grounded-bias-eval (Grounded Bias Eval)

stellaathena

authored a paper 2 months ago

Open Problems in Mechanistic Interpretability

Paper • 2501.16496 • Published Jan 27 • 19

stellaathena

authored a paper 3 months ago

Towards Best Practices for Open Datasets for LLM Training

Paper • 2501.08365 • Published Jan 14 • 60

shanchen

authored a paper 5 months ago

ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?

Paper • 2411.06469 • Published Nov 10, 2024 • 17

daniellebitt

authored a paper 5 months ago

ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?

Paper • 2411.06469 • Published Nov 10, 2024 • 17

shanchen

authored 2 papers 6 months ago

Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation

Paper • 2409.20385 • Published Sep 30, 2024

WorldMedQA-V: a multilingual, multimodal medical examination dataset for multimodal language models evaluation

Paper • 2410.12722 • Published Oct 16, 2024 • 5

daniellebitt

authored a paper 10 months ago

Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks

Paper • 2406.12066 • Published Jun 17, 2024 • 8

gallifantjack

authored a paper 10 months ago

Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks

Paper • 2406.12066 • Published Jun 17, 2024 • 8

shanchen

authored 3 papers 10 months ago

Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks

Paper • 2406.12066 • Published Jun 17, 2024 • 8

Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias

Paper • 2405.05506 • Published May 9, 2024 • 1

Measuring Pointwise $\mathcal{V}$-Usable Information In-Context-ly

Paper • 2310.12300 • Published Oct 18, 2023 • 1

stellaathena

authored a paper 10 months ago

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?

Paper • 2406.04391 • Published Jun 6, 2024 • 9

stellaathena

authored 8 papers about 1 year ago

Documenting Geographically and Contextually Diverse Data Sources: The BigScience Catalogue of Language Data and Resources

Paper • 2201.10066 • Published Jan 25, 2022

What Language Model to Train if You Have One Million GPU Hours?

Paper • 2210.15424 • Published Oct 27, 2022 • 2

Recasting Self-Attention with Holographic Reduced Representations

Paper • 2305.19534 • Published May 31, 2023 • 2

BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing

Paper • 2206.15076 • Published Jun 30, 2022 • 4

Grounded Bias Eval

AI & ML interests

grounded-bias-eval's activity

Open Problems in Mechanistic Interpretability

Towards Best Practices for Open Datasets for LLM Training

ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?

ClinicalBench: Can LLMs Beat Traditional ML Models in Clinical Prediction?

Wait, but Tylenol is Acetaminophen... Investigating and Improving Language Models' Ability to Resist Requests for Misinformation

WorldMedQA-V: a multilingual, multimodal medical examination dataset for multimodal language models evaluation

Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks

Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks

Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks

Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias

Measuring Pointwise $\mathcal{V}$-Usable Information In-Context-ly

Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?

On the Societal Impact of Open Foundation Models

Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets

Datasheet for the Pile

BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting

Documenting Geographically and Contextually Diverse Data Sources: The BigScience Catalogue of Language Data and Resources

What Language Model to Train if You Have One Million GPU Hours?

Recasting Self-Attention with Holographic Reduced Representations

BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing

AI & ML interests

Team members 7

grounded-bias-eval's activity