Shanshan Xu
@sxu3.bsky.social
PhD student @ TU Munich, Human-centered AI, Computational Social Science
https://sxu3.github.io/
https://sxu3.github.io/
📄 Check out the preprint: arxiv.org/pdf/2510.08524
We propose a prompt optimization framework that combines Monte Carlo Tree Search with a lightweight proxy prompt evaluator to efficiently discover better prompts for unfair ToS clause classification.
🧵2/2
We propose a prompt optimization framework that combines Monte Carlo Tree Search with a lightweight proxy prompt evaluator to efficiently discover better prompts for unfair ToS clause classification.
🧵2/2
arxiv.org
October 10, 2025 at 9:57 AM
📄 Check out the preprint: arxiv.org/pdf/2510.08524
We propose a prompt optimization framework that combines Monte Carlo Tree Search with a lightweight proxy prompt evaluator to efficiently discover better prompts for unfair ToS clause classification.
🧵2/2
We propose a prompt optimization framework that combines Monte Carlo Tree Search with a lightweight proxy prompt evaluator to efficiently discover better prompts for unfair ToS clause classification.
🧵2/2
This list is definitely incomplete, so feel free to share more relevant work!
While it’s great to see increasing engagement , I notice the terminology varies widely, 💬 human label variation, 💡perspectivism in NLP, and 📊 pluralistic human values 🤔 which is sometimes a bit confusing to me.
While it’s great to see increasing engagement , I notice the terminology varies widely, 💬 human label variation, 💡perspectivism in NLP, and 📊 pluralistic human values 🤔 which is sometimes a bit confusing to me.
July 31, 2025 at 2:50 PM
This list is definitely incomplete, so feel free to share more relevant work!
While it’s great to see increasing engagement , I notice the terminology varies widely, 💬 human label variation, 💡perspectivism in NLP, and 📊 pluralistic human values 🤔 which is sometimes a bit confusing to me.
While it’s great to see increasing engagement , I notice the terminology varies widely, 💬 human label variation, 💡perspectivism in NLP, and 📊 pluralistic human values 🤔 which is sometimes a bit confusing to me.
👏 Upcoming workshop: Perspectivist Approaches to NLP @EMNLP 2025
Focusing on non-aggregated datasets and multi-perspective modeling, with sessions on labeling, modeling, evaluation, and applications.
nlperspectives.di.unito.it
Focusing on non-aggregated datasets and multi-perspective modeling, with sessions on labeling, modeling, evaluation, and applications.
nlperspectives.di.unito.it
NLPerspectives – Perspectivist Approaches to NLP
nlperspectives.di.unito.it
July 31, 2025 at 2:50 PM
👏 Upcoming workshop: Perspectivist Approaches to NLP @EMNLP 2025
Focusing on non-aggregated datasets and multi-perspective modeling, with sessions on labeling, modeling, evaluation, and applications.
nlperspectives.di.unito.it
Focusing on non-aggregated datasets and multi-perspective modeling, with sessions on labeling, modeling, evaluation, and applications.
nlperspectives.di.unito.it
🔊 @vinodkpg.bsky.social – Invited Talk #NLP4PosImpact #ACL2025: “AI for the World of Many”
- Also a shout-out to the three talks above that inspired this thread!
sites.google.com/view/nlp4pos...
- Also a shout-out to the three talks above that inspired this thread!
sites.google.com/view/nlp4pos...
NLP for Positive Impact
Workshop Overview
sites.google.com
July 31, 2025 at 2:50 PM
🔊 @vinodkpg.bsky.social – Invited Talk #NLP4PosImpact #ACL2025: “AI for the World of Many”
- Also a shout-out to the three talks above that inspired this thread!
sites.google.com/view/nlp4pos...
- Also a shout-out to the three talks above that inspired this thread!
sites.google.com/view/nlp4pos...
🗣️ Lora Aroyo – Keynote #NeurIPS2023: “The Many Faces of Responsible AI”
- callling for recognizing the inherent ambiguity of content and the natural diversity of human perspectives, urging to "treat label disagreement as signal, not noise".
neurips.cc/virtual/2023...
- callling for recognizing the inherent ambiguity of content and the natural diversity of human perspectives, urging to "treat label disagreement as signal, not noise".
neurips.cc/virtual/2023...
NeurIPS Invited Talk The Many Faces of Responsible AINeurIPS 2023
neurips.cc
July 31, 2025 at 2:50 PM
🗣️ Lora Aroyo – Keynote #NeurIPS2023: “The Many Faces of Responsible AI”
- callling for recognizing the inherent ambiguity of content and the natural diversity of human perspectives, urging to "treat label disagreement as signal, not noise".
neurips.cc/virtual/2023...
- callling for recognizing the inherent ambiguity of content and the natural diversity of human perspectives, urging to "treat label disagreement as signal, not noise".
neurips.cc/virtual/2023...
🔈 @barbaraplank.bsky.social – Keynote #ACL2024: Are LLMs Narrowing Our Horizon? Let’s Embrace Variation in NLP!
- Introducing human label variation across the ML pipeline, and arguing that "embracing human label variation" is crucial for building trustworthy NLP
2024.aclweb.org/program/keyn...
- Introducing human label variation across the ML pipeline, and arguing that "embracing human label variation" is crucial for building trustworthy NLP
2024.aclweb.org/program/keyn...
Keynotes
ACL 2024 Conference Overview.
2024.aclweb.org
July 31, 2025 at 2:50 PM
🔈 @barbaraplank.bsky.social – Keynote #ACL2024: Are LLMs Narrowing Our Horizon? Let’s Embrace Variation in NLP!
- Introducing human label variation across the ML pipeline, and arguing that "embracing human label variation" is crucial for building trustworthy NLP
2024.aclweb.org/program/keyn...
- Introducing human label variation across the ML pipeline, and arguing that "embracing human label variation" is crucial for building trustworthy NLP
2024.aclweb.org/program/keyn...
📢 @verenarieser.bsky.social – Keynote #ACL2025: “Whose Gold? Re-imagining Alignment for Truly Beneficial AI”
- Discusseing the ethical and technical challenges of aligning AI when human values conflict, and proposes a three-level alignment pyramid as a path forward.
2025.aclweb.org/program/keyn...
- Discusseing the ethical and technical challenges of aligning AI when human values conflict, and proposes a three-level alignment pyramid as a path forward.
2025.aclweb.org/program/keyn...
July 31, 2025 at 2:50 PM
📢 @verenarieser.bsky.social – Keynote #ACL2025: “Whose Gold? Re-imagining Alignment for Truly Beneficial AI”
- Discusseing the ethical and technical challenges of aligning AI when human values conflict, and proposes a three-level alignment pyramid as a path forward.
2025.aclweb.org/program/keyn...
- Discusseing the ethical and technical challenges of aligning AI when human values conflict, and proposes a three-level alignment pyramid as a path forward.
2025.aclweb.org/program/keyn...
📜Poster: 14:00, Mon. 12.Aug
📢Oral: 16:00, Tue 13. Aug
Please drop by if you are interested in human label variation, pluralistic human values and NLP for LegalTech. Looking forward to insightful discussion. (2/2)
📢Oral: 16:00, Tue 13. Aug
Please drop by if you are interested in human label variation, pluralistic human values and NLP for LegalTech. Looking forward to insightful discussion. (2/2)
March 11, 2025 at 10:29 PM
📜Poster: 14:00, Mon. 12.Aug
📢Oral: 16:00, Tue 13. Aug
Please drop by if you are interested in human label variation, pluralistic human values and NLP for LegalTech. Looking forward to insightful discussion. (2/2)
📢Oral: 16:00, Tue 13. Aug
Please drop by if you are interested in human label variation, pluralistic human values and NLP for LegalTech. Looking forward to insightful discussion. (2/2)