Lightnews — Scholar-powered news

Reposted by Karolina Stańczak

Gender Bias in NLP Workshop @genderbiasnlp.bsky.social · Aug 11

Thank you to everyone who joined the GeBNLP Workshop at #ACL2025! ✨

To help us improve future events, please share your feedback in our anonymous 5-minute survey. Your perspective is needed!

📝 Survey Link: forms.gle/mXtZ4mWUGSBN...

#GeBNLP #NLP

Feedback form for the Workshop on Gender Bias in NLP (GeBNLP) @ ACL

Thank you for participating in the 6th Workshop on Gender Bias in NLP! Your feedback is incredibly valuable and will help us improve future events. This anonymous form should take less than 5 minutes ...

forms.gle

1 1

Reposted by Karolina Stańczak

Gender Bias in NLP Workshop @genderbiasnlp.bsky.social · Aug 4

The Gender Bias in NLP workshop #ACL2025 is officially over, and we're buzzing with energy! ✨

A huge thank you to all our participants for a day packed with incredible discussions. You are the community we need 🙌

See you next time!

#GeBNLP #NLP

1 2

Reposted by Karolina Stańczak

Gender Bias in NLP Workshop @genderbiasnlp.bsky.social · Aug 1

It's time! ⏰ Organizers are ready to kick off the Gender Bias in NLP Workshop #ACL2025. Join us for a day of talks, posters, and discussions!

🗓️ Today, August 1
🕘 9 AM - 6:15 PM
📍 Hall C

#GeBNLP #NLP

1 4

Reposted by Karolina Stańczak

Gender Bias in NLP Workshop @genderbiasnlp.bsky.social · Jul 16

We are thrilled to announce our keynote speakers for the 6th Workshop on Gender Bias in NLP @ #ACL2025!

Please join us in welcoming:
🔹Anne Lauscher @a-lauscher.bsky.social
🔹Maarten Sap @maartensap.bsky.social

Full details: gebnlp-workshop.github.io/keynotes.html
See you on August 1! ☀️
#NLP #GeBNLP

5 15

Reposted by Karolina Stańczak

VLMs4All - CVPR 2025 Workshop @vlms4all.bsky.social · Jun 12

Our VLMs4All workshop is taking place today!
📅 on Thursday, June 12
⏲️ from 9AM CDT
🏛️in Room 104E

Join us today at @cvprconference.bsky.social for amazing speakers, posters, and a panel discussion on making VLMs more geo-diverse and culturally aware!

#CVPR2025

VLMs4All - CVPR 2025 Workshop @vlms4all.bsky.social · Jun 6

🗓️ Save the date! It's official: The VLMs4All Workshop at #CVPR2025 will be held on June 12th!

Get ready for a full day of speakers, posters, and a panel discussion on making VLMs more geo-diverse and culturally aware 🌐

Check out the schedule below!

2 4

Reposted by Karolina Stańczak

Ziling Cheng @ziling-cheng.bsky.social · Jun 6

Do LLMs hallucinate randomly? Not quite.

Our #ACL2025 (Main) paper shows that hallucinations under irrelevant contexts follow a systematic failure mode — revealing how LLMs generalize using abstract classes + context cues, albeit unreliably.

📎 Paper: arxiv.org/abs/2505.22630 1/n

1 18 46

Reposted by Karolina Stańczak

VLMs4All - CVPR 2025 Workshop @vlms4all.bsky.social · Jun 6

🗓️ Save the date! It's official: The VLMs4All Workshop at #CVPR2025 will be held on June 12th!

Get ready for a full day of speakers, posters, and a panel discussion on making VLMs more geo-diverse and culturally aware 🌐

Check out the schedule below!

3 4

Reposted by Karolina Stańczak

VLMs4All - CVPR 2025 Workshop @vlms4all.bsky.social · Apr 17

🚨 Deadline Extension Alert for #VLMs4All Challenges! 🚨

We have extended the challenge submission deadline
🛠️ New challenge deadline: Apr 22

Show your stuff in the CulturalVQA and GlobalRG challenges!
👉 sites.google.com/view/vlms4al...

Spread the word and keep those submissions coming! 🌍✨

2 2

Karolina Stańczak @karstanczak.bsky.social · Apr 15

Exciting release! AgentRewardBench offers that much-needed closer look at evaluating agent capabilities: automatic vs. human eval. Important findings here, especially on the popular LLM judges. Amazing work by @xhluca.bsky.social & team!

Xing Han Lu @xhluca.bsky.social · Apr 15

AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories

We are releasing the first benchmark to evaluate how well automatic evaluators, such as LLM judges, can evaluate web agent trajectories.

1 1 3

Reposted by Karolina Stańczak

VLMs4All - CVPR 2025 Workshop @vlms4all.bsky.social · Apr 9

🔔 Reminder & Call for #VLMs4All @ #CVPR2025!
Help shape the future of culturally aware & geo-diverse VLMs:
⚔️ Challenges: Deadline: Apr 15 🔗https://sites.google.com/view/vlms4all/challenges
📄 Papers (4pg): Deadline: Apr 22 🔗https://sites.google.com/view/vlms4all/call-for-papers
Join us!

VLMs4All - CVPR 2025 Workshop @vlms4all.bsky.social · Mar 14

📢Excited to announce our upcoming workshop - Vision Language Models For All: Building Geo-Diverse and Culturally Aware Vision-Language Models (VLMs-4-All) @CVPR 2025!
🌐 sites.google.com/view/vlms4all

2 4

Karolina Stańczak @karstanczak.bsky.social · Apr 7

Reviewers needed! 📢 The 6th Workshop on Gender Bias in NLP at #ACL2025 (Vienna, Aug 1st) is looking for you! Sign up to review:

forms.gle/VkPU4vS4EacE... #NLP

Karolina Stańczak @karstanczak.bsky.social · Mar 14

Excited to be organizing the VLMs4All workshop at #CVPR2025! 🎉
The workshop features fantastic speakers, a short-paper track, and two challenges, including one based on CulturalVQA. Don’t miss it!

2 10

Reposted by Karolina Stańczak

VLMs4All - CVPR 2025 Workshop @vlms4all.bsky.social · Mar 14

6/ 🤝 Thanks to our steering committees and co-organizers for their hard work in making the VLMs4All Workshop possible!

@meharbhatia.bsky.social @rabiul.bsky.social @spandanagella.bsky.social @sivareddyg.bsky.social @svansteenkiste.bsky.social @karstanczak.bsky.social

1 2 5

Reposted by Karolina Stańczak

Parishad BehnamGhader @parishadbehnam.bsky.social · Mar 12

Instruction-following retrievers can efficiently and accurately search for harmful and sensitive information on the internet! 🌐💣

Retrievers need to be aligned too! 🚨🚨🚨

Work done with the wonderful Nick and @sivareddyg.bsky.social

🔗 mcgill-nlp.github.io/malicious-ir/
Thread: 🧵👇

Exploiting Instruction-Following Retrievers for Malicious Information Retrieval

Parishad BehnamGhader, Nicholas Meade, Siva Reddy

mcgill-nlp.github.io

1 8 12

Karolina Stańczak @karstanczak.bsky.social · Mar 10

The potential for malicious misuse of LLM agents is a serious threat.

That's why we created SafeArena, a safety benchmark for web agents. See the thread and our paper for details: arxiv.org/abs/2503.04957 👇

2 9

Reposted by Karolina Stańczak

Arkil Patel @arkil.bsky.social · Mar 10

Llamas browsing the web look cute, but they are capable of causing a lot of harm!

Check out our new Web Agents ∩ Safety benchmark: SafeArena!

Paper: arxiv.org/abs/2503.04957

3 9

Karolina Stańczak @karstanczak.bsky.social · Mar 4

6/ @meharbhatia.bsky.social @hattie.bsky.social @nicolaspapernot.bsky.social @nicolaschapados.bsky.social @anamarasovic.bsky.social @ghadfield.bsky.social @sivareddyg.bsky.social
#AIAlignment #LLM #ResponsibleAI #NLP

6

Karolina Stańczak @karstanczak.bsky.social · Mar 4

5/ Read our full paper here: arxiv.org/abs/2503.00069
Let’s discuss! How should AI align with society? 🤝💡

Societal Alignment Frameworks Can Improve LLM Alignment

Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment. However, aligning LLMs remain...

arxiv.org

1 1 7

Karolina Stańczak @karstanczak.bsky.social · Mar 4

4/ We also discuss the role of participatory alignment, where diverse stakeholders help shape AI behavior rather than deferring solely to designers.

1 5

Karolina Stańczak @karstanczak.bsky.social · Mar 4

3/ Instead of perfecting rigid alignment objectives, we explore how LLMs can navigate uncertainty—a feature, not a flaw!

1 5

Karolina Stańczak @karstanczak.bsky.social · Mar 4

2/ We propose leveraging societal alignment frameworks to guide LLM alignment:
🔹 Social alignment: Modeling norms, values & cultural competence
🔹 Economic alignment: Fair reward mechanisms & collective decision-making
🔹 Contractual alignment: Legal principles for LLMs

1 5

Karolina Stańczak @karstanczak.bsky.social · Mar 4

1/ LLM alignment remains a challenge because human values are complex, dynamic, and often conflict with narrow optimization goals.

Existing methods like RLHF struggle with misspecified objectives.

1 4

Karolina Stańczak @karstanczak.bsky.social · Mar 4

📢New Paper Alert!🚀

Human alignment balances social expectations, economic incentives, and legal frameworks. What if LLM alignment worked the same way?🤔

Our latest work explores how social, economic, and contractual alignment can address incomplete contracts in LLM alignment🧵

2 13 28

Reposted by Karolina Stańczak

Gender Bias in NLP Workshop @genderbiasnlp.bsky.social · Feb 28

The 6th edition of the Gender Bias in Natural Language Processing (GeBNLP) workshop is happening at #ACL2025 in Vienna!

📢 Check out our Call for Papers! Find all the details on our website: gebnlp-workshop.github.io

We look forward to your submissions!

5 14

Reposted by Karolina Stańczak

Gender Bias in NLP Workshop @genderbiasnlp.bsky.social · Feb 28

Great news! We've extended the direct submission deadline to *April 18*, giving you more time to prepare your submissions 🚀

Check the new deadlines on our webpage: gebnlp-workshop.github.io/cfp.html

Call For Papers

The 6th Workshop on Gender Bias in Natural Language Processing at ACL 2025.

gebnlp-workshop.github.io

5 8