harms that are context-dependent. FairPrism’s annotations include the extent of stereotyping and demeaning harms, the demographic groups targeted, and appropriateness for different applications. The annotations also include specific harms that occur in interactive contexts and harms that raise normative concerns when the “speaker” is an AI system. Due to its precision and granularity, FairPrism can be used to diagnose (1) the types of fairness-related harms that AI text generation systems cause, and (2) the potential limitations of mitigation methods, both of which we illustrate through case studies. Finally, the process we followed to develop FairPrism offers a recipe for building improved datasets for measuring and mitigating harms caused by AI systems.

2023-06-30

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (publié)