Top Tweets for #20daysofresponsibleAI
How Gender Debiasing Affects Internal Model Representations, and Why It Matters (NAACL 2022)
Paper: https://t.co/8aBS6IJTXf
TLDR: Intrinsic bias metrics can correlate well with extrinsic metrics, with some changes, and can be more reliable
Day 20 of #20daysofresponsibleAI #NLP

Debiasing should be Good and Bad (ACL 2023)
Paper: https://t.co/erPvi2lqR6
TLDR: Proposes that if bias specifications are reversed, output of debiasing method should also get reversed & find current methods to be inconsistent with this
Day 19 of #20daysofresponsibleAI #NLProc

When Do Pre-Training Biases Propagate to Downstream Tasks? (EACL 2023)
Paper: https://t.co/q3rHBmeo3E
TLDR: Presence of high biases in pre-trained LMs can lead to high hallucination rates in downstream tasks!
Day 18 of #20daysofresponsibleAI #NLProc

Debiasing Masks: A New Framework for Shortcut Mitigation in NLU
Paper: https://t.co/084PECg9Ik
TLDR: Finds a subset of weights in the model which causes bias and prunes it to zero during inference. Requires no retraining!
Day 15 of #20daysofresponsibleAI #NLP

The Tail Wagging the Dog (ACL 2023 Outstanding Paper)
Paper: https://t.co/TvF55jnqgC
TLDR: Social bias benchmarks are very sensitive to small modifications e.g. synonymizing words in templates, resulting in very different bias values
Day 14 of #20daysofresponsibleAI #NLP

“How Biased are Your Features?” (FAccT 2023)
Paper: https://t.co/NEsKe1n6uf
TLDR: They measure the contribution of individual features to the overall bias of a classifier by fitting a set-additive model to the classifier
Day 13 of #20daysofresponsibleAI #NLP

Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model
Paper: https://t.co/pQm6io2W0F
TLDR: Biased machine translation models create gender-biased text from unbiased text, later used to train unbiased seq-to-seq model
Day 12 of #20daysofresponsibleAI #NLP

FairPrism: Evaluating Fairness-Related Harms in Text Generation (ACL 2023)
Paper: https://t.co/G5NF6GuXbr
TLDR: A new dataset for different types of harm. Addresses issues such as clearer coverage specification, annotators disagreement
Day 11 of #20daysofresponsibleAI #NLP

BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation (EMNLP 2022)
Paper: https://t.co/DKRcyOzCRX
TLDR: Pre-trained LM based metrics have higher bias on 6 sensitive attributes including race and gender
Day 10 of #20daysofresponsibleAI #NLP

NLPositionality: Characterizing Design Biases of Datasets and Models (ACL 2023 Outstanding Paper)
Paper: https://t.co/aMZud0oq74
TLDR: Authors impart their own identities, backgrounds into datasets and models which leads to design biases
Day 9 of #20daysofresponsibleAI #NLP

Tracking the Trails of Political Biases Leading to Unfair NLP Models (ACL 2023 Best Paper)
Paper: https://t.co/VjrMg7fcy3
TLDR: Using political spectrum theories they show political bias propagates from train data to LMs to downstream tasks
Day 8 of #20daysofresponsibleAI #NLP

Can Voice Assistants Be Microaggressors?
Paper: https://t.co/nxcXcV4TNK
TLDR: They found that high errors/biases in speech recognition harm marginalized groups more psychologically
Thanks @kimiwenzel for the suggestion and great work!
Day 7 of #20daysofresponsibleAI #NLProc

Stereotyping Norwegian Salmon
Paper: https://t.co/6dXlGvh54D
TLDR: Identified pitfalls in bias benchmark datasets about what they aim to measure vs how well they measure it 🧵⬇️
Thanks @shaily99 for the suggestion!
Day 6 of #20daysofresponsibleAI #NLProc #bias

Using Natural Sentences for Understanding Biases in Language Models
Paper: https://t.co/7mx76QU0GQ
TLDR: Quantifying bias is very sensitive to the design choice by authors. Real-world (Natural) sentences should be used instead 🧵⬇️
Day 4 of #20daysofresponsibleAI #NLP #bias
Last Seen Hashtags on Sotwe
nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit #nolimit filter:videos
Seen from France
muscleboy
nolimit nolimit filter:videos
Seen from Mexico
男娘
Seen from Korea
omegle
Seen from United Kingdom
おっぱいバニー学園
Seen from Japan
เรียวชาย
น้องหลุยส์
Seen from Thailand
熊大法学部
Seen from Japan
SONDAKİKA
Seen from Turkey
Most Popular Users

Elon Musk 
@elonmusk
240.5M followers

Barack Obama 
@barackobama
119.3M followers

Donald J. Trump 
@realdonaldtrump
111.7M followers

Cristiano Ronaldo 
@cristiano
110.2M followers

Narendra Modi 
@narendramodi
107M followers

Rihanna 
@rihanna
97.6M followers

NASA 
@nasa
92.1M followers

Justin Bieber 
@justinbieber
90.8M followers

KATY PERRY 
@katyperry
87.5M followers

Taylor Swift 
@taylorswift13
81.3M followers

Lady Gaga 
@ladygaga
72.8M followers

Kim Kardashian 
@kimkardashian
69.7M followers

Virat Kohli 
@imvkohli
69.6M followers

YouTube 
@youtube
68.7M followers

Bill Gates 
@billgates
63.8M followers

The Ellen Show
@theellenshow
62.5M followers

Neymar Jr 
@neymarjr
62.3M followers

CNN 
@cnn
61.9M followers

X 
@x
60.8M followers

Selena Gomez 
@selenagomez
60.6M followers
