Recent searches

No recent searches

Search options

Only available when logged in.
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Administered by:

Server stats:

605
active users

sigmoid.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.1

#nlproc

3 posts3 participants0 posts today
Continued thread
UKP Lab

Whether you're into cultural adaptation, reasoning chains, or robust anonymization, there’s something for every enthusiast!

So pour yourself a Verlängerter, grab a slice of Sachertorte, and get ready for some serious reading ☕🍰

See you in beautiful ! 🎶

(2/2)

#UKPLab#ACL#NLProc
Continued thread
The Data Therapist

7. Neural Machine Translation for Low-Resource Languages with Monolingual Data and Back-Translation
8. Multilingual Sarcasm Detection

Ideal turnaround: 4 weeks.
If you can review pls reply/DM with first+last name, email for reviews, and paper number(s) from the list above.

Please boost! Thanks!

#NLP
#NLProc
#LLM

Continued thread
UKP Lab

[...] enhance their robustness and relevance in real world applications.

A significant contribution to the field of context aware NLP and a milestone for Tilman personally and academically.

We wish him all the best for his next steps!

(3/3)

#NLProc#PhDDefense#ContextualAI
The Data Therapist

I’m looking for reviewers for these journal articles:
1. Phonology/IPA and LLM (not for English)
2. LLM math/logic abilities in diff cultural contexts
3. Prosody-syntax interact in low resource lang

Ideal turnaround: 4 weeks. If you can review pls reply/DM with first+last name & email for reviews.

Thanks!
#NLP #NLProc

Continued thread
LTG Oslo

In addition to the previously mentioned five papers: we are very proud for the LTG Master students who got their paper accepted to the ACL Fact Extraction and Verification Workshop (FEVER).
A big shout-out to Eivind Morris Bakke, Nora Winger Heggelund and their paper "(Fact) Check Your Bias"!
(parts of the paper originally constituted their exam work for our IN5550 course - Neural Methods in Natural Language Processing)

arxiv.org/abs/2506.21745

arXiv logo
arXiv.org(Fact) Check Your BiasAutomatic fact verification systems increasingly rely on large language models (LLMs). We investigate how parametric knowledge biases in these models affect fact-checking outcomes of the HerO system (baseline for FEVER-25). We examine how the system is affected by: (1) potential bias in Llama 3.1's parametric knowledge and (2) intentionally injected bias. When prompted directly to perform fact-verification, Llama 3.1 labels nearly half the claims as "Not Enough Evidence". Using only its parametric knowledge it is able to reach a verdict on the remaining half of the claims. In the second experiment, we prompt the model to generate supporting, refuting, or neutral fact-checking documents. These prompts significantly influence retrieval outcomes, with approximately 50\% of retrieved evidence being unique to each perspective. Notably, the model sometimes refuses to generate supporting documents for claims it believes to be false, creating an inherent negative bias. Despite differences in retrieved evidence, final verdict predictions show stability across prompting strategies. The code is available at: https://github.com/eibakke/FEVER-8-Shared-Task
#NLProc#Norway#UiO
Emiel van Miltenburg

Does anyone know whether there are automatic solutions to detect either "ghost references" (academic sources that do not actually exist) or improper citations (misrepresenting claims in earlier work)?

Would be a very interesting #nlp #nlproc challenge, and useful to flag potential fraud.

Judith van Stegeren

New blogpost:
Lessons from the first year of my PhD

I finished my PhD in computer science more than three years ago. Now that I have a little bit of mental distance from my PhD time, I'm going through my research diary to see if there's stuff in there that can be useful for other people.

Apparently I'm incapable of writing short-form texts, so here is part 1. ;)

judithvanstegeren.com/blog/les

www.judithvanstegeren.comLessons from the first year of my PhD - Judith van Stegeren
#academia#nlproc#phd
Continued thread
DW Innovation

(2/2)

Nicolas Patz is at the Europeana Conference in Warsaw, leading a panel on "Telling stories with tech: XR, 3D and AI for #CulturalHeritage".
This one will also feature EU-funded projects @transmixr, @presence, @Eureka3D-XR and 5D Culture.

Warsaw: pro.europeana.eu/page/conferen

If you happen to be in Dublin or Warsaw, don't hesitate to say hi & have a cup of coffee with the ReCos. ☕

Europeana PROEuropeana Conference | Europeana PROOur annual conference brings together hundreds of professionals working in and around cultural heritage
#AI#NLProc#XR
UKP Lab

🏛️ On June 4, our colleague Jonathan Tonglet will present our work "Protecting MLLMs against misleading visualizations" at the Royal Flemish Academy of Belgium for Science and the Arts – hosted at the Palace of the Academies in Brussels.
🔗 kvab.be/en/lentecyclus/more-me

The talk builds on a recently released paper in collaboration between UKP Lab (TU Darmstadt) and KU Leuven.
🔍 ukplab.github.io/arxiv2025-mis

We wish Jonathan insightful discussions and a great experience at this remarkable venue!

#NLProc
UKP Lab

Are LM more than their behavior? 🤔

Join our Conference on Language Modeling (COLM) workshop and explore the interplay between what LMs answer and what happens internally ✨

See you in Montréal 🍁

CfP: shorturl.at/sBomu
Page: shorturl.at/FT3fX
Reviewer Nomination: shorturl.at/Jg1BP

#nlproc#interpretability
*SEM

*SEM 2025 offers travel subsidies up to USD 750 for lead student authors with an accepted paper. Priority will be given to applicants from developing countries who would not have adequate financial support to attend in person. Please see starsem2025.github.io/subsidies for details. #NLP #NLProc

Travel Subsidies

The 14th Joint Conference on Lexical and Computational SemanticsTravel SubsidiesOfficial website of the 14th Joint Conference on Lexical and Computational Semantics
*SEM

*SEM 2025 final call for DIRECT SUBMISSIONS! starsem2025.github.io/cfp Direct submissions are due next week on May 30, 2025. We also accept papers via ARR commitment, due on August 22, 2025. Give your strong-but-overlooked ACL paper the second chance it deserves! 😉 #NLProc #NLP

Call for Papers

The 14th Joint Conference on Lexical and Computational SemanticsCall for PapersOfficial website of the 14th Joint Conference on Lexical and Computational Semantics
TrendingLive feeds
About