Who's Who of AI

Miryam de Lhoneux

398 trust researcher @mdlhx.bsky.social · 3,568 followers
AI research NLP & language Safety & security
Why they matter

Researcher with public evidence across AI research, NLP & language, Safety & security.

AI signals
4
past 30d
Sources
3
distinct domains
Discussões
5
past 30d
Latest signal
20h ago
View every signal from Miryam de Lhoneux →
NLP assistant prof at KU Leuven, PI @lagom-nlp.bsky.social. I like syntax more than most people. Also multilingual NLP, interpretability, mountains and beer. (She/her)
What they're sharing

Articles & links

↻ Miryam de Lhoneux reposted
LAGoM NLP @lagom-nlp.bsky.social

July has been a good month: * Our ACL paper about Wikipedia quality was awarded an SAC highlight (aclanthology.org/2026.acl-lon...) * @colemanhaley.bsky.social joined our lab as a postdoc * Coleman's CoNLL paper about impossible languages won the best paper award (aclanthology…

How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLP aclanthology.org
AI Weekly's analysis →
  • MinHash deduplication removes 28.33% of all non-English Wikipedia articles, mostly from editions known to be dominated by bot-generated content.
  • Cited bot-content shares reach 99% for Cebuano, 90% for Waray and 68% for Swedish Wikipedia, per an Alshahrani et al. 2023 estimate.
  • Language models trained on the filtered Wikipedia largely match or outperform those trained on the raw dumps, with the biggest gains on lower-quality editions.
Read full analysis →
 View on Bluesky →
↻ Miryam de Lhoneux reposted
EACL 2027 @eaclmeeting.bsky.social

⚠️⚠️⚠️ Attention #NLProc researchers, the #EACL2027 deadline is only a week away! Submit your best work by August 3d AoE, best of luck! 💪 📝CfP: 2027.eacl.org/calls/papers/ 📬 submit here: openreview.net/group?id=acl...

ACL ARR 2026 August openreview.net View on Bluesky →
↻ Miryam de Lhoneux reposted
LAGoM NLP @lagom-nlp.bsky.social

July has been a good month: * Our ACL paper about Wikipedia quality was awarded an SAC highlight (aclanthology.org/2026.acl-lon...) * @colemanhaley.bsky.social joined our lab as a postdoc * Coleman's CoNLL paper about impossible languages won the best paper award (aclanthology…

When transformers learn “impossible” languages, what do they learn? aclanthology.org
AI Weekly's analysis →
  • Janarthan, Haley and Goldwater train GPT-2 style models on perturbed 'impossible' variants of English and probe them beyond perplexity.
  • On BLiMP minimal pairs the models show only gradual degradation on impossible languages, mediated by information locality.
  • Generation is where the bias lives: the same models produce substantially fewer high-quality sentences at longer lengths.
Read full analysis →
 View on Bluesky →
Their own posts

Recent commentary

some students start to sound like LLMs in their paper and pen exams

View on Bluesky · ♥ 8 ↻ 0 ↩ 0 · 48d ago
Their network

In Miryam de Lhoneux's orbit

Center = Miryam de Lhoneux. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.