Accepted Papers

Evaluating and Mitigating Discrimination in Language Model Decisions

Alex Tamkin · Amanda Askell · Liane Lovitt · Esin DURMUS · Nicholas Joseph · Shauna Kravec · Karina Nguyen · Jared Kaplan · Deep Ganguli

Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation

To Eun Kim · Fernando Diaz

Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML

Prakhar Ganesh · Usman Gohar · Lu Cheng · Golnoosh Farnadi

Evaluating Gender Bias Transfer between Pre-trained and Prompt Adapted Language Models

Nivedha Sivakumar · Natalie Mackraz · Samira Khorshidi · Krishna Patel · Barry-John Theobald · Luca Zappella · Nicholas Apostoloff

The Search for Less Discriminatory Algorithms: Limits and Opportunities

Benjamin Laufer · Manish Raghavan · Solon Barocas

M²FGB: A Min-Max Gradient Boosting Framework for Subgroup Fairness

Jansen Pereira · Giovani Valdrighi · Marcos M. Raimundo

Benchmark to Audit LLM Generated Clinical Notes for Disparities Arising from Biases and Stereotypes

Hongyu Cai · Swetasudha Panda · Naveen Jafer Nizar · Qinlan Shen · Daeja Oxendine · Sumana Srivatsa · Krishnaram Kenthapadi

Mitigating Bias in Facial Recognition Systems: Centroid Fairness Loss Optimization   

Jean-Rémy Conti · Stephan Clémençon

Measuring Representational Harms in Image Generation with a Multi-Group Proportional Metric 

Sangwon Jung · Claudio Mayrink Verdun · Alex Oesterling · Sajani Vithana · Taesup Moon · Flavio du Pin Calmon

Efficient Fairness-Performance Pareto Front Computation

Mark Kozdoba · Benny Perets · Shie Mannor

The Search for Less Discriminatory Algorithms: Limits and Opportunities

Benjamin Laufer · Manish Raghavan · Solon Barocas

From Models to Systems: A Comprehensive Fairness Framework for Compositional Recommender Systems

Brian Hsu · Cyrus DiCiccio · Natesh Pillai · Hongseok Namkoong

Understanding The Effect Of Temperature On Alignment With Human Opinions

Maja Pavlovic · Massimo Poesio

Towards Reliable Fairness Assessments of Multi-Label Image Classifiers

Melissa Hall · Bobbie Chern · Laura Gustafson · Denisse Ventura · Harshad Kulkarni · Candace Ross · Nicolas Usunier

Toward Large Language Models that Benefit for All: Benchmarking Group Fairness in Reward Models

Kefan Song · Jin Yao · Shangtong Zhang

Better Bias Benchmarking of Language Models via Multi-factor Analysis

Hannah Powers · Ioana Baldini · Dennis Wei · Kristin P Bennett

Adaptive Group Robust Ensemble Knowledge Distillation

Patrik Joslin Kenfack · Ulrich Aïvodji · Samira Ebrahimi Kahou

Evaluating Gender Bias Transfer between Pre-trained and Prompt Adapted Language Models

Nivedha Sivakumar · Natalie Mackraz · Samira Khorshidi · Krishna Patel · Barry-John Theobald · Luca Zappella · Nicholas Apostoloff

The Intersectionality Problem for Algorithmic Fairness 

Johannes Himmelreich · Arbie Hsu · Kristian Lum · Ellen Veomett

Counterpart Fairness – Addressing Systematic Between-Group Differences in Fairness Evaluation

Yifei Wang · Zhengyang Zhou · Liqin Wang · John Laurentiev · Peter Hou · Li Zhou · Pengyu Hong

Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation

To Eun Kim · Fernando Diaz

Multi-Output Distributional Fairness via Post-Processing

Gang Li · Qihang Lin · Ayush Ghosh · Tianbao Yang

Fair Summarization: Bridging Quality and Diversity in Extractive Summaries

Sina Bagheri Nezhad · Sayan Bandyapadhyay · Ameeta Agrawal

Different Horses for Different Courses: Comparing Bias Mitigation Algorithms in ML

Prakhar Ganesh · Usman Gohar · Lu Cheng · Golnoosh Farnadi

Improving Bias Metrics in Vision-Language Models by Addressing Inherent Model Disabilities

Lakshmipathi Balaji Darur · Shanmukha Sai Keerthi Gouravarapu · Shashwat Goel · Ponnurangam Kumaraguru

Beyond Internal Data: Constructing Complete Datasets for Fairness Testing

Varsha Ramineni · Hossein A. Rahmani · Emine Yilmaz · David Barber

Optimal Selection Using Algorithmic Rankings with Side Information

Kate Donahue · Nicole Immorlica · Brendan Lucier

Verifiable evaluations of machine learning models using zkSNARKs

Tobin South · Alexander Camuto · Shrey Jain · Robert Mahari · Christian Paquin · Jason Morton · Alex `Sandy' Pentland

Imitation Guided Automated Red Teaming

Sajad Mousavi · Desik Rengarajan · Ashwin Ramesh Babu · Vineet Gundecha · Soumyendu Sarkar

Measuring the Impact of Equal Treatment as Blindness via Explanations Disparity

Carlos Mougan · Salvatore Ruggieri · Laura State · Antonio Ferrara · Steffen Staab

Multilingual Hallucination Gaps in Large Language Models 

Cléa Chataigner · Afaf Taik · Golnoosh Farnadi

Evaluating and Mitigating Discrimination in Language Model Decisions 

Alex Tamkin · Amanda Askell · Liane Lovitt · Esin DURMUS · Nicholas Joseph · Shauna Kravec · Karina Nguyen · Jared Kaplan · Deep Ganguli

Fairness-Enhancing Data Augmentation Methods for Worst-Group Accuracy

Monica Welfert · Nathan Stromberg · Lalitha Sankar

Exploring AUC-like metrics to propose threshold-independent fairness evaluation 

Daniel Gratti · Thalita Veronese · Marcos M. Raimundo

Integrating Participatory Methods with Technical Fairness Solutions: Enhancing Bias Mitigation and Equity in AI Systems 

Abdoul Jalil Djiberou Mahamadou · Lea Goetz 

Improving Fairness in Matching under Uncertainty

Piyushi Manupriya

LLMs Infer Protected Attributes Beyond Proxy Features

Dimitri Staufer

On Optimal Subgroups for Group Distributionally Robust Optimisation 

Anissa Alloula · Daniel McGowan · Bartlomiej W. Papiez

Demographic (Mis)Alignment of LLMs' Perception of Offensiveness 

Shayan Alipour · Indira Sen · Preetam Prabhu Srikar Dammu · Chris Choi · Mattia Samory · Tanu Mitra

Towards Better Fairness Metrics for Counter-Human Trafficking AI Initiatives

Vidya Sujaya · Pratheeksha Nair · Reihaneh Rabbany

Q-Morality: Quantum-Enhanced ActAdd-Guided Bias Reduction in LLMs 

Shardul Kulkarni

What's in a Query: Examining Distribution-based Amortized Fair Ranking

Aparna Balagopalan · Kai Wang · Asia Biega · Marzyeh Ghassemi