Indira Sen
@indiiigo.bsky.social
Junior Faculty at the University of Mannheim || Computational Social Science ∩ Natural Language Processing || Formerly at: RWTH, GESIS || she/her
indiiigo.github.io/
indiiigo.github.io/
Lots of great posters at the #wiknlp workshop at #ACL2025NLP
August 1, 2025 at 1:54 PM
Lots of great posters at the #wiknlp workshop at #ACL2025NLP
Great keynote by Matthias Gallé on multilinguality in LLMs with takeaways on how we have to go broader *and* deeper to achieve multilingual efficacy by covering local knowledge.
Struck by the industrialization of LLM research with LLM tech reports now having massive # authors. #wikinlp #acl2025nlp
Struck by the industrialization of LLM research with LLM tech reports now having massive # authors. #wikinlp #acl2025nlp
August 1, 2025 at 9:47 AM
Great keynote by Matthias Gallé on multilinguality in LLMs with takeaways on how we have to go broader *and* deeper to achieve multilingual efficacy by covering local knowledge.
Struck by the industrialization of LLM research with LLM tech reports now having massive # authors. #wikinlp #acl2025nlp
Struck by the industrialization of LLM research with LLM tech reports now having massive # authors. #wikinlp #acl2025nlp
Excellent panel on dataset papers using Wikipedia data and the importance and challenges of multilingual research.
Check out the dataset paper’s here: meta.m.wikimedia.org/wiki/NLP_for...
Check out the dataset paper’s here: meta.m.wikimedia.org/wiki/NLP_for...
August 1, 2025 at 9:15 AM
Excellent panel on dataset papers using Wikipedia data and the importance and challenges of multilingual research.
Check out the dataset paper’s here: meta.m.wikimedia.org/wiki/NLP_for...
Check out the dataset paper’s here: meta.m.wikimedia.org/wiki/NLP_for...
Incredible keynote by Monica Lam on creating LLM-powered research assistants.
One great example of NLP/wikipedia synergy is this tool that helps find inconsistencies in Wikipedia articles and fix them semi-automatically: wikifix.genie.stanford.edu
One great example of NLP/wikipedia synergy is this tool that helps find inconsistencies in Wikipedia articles and fix them semi-automatically: wikifix.genie.stanford.edu
August 1, 2025 at 8:06 AM
Incredible keynote by Monica Lam on creating LLM-powered research assistants.
One great example of NLP/wikipedia synergy is this tool that helps find inconsistencies in Wikipedia articles and fix them semi-automatically: wikifix.genie.stanford.edu
One great example of NLP/wikipedia synergy is this tool that helps find inconsistencies in Wikipedia articles and fix them semi-automatically: wikifix.genie.stanford.edu
Last day of #ACL2025NLP but there's still lots to do: attend the #WikiNLP workshop, where we explore how NLP and wikipedia can help each other!
We have amazing keynotes, discussions with Wikipedia editors, a panel + posters!
Details: meta.wikimedia.org/wiki/NLP_for...
Join us in room 2.31!
We have amazing keynotes, discussions with Wikipedia editors, a panel + posters!
Details: meta.wikimedia.org/wiki/NLP_for...
Join us in room 2.31!
August 1, 2025 at 5:43 AM
Last day of #ACL2025NLP but there's still lots to do: attend the #WikiNLP workshop, where we explore how NLP and wikipedia can help each other!
We have amazing keynotes, discussions with Wikipedia editors, a panel + posters!
Details: meta.wikimedia.org/wiki/NLP_for...
Join us in room 2.31!
We have amazing keynotes, discussions with Wikipedia editors, a panel + posters!
Details: meta.wikimedia.org/wiki/NLP_for...
Join us in room 2.31!
The current literature is divided about LLM representativeness: 29% say yes, 31% say no. We find the usual issues that plague CSS/NLP literature: outsized focus on the U.S, marginalized groups excluded from the analysis.
We find these issues are worse in papers that say LLMs are representative.
3/
We find these issues are worse in papers that say LLMs are representative.
3/
July 21, 2025 at 10:12 AM
The current literature is divided about LLM representativeness: 29% say yes, 31% say no. We find the usual issues that plague CSS/NLP literature: outsized focus on the U.S, marginalized groups excluded from the analysis.
We find these issues are worse in papers that say LLMs are representative.
3/
We find these issues are worse in papers that say LLMs are representative.
3/
We annotate different aspects of 211 papers including:
- usage context (e.g content analysis, advice)
- steering method (prompting, RLHF)
- demographics studied
- whether the paper reported LLM results across demographic groups & subgroups
- the paper's conclusion on LLM representativeness
2/
- usage context (e.g content analysis, advice)
- steering method (prompting, RLHF)
- demographics studied
- whether the paper reported LLM results across demographic groups & subgroups
- the paper's conclusion on LLM representativeness
2/
July 21, 2025 at 10:12 AM
We annotate different aspects of 211 papers including:
- usage context (e.g content analysis, advice)
- steering method (prompting, RLHF)
- demographics studied
- whether the paper reported LLM results across demographic groups & subgroups
- the paper's conclusion on LLM representativeness
2/
- usage context (e.g content analysis, advice)
- steering method (prompting, RLHF)
- demographics studied
- whether the paper reported LLM results across demographic groups & subgroups
- the paper's conclusion on LLM representativeness
2/
Do LLMs represent the people they're supposed simulate or provide personalized assistance to?
We review the current literature in our #ACL2025 Findings paper and investigating what researchers conclude about the demographic representativeness of LLMs:
osf.io/preprints/so...
1/
We review the current literature in our #ACL2025 Findings paper and investigating what researchers conclude about the demographic representativeness of LLMs:
osf.io/preprints/so...
1/
July 21, 2025 at 10:12 AM
Do LLMs represent the people they're supposed simulate or provide personalized assistance to?
We review the current literature in our #ACL2025 Findings paper and investigating what researchers conclude about the demographic representativeness of LLMs:
osf.io/preprints/so...
1/
We review the current literature in our #ACL2025 Findings paper and investigating what researchers conclude about the demographic representativeness of LLMs:
osf.io/preprints/so...
1/