Shanshan Xu
@sxu3.bsky.social
PhD student @ TU Munich, Human-centered AI, Computational Social Science
https://sxu3.github.io/
https://sxu3.github.io/
🎉 Proud moment: my students’ paper get accepted at @nllpworkshop.bsky.social @EMNLP 2025
💪 so proud of the students' dedication and growth throughout the project
🚩 Also a milestone for me - my first last-author paper
🌱 It’s been a new and interesting experience: part author, part reviewer 🧵1/2
💪 so proud of the students' dedication and growth throughout the project
🚩 Also a milestone for me - my first last-author paper
🌱 It’s been a new and interesting experience: part author, part reviewer 🧵1/2
October 10, 2025 at 9:57 AM
🎉 Proud moment: my students’ paper get accepted at @nllpworkshop.bsky.social @EMNLP 2025
💪 so proud of the students' dedication and growth throughout the project
🚩 Also a milestone for me - my first last-author paper
🌱 It’s been a new and interesting experience: part author, part reviewer 🧵1/2
💪 so proud of the students' dedication and growth throughout the project
🚩 Also a milestone for me - my first last-author paper
🌱 It’s been a new and interesting experience: part author, part reviewer 🧵1/2
📣New adventure! 🇩🇰Just joined Uni Copenhagen as a postdoc with @danielhers.bsky.social. I'll be working on LegalNLP & human-centered AI🤗 Excited for the research, collaborations, and much hygge & lykke✨fun fact: I stumbled on the book lying on the street in Munich just before applying the position 🔮⭐️
September 1, 2025 at 1:01 PM
📣New adventure! 🇩🇰Just joined Uni Copenhagen as a postdoc with @danielhers.bsky.social. I'll be working on LegalNLP & human-centered AI🤗 Excited for the research, collaborations, and much hygge & lykke✨fun fact: I stumbled on the book lying on the street in Munich just before applying the position 🔮⭐️
Super excited to see the growing interest and awareness in diversity, variation, and pluralistic alignment in the NLP community! ✨ 🪩
Below 🧵 are some keynote talks and workshops that highlight this important direction 🤸
Below 🧵 are some keynote talks and workshops that highlight this important direction 🤸
July 31, 2025 at 2:50 PM
Super excited to see the growing interest and awareness in diversity, variation, and pluralistic alignment in the NLP community! ✨ 🪩
Below 🧵 are some keynote talks and workshops that highlight this important direction 🤸
Below 🧵 are some keynote talks and workshops that highlight this important direction 🤸
I'll present our work w/ @santosh-tyss.bsky.social
@yanai.bsky.social @barbaraplank.bsky.social on LLMs memorization of distributions of political leanings in their pretraining data! Catch us at L2M2 workshop @l2m2workshop.bsky.social #ACL2025 tmrw
📆 Aug 1, 14:00–15:30 📑 arxiv.org/pdf/2502.18282
@yanai.bsky.social @barbaraplank.bsky.social on LLMs memorization of distributions of political leanings in their pretraining data! Catch us at L2M2 workshop @l2m2workshop.bsky.social #ACL2025 tmrw
📆 Aug 1, 14:00–15:30 📑 arxiv.org/pdf/2502.18282
July 31, 2025 at 8:41 AM
I'll present our work w/ @santosh-tyss.bsky.social
@yanai.bsky.social @barbaraplank.bsky.social on LLMs memorization of distributions of political leanings in their pretraining data! Catch us at L2M2 workshop @l2m2workshop.bsky.social #ACL2025 tmrw
📆 Aug 1, 14:00–15:30 📑 arxiv.org/pdf/2502.18282
@yanai.bsky.social @barbaraplank.bsky.social on LLMs memorization of distributions of political leanings in their pretraining data! Catch us at L2M2 workshop @l2m2workshop.bsky.social #ACL2025 tmrw
📆 Aug 1, 14:00–15:30 📑 arxiv.org/pdf/2502.18282
Congratulations Dr. @LijunLyu for a fantastic PhD defense 👏🎓🎉
March 11, 2025 at 10:19 PM
Congratulations Dr. @LijunLyu for a fantastic PhD defense 👏🎓🎉
Catch me in oral talk on split voted case and human-model alignment in 🪷loutus suit 5-7🪷16:00⌚Session: Interpretability and model analysis (15 minutes to go) #ACL2024
March 11, 2025 at 10:19 PM
Catch me in oral talk on split voted case and human-model alignment in 🪷loutus suit 5-7🪷16:00⌚Session: Interpretability and model analysis (15 minutes to go) #ACL2024
Poster session now!📜How aligned is the model 🤖with human 👀on the split voted cases, which are often social - politically controversial? Come to visit us at poster 1⃣2⃣4⃣ in CCA1 #ACL2024
March 11, 2025 at 10:19 PM
Poster session now!📜How aligned is the model 🤖with human 👀on the split voted cases, which are often social - politically controversial? Come to visit us at poster 1⃣2⃣4⃣ in CCA1 #ACL2024
✈️ On my way to #ACL2024 in Bangkok🇹🇭 I'll present our work 🔍Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification 🔍with @TYSSSantosh2 Oana @barbara_plank @matgrabmair (1/2🧵)
📰 https://dir.lat/EzcxUr
📰 https://dir.lat/EzcxUr
March 11, 2025 at 10:24 PM
✈️ On my way to #ACL2024 in Bangkok🇹🇭 I'll present our work 🔍Through the Lens of Split Vote: Exploring Disagreement, Difficulty and Calibration in Legal Case Outcome Classification 🔍with @TYSSSantosh2 Oana @barbara_plank @matgrabmair (1/2🧵)
📰 https://dir.lat/EzcxUr
📰 https://dir.lat/EzcxUr
I really enjoyed the poster session today at #emnlp23. Thank you all for stopping by 😀 (Interestingly, we all seem to agree on the human disagreement) @mumblamb @barbara_plank @TYSSSantosh2 @LeonStaufer
March 11, 2025 at 10:30 PM
I really enjoyed the poster session today at #emnlp23. Thank you all for stopping by 😀 (Interestingly, we all seem to agree on the human disagreement) @mumblamb @barbara_plank @TYSSSantosh2 @LeonStaufer
Happening now! Come to the Law Law Land in Aquarius 2 for 🐤BoF session of 🪶 NLP on legal text ⚖️ #EMNLP2023
March 11, 2025 at 10:35 PM
Happening now! Come to the Law Law Land in Aquarius 2 for 🐤BoF session of 🪶 NLP on legal text ⚖️ #EMNLP2023
⏲️ 14:00 - 15:30 join us at the🦜BoF 🪶session at Aquarius 2 📢No matter you are an NLP researcher on #LLMref="/hashtag/LLM" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link">#LLM or a lawyer with an #LLM feel free to join everything under Law, Language and LLM 3/3
March 11, 2025 at 10:45 PM
⏲️ 14:00 - 15:30 join us at the🦜BoF 🪶session at Aquarius 2 📢No matter you are an NLP researcher on #LLMref="/hashtag/LLM" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link">#LLM or a lawyer with an #LLM feel free to join everything under Law, Language and LLM 3/3
TUM LegalTech Rundown today (8. Dec)@EMNLP23: 11- 12:30 We’ll present our poster“From Dissonance to Insights: Dissecting Disagreements ...............” at East Foyer. Come and stop by to chat about Human Label Variation, Disagreement and LegalNLP 1/3🧵
March 11, 2025 at 10:35 PM
TUM LegalTech Rundown today (8. Dec)@EMNLP23: 11- 12:30 We’ll present our poster“From Dissonance to Insights: Dissecting Disagreements ...............” at East Foyer. Come and stop by to chat about Human Label Variation, Disagreement and LegalNLP 1/3🧵
We observe that, although article-aware models outperform the fact-only variants in classification, their alignment with the experts remains similarly low. In other words, the models might be right for the wrong reasons. 4/6
March 11, 2025 at 10:55 PM
We observe that, although article-aware models outperform the fact-only variants in classification, their alignment with the experts remains similarly low. In other words, the models might be right for the wrong reasons. 4/6
We compare integrated gradient focus with the experts’ rationales across (i) fact-only models which rely solely on case facts, and (ii) article-aware models which combine case facts and convention article text to predict the case outcome. 3/6
March 11, 2025 at 10:50 PM
We compare integrated gradient focus with the experts’ rationales across (i) fact-only models which rely solely on case facts, and (ii) article-aware models which combine case facts and convention article text to predict the case outcome. 3/6
We characterize the sources of expert disagreements and build a two-level taxonomy. Our experiments show that disagreements mainly stem from underspecification of the legal context, which poses challenges given the typically limited granularity and noise in ECHR case metadata 2/6
March 11, 2025 at 10:45 PM
We characterize the sources of expert disagreements and build a two-level taxonomy. Our experiments show that disagreements mainly stem from underspecification of the legal context, which poses challenges given the typically limited granularity and noise in ECHR case metadata 2/6
1 dataset 🗂️, 2 lawyers🧑⚖️, 3 models 🤖 and lots of disagreement ⁉️Our #emnlp2023 paper presents 🪩RaVE🪩: a dataset for Rationale Variation in ECHR, which is obtained from two legal experts and we observe limited agreement between models and experts🔗https://dir.lat/hk2rcy...
March 11, 2025 at 10:35 PM
1 dataset 🗂️, 2 lawyers🧑⚖️, 3 models 🤖 and lots of disagreement ⁉️Our #emnlp2023 paper presents 🪩RaVE🪩: a dataset for Rationale Variation in ECHR, which is obtained from two legal experts and we observe limited agreement between models and experts🔗https://dir.lat/hk2rcy...
Yesterday I had the great honor of organizing and moderating an event, aiming to encourage women in NLP to share experiences and build networks. Panelist @barbara_plank from @MaiNLPlab @CisLmu, Annette Green from @microsoft and Claudia Schulze chaired insightful panel discussions
March 11, 2025 at 10:40 PM
Yesterday I had the great honor of organizing and moderating an event, aiming to encourage women in NLP to share experiences and build networks. Panelist @barbara_plank from @MaiNLPlab @CisLmu, Annette Green from @microsoft and Claudia Schulze chaired insightful panel discussions
5/ We would like to express sincere gratitude to CONVALID Analytics for sponsoring the venue and food for our event. I am happy to be organizing the event with a great team 🥨@MunichNlp and amazing mentors @LAWeissweiler , @iamdddaryna , Verena Blaschke, Ekaterina Artemova
March 11, 2025 at 11:15 PM
5/ We would like to express sincere gratitude to CONVALID Analytics for sponsoring the venue and food for our event. I am happy to be organizing the event with a great team 🥨@MunichNlp and amazing mentors @LAWeissweiler , @iamdddaryna , Verena Blaschke, Ekaterina Artemova
Day 1 at #xaiss eXplainable AI Summer School in Delft. Great lectures and amazing socials 🪩 glad to catch up with old friends and meet new ppl 🤗
March 11, 2025 at 10:50 PM
Day 1 at #xaiss eXplainable AI Summer School in Delft. Great lectures and amazing socials 🪩 glad to catch up with old friends and meet new ppl 🤗