Dirk Hovy
@dirkhovy.bsky.social
๐ค 640
๐ฅ 336
๐ 54
Professor
@milanlp.bsky.social
for
#NLProc
, compsocsci,
#ML
Also at
http://dirkhovy.com/
pinned post!
๐จ(Software) Update: In my PhD, I had a side project to fix an annoying problem: when you ask 5 people to label the same thing, you often get different answers. But in ML (and lots of other analyses), you still need a single aggregated answer. Using the majority vote is easyโbut often wrong. 1/N
loading . . .
GitHub - dirkhovy/MACE: Multi-Annotator Competence Estimation tool
Multi-Annotator Competence Estimation tool. Contribute to dirkhovy/MACE development by creating an account on GitHub.
https://github.com/dirkhovy/MACE
5 months ago
6
75
14
reposted by
Dirk Hovy
MilaNLP Lab
8 days ago
#MemoryMonday
#NLProc
Uma, A. N. et al. examine AI model training in 'Learning from Disagreement: A Survey'. Disagreement-handling methods' performance is shaped by evaluation methods & dataset traits.
www.jair.org/index.php/ja...
loading . . .
https://www.jair.org/index.php/jair/article/download/12752/26751
0
3
2
reposted by
Dirk Hovy
MilaNLP Lab
11 days ago
@taniseceron.bsky.social
is presenting her work about political content in pre-training and post-training data at the AI & Society conference.
#AIandSociety
#NLProc
0
17
5
On the heels of a fantastic Dagstuhl seminar on Social Intelligence in AI (thx,
@jennhu.bsky.social
,
@maartensap.bsky.social
,
@tomerullman.bsky.social
, & Lucie Flek), a callback to how we thought about this 5 years ago.
add a skeleton here at some point
11 days ago
0
6
2
reposted by
Dirk Hovy
MilaNLP Lab
about 2 months ago
#TBT
#NLProc
'Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview' by Shah, Schwartz, Dirk Hovy (2020). Dive into their mathematical NLP bias framework, its origins, impacts, and types.
#AIEthics
aclanthology.org/2020.acl-mai...
loading . . .
https://aclanthology.org/2020.acl-main.468v2
0
5
2
reposted by
Dirk Hovy
MilaNLP Lab
about 1 month ago
#TBT
#NLProc
Check out 'Helpful or Hierarchical?' by Rashid, F. et al advocating better non-binary representation in tech.
#Inclusion
loading . . .
Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success
Farzana Rashid, Tommaso Fornaciari, Dirk Hovy, Eduardo Blanco, Fernando Vega-Redondo. Findings of the Association for Computational Linguistics: EMNLP 2020. 2020.
https://aclanthology.org/2020.findings-emnlp.214
0
3
2
reposted by
Dirk Hovy
MilaNLP Lab
about 1 month ago
aclanthology.org/2021.finding...
loading . . .
โWe will Reduce Taxesโ - Identifying Election Pledges with Language Models
Tommaso Fornaciari, Dirk Hovy, Elin Naurin, Julia Runeson, Robert Thomson, Pankaj Adhikari. Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. 2021.
https://aclanthology.org/2021.findings-acl.301/
0
4
2
reposted by
Dirk Hovy
MilaNLP Lab
about 1 month ago
#MemoryModay
#NLProc
'We will Reduce Taxes' - Identifying Election Pledges with Language Models' by Fornaciari et al. makes election promise tracking effortless with neural models.
1
4
2
reposted by
Dirk Hovy
MilaNLP Lab
about 1 month ago
#TBT
#NLProc
Bianchi, Terragni & Dirk Hovy present a smarter technique for topic modeling. Their method uses contextual embeddings for clear, meaningful word clusters, transforming how we interpret large text collections.
loading . . .
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence
Federico Bianchi, Silvia Terragni, Dirk Hovy. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Languageโฆ
https://aclanthology.org/2021.acl-short.96
0
4
2
reposted by
Dirk Hovy
Anna Rogers
about 2 months ago
I see lots of posts about the automated reviewing at AAAI. Just to be contrarian: here's a counter from
@dirkhovy.bsky.social
's team:
openreview.net/forum?id=cJh...
loading . . .
Stop Automating Peer Review Without Rigorous Evaluation
As AI systems increasingly generate scientific knowledge, the human ability to critically evaluate research becomes more important, not less. Yet large language models offer a tempting solution to...
https://openreview.net/forum?id=cJhlquXIuS
1
13
4
reposted by
Dirk Hovy
MilaNLP Lab
about 1 month ago
#MemoryModay
#NLProc
'Visualizing Regional Language Variation Across Europe on Twitter' by Dirk Hovy et al. uncovers language differences across Europe with stunning visuals. Language is art!
#Linguistics
link.springer.com/referencewor...
loading . . .
Visualizing Regional Language Variation Across Europe on Twitter
Geotagged Twitter data allows us to investigate correlations of geographic language variation, both at an interlingual and intralingual level. Based on data-driven studies of such relationships, thisโฆ
https://link.springer.com/referenceworkentry/10.1007/978-3-030-02438-3_175
0
4
3
reposted by
Dirk Hovy
EACL 2027
about 2 months ago
๐ขโ ๏ธ IMPORTANT DATE CORRECTION: the ARR deadline for EACL 2027 is Aug 3, 2026 (not Aug 6 as previously announced). EACL is earlier than usual in '27, so this is the only viable ARR cycle! ๐ All areas of CL/NLP + related fields welcome. Full CfP coming soon.
#NLProc
#EACL2027
add a skeleton here at some point
0
14
12
reposted by
Dirk Hovy
Joachim Baumann
about 2 months ago
Can you boost your AI review scores by asking an LLM to rewrite your paper? Yes! We call it paper laundering Our
@icmlconf.bsky.social
spotlight paper argues current AI reviewers aren't ready to automate peer review, and outlines what a science of peer review automation should look like ๐งต๐
#ICML2026
4
39
14
reposted by
Dirk Hovy
ACL Rolling Review (ARR)
2 months ago
๐๏ธ The ARR March review deadline is approaching: April 20 AoE. Finishing up your review? Run it through REVAS, a peer review assistant that makes your suggestions more actionable, flags unsupported claims, and grounds your feedback in the paper. ๐
revas.mbzuai.ac.ae
loading . . .
REVAS โ AI-Powered Peer Review Feedback for Academics
REVAS analyzes the weakness section of your peer review, scoring each paragraph on actionability, helpfulness, grounding, and verifiability.
https://revas.mbzuai.ac.ae
0
3
5
reposted by
Dirk Hovy
MilaNLP Lab
3 months ago
#MemoryModay
#NLProc
Uma et al. (2020) highlights 'A Case for Soft Loss Functions' efficacy using soft labels & crowd annotations in AI tasks, outshining top-tier methods.
loading . . .
https://ojs.aaai.org/index.php/HCOMP/article/download/7478/7255/10850
0
5
3
reposted by
Dirk Hovy
3 months ago
To accommodate ACL decisions, we are further extending the commitment deadline for pre-reviewed ARR submissions to April 7!
add a skeleton here at some point
0
4
4
reposted by
Dirk Hovy
ACL
3 months ago
The paper acceptance notifications will be out by the 6th of April, AoE. The PCs are working hard throughout the holiday season to finalize the decisions. Apologies for the delay!
0
4
6
reposted by
Dirk Hovy
David Lazer
3 months ago
The deadline for submission to the Political Networks conference is this Friday. It's taking place Aug 4-7, in Manchester.
sites.google.com/view/confpol...
loading . . .
2026 Manchester
Application and registration
https://sites.google.com/view/confpolinetworks/
0
3
2
reposted by
Dirk Hovy
MilaNLP Lab
3 months ago
#TBT
#NLProc
'[MASK]? Making Sense of Language-Specific BERT Models' by
@deboranozza.bsky.social
, Bianchi &
@dirkhovy.bsky.social
(2020), explores language-specific vs universal BERT models.
loading . . .
https://arxiv.org/pdf/2003.02912
0
5
2
I realized how much DMing is like being a professor/chairing a committee. You: - make a brilliant plan for 2+ hours of fun - prep lots of material - immediately get derailed by questions/arguments/etc. - keep it together to make the most of the time together - end up not using most of the material
3 months ago
1
6
1
reposted by
Dirk Hovy
MilaNLP Lab
3 months ago
#MemoryModay
#NLProc
'Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers,' by Nguyen &
@dirkhovy.bsky.social
decodes speaker reviews for user preferences using topic models. Domain knowledge needed for market analysis.
loading . . .
Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers
Hanh Nguyen, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.
https://aclanthology.org/D19-5510
0
5
2
reposted by
Dirk Hovy
Alexander Hoyle
3 months ago
I wrote a blog post on my experience using AI for slide generation Basic idea: write your lecture notes first, then prompt the LLM to produce corresponding slides in reveal.js (h/t
@chenhaotan.bsky.social
). I'm picky about my slides but was happy with the results!
alexanderhoyle.com/posts/ai-sli...
4
63
10
reposted by
Dirk Hovy
MilaNLP Lab
3 months ago
#TBT
#NLProc
Fornaciari,
@dirkhovy.bsky.social
's 'Identifying Linguistic Areas for Geolocation' explores using social media writing for geolocation via Point-to-City (P2C).
loading . . .
Identifying Linguistic Areas for Geolocation
Tommaso Fornaciari, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.
https://aclanthology.org/D19-5530
0
4
2
Wish I could be at
@eaclmeeting.bsky.social
, but the lab is well represetned. If you are there, come and say hi!
add a skeleton here at some point
3 months ago
0
2
1
reposted by
Dirk Hovy
MilaNLP Lab
3 months ago
#MemoryModay
#NLProc
'Dense Node Representation for Geolocation' by Fornaciari &
@dirkhovy.bsky.social
reveals efficient geolocation methods using node2vec & doc2vec models. Greater network size, less parameters.
loading . . .
Dense Node Representation for Geolocation
Tommaso Fornaciari, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.
https://aclanthology.org/D19-5529
0
4
2
reposted by
Dirk Hovy
MilaNLP Lab
3 months ago
#TBT
#NLProc
'Geolocation with Attention-Based Multitask Learning Models' by Tommaso Fornaciari,
@dirkhovy.bsky.social
(2019) reveals how online political talks can become one-sided. Breaking out of our bubbles!
#SocialMedia
loading . . .
Geolocation with Attention-Based Multitask Learning Models
Tommaso Fornaciari, Dirk Hovy. Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019). 2019.
https://aclanthology.org/D19-5528
0
3
2
reposted by
Dirk Hovy
Taha Yasseri
3 months ago
Chpater 8:
@dirkhovy.bsky.social
, M Gerondeau & J Globisz on text data and natural language processing. A very useful chapter on why text is such a rich source for CSS, and how NLP can help with exploration, prediction, and generation; if used thoughtfully and with clear research goals.
add a skeleton here at some point
2
4
3
reposted by
Dirk Hovy
Jeremy Foote
3 months ago
Just read this great piece -
paulgp.com/2026/03/16/r...
by
@paulgp.com
and it got me thinking. It feels like there is a lot of moral(?) ambiguity and ambivalence around the use of LLMs for academics. So far, I've avoided having LLMs do basically any of my research writing ...
loading . . .
https://paulgp.com/2026/03/16/research-in-time-of-ai.htmlIt
2
6
2
reposted by
Dirk Hovy
MilaNLP Lab
3 months ago
#MemoryModay
#NLProc
'Make Natural Language Processing About People Again' by
@dirkhovy.bsky.social
(2018) uncovers how AI models portray different religions and emotions.
#AIEthics
loading . . .
The Social and the Neural Network: How to Make Natural Language Processing about People again
Dirk Hovy. Proceedings of the Second Workshop on Computational Modeling of Peopleโs Opinions, Personality, and Emotions in Social Media. 2018.
https://aclanthology.org/W18-1106
0
7
5
reposted by
Dirk Hovy
MilaNLP Lab
4 months ago
#MemoryModay
#NLProc
'Comparing Bayesian Models of Annotation' by Paun et al. dives into corpus annotation, evaluating six models' predictiveness and accuracy. Essential for navigating annotators and item difficulties.
loading . . .
Comparing Bayesian Models of Annotation
Silviu Paun, Bob Carpenter, Jon Chamberlain, Dirk Hovy, Udo Kruschwitz, Massimo Poesio. Transactions of the Association for Computational Linguistics, Volume 6. 2018.
https://aclanthology.org/Q18-1040
0
8
2
reposted by
Dirk Hovy
MilaNLP Lab
3 months ago
๐ข Call for Abstracts! Towards a Safer Web for Women (co-located with
#WebSci26
) ๐ Braunschweig ๐ฉ๐ช | 26 May 2026 Theme: Preventive approaches to womenโs online safety ๐ Deadline: 27 March 2026 ๐
forms.gle/tYheEgSwGecf...
๐
tsww26.github.io
0
5
5
reposted by
Dirk Hovy
MilaNLP Lab
3 months ago
#TBT
#NLProc
'Predicting News Headline Popularity' by Lamprinidis, Hardt,
@dirkhovy.bsky.social
(2018) shows neural networks perform similar to Logistic Regression in prediction.
loading . . .
Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning
Sotiris Lamprinidis, Daniel Hardt, Dirk Hovy. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018.
https://aclanthology.org/D18-1068
0
3
2
One of my favorite studies of the last few years! Great read (albeit with a side of worrying implications for surveys)
add a skeleton here at some point
3 months ago
0
6
2
One of my favorite interdisciplinary projects (with
@questoph.bsky.social
). Plus: colorful maps!
add a skeleton here at some point
4 months ago
0
3
1
reposted by
Dirk Hovy
MilaNLP Lab
4 months ago
#TBT
#NLProc
'Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting' by
@dirkhovy.bsky.social
and Christoph Purschke (2018) highlights how social class and background impact technology performance.
#TechInclusion
loading . . .
Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting
Dirk Hovy, Christoph Purschke. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018.
https://aclanthology.org/D18-1469
0
3
4
reposted by
Dirk Hovy
Tiancheng Hu
4 months ago
4/7 We argue these aren't separate bugs. They're four facets of the same problem: ๐ด Probabilistic โ can't match requested distributions ๐ Semantic โ confidence โ correctness ๐ต Distributional โ output diversity collapse ๐ข Metacognitive โ can't assess its own competence
1
2
1
reposted by
Dirk Hovy
Tiancheng Hu
4 months ago
1/7 ๐งต The GPT-4 technical report featured detailed calibration curves. Since then, not a single major model release has reported calibration. The field quietly stopped measuring whether models know what they don't know. Our new position paper argues this is a mistake. Here's why.
1
8
2
reposted by
Dirk Hovy
MilaNLP Lab
4 months ago
We were thrilled to host
@mtutek.bsky.social
at our lab last week. His talk "From Internals to Integrity: How Insights into Transformer LMs Improve Safety, Interpretability, and Explanation Faithfulness" led to great discussions! ๐
#Transformers
#AISafety
#ExplainableAI
#MLResearch
#NLProc
0
18
3
reposted by
Dirk Hovy
EACL 2027
4 months ago
Call for Virtual Registration Subsidies for
#EACL26
๐ โ ๏ธ Not for paper registrants ๐ Apply by Feb 27, 2026 (AoE) ๐ฉ Decisions by Mar 2, 2026
2026.eacl.org/calls/virtua...
Donโt register before hearing back if you apply!
loading . . .
Call for Virtual Registration Subsidies
Official website for the 2026 Conference of the European Chapter of the Association for Computational Linguistics
https://2026.eacl.org/calls/virtual-subsidies/
1
6
5
reposted by
Dirk Hovy
UKP Lab
4 months ago
๐๐งฉ ๐๐ฒ๐๐ผ๐ป๐ฑ ๐๐ฒ๐ป๐ฐ๐ต๐บ๐ฎ๐ฟ๐ธ๐: ๐๐ผ๐ ๐๐ผ ๐๐๐ฎ๐น๐๐ฎ๐๐ฒ ๐ ๐ฒ๐ป๐๐ฎ๐น ๐๐ฒ๐ฎ๐น๐๐ต ๐๐ ๐ฅ๐ฒ๐๐ฝ๐ผ๐ป๐๐ถ๐ฏ๐น๐ AI for mental health is a high-stakes area: its evaluation needs to meet the highest expectations. The new preprint ๐๐ฆ๐ด๐ฑ๐ฐ๐ฏ๐ด๐ช๐ฃ๐ญ๐ฆ ๐๐ท๐ข๐ญ๐ถ๐ข๐ต๐ช๐ฐ๐ฏ ๐ฐ๐ง ๐๐ ๐ง๐ฐ๐ณ ๐๐ฆ๐ฏ๐ต๐ข๐ญ ๐๐ฆ๐ข๐ญ๐ต๐ฉ, written by an interdisciplinary team spanning AI [...]
1
3
3
reposted by
Dirk Hovy
Debora Nozza
4 months ago
Honored to give my first keynote at
#IRCDL2026
on February 19th. Iโll talk about how LLMs have shifted from productivity tools to everyday sources of info & personal guidance and what that means for risk, trust, bias, and alignment.
ircdl2026.unimore.it
0
14
2
reposted by
Dirk Hovy
Cambridge University Press Political Science & IR
4 months ago
#OpenAccess from
@politicsgenderj.bsky.social
- Male Agency? Analyzing Fatherhood Roles in Swedish Parliamentary Documents, 1993โ2021 - https://cup.org/40el36q - Lena Wรคngnerud, Elin Naurin,
@dirkhovy.bsky.social
#OpenAccess
Lorenzo Lupo & Oscar Magnusson
#FirstView
0
6
2
reposted by
Dirk Hovy
MilaNLP Lab
5 months ago
#MemoryModay
#NLProc
@gattanasio.cc
et al. study asks 'Is It Worth the (Environmental) Cost?' analyzing continuous training for language models. Balances benefits, environmental impacts, for responsible use.
#AI
#Sustainability
arxiv.org/pdf/2210.07365
loading . . .
https://arxiv.org/pdf/2210.07365
0
7
4
reposted by
Dirk Hovy
รtienne Ollion
5 months ago
What are the main issues discussed in a set of documents? Weโve just released a step-by-step BERTopic tutorial. We also launch a new page, gathering various NLP tutorials for social scientists. ๐
www.css.cnrs.fr/tutorials-an...
loading . . .
Tutorials and Resources โ CSS @ IP-Paris
Site web de l'axe sciences sociales computationnelles du CREST-CNRS. Cours et tutoriels pour l'analyse des donnรฉes numรฉriques en sciences sociales.
https://www.css.cnrs.fr/tutorials-and-resources/
3
48
25
reposted by
Dirk Hovy
David Mimno
5 months ago
Citation is the foundation of academic promotion. Itโs noisy, sure, but its integrity is worth fighting for. Hallucinated citations should be a desk reject.
add a skeleton here at some point
1
27
5
reposted by
Dirk Hovy
David Jurgens
5 months ago
The second new class I'm teaching is a very experimental graduate level seminar in CSE: "Building Small Language Models". I taught the grad level NLP class last semester (so fun!) but students wanted moreโwhich of these new ideas work, and which work for SLMs?
jurgens.people.si.umich.edu/CSE598-004/
loading . . .
CSE 598-004 - Building Small Language Models
http://jurgens.people.si.umich.edu/CSE598-004/
2
32
10
reposted by
Dirk Hovy
MilaNLP Lab
5 months ago
๐ MilaNLP 2025 Wrapped ๐ Lots of learning, building , sharing, and growing together ๐ฑ
#NLProc
0
10
4
reposted by
Dirk Hovy
MilaNLP Lab
5 months ago
โณ Deadline approaching! Weโre hiring 2 fully funded postdocs in
#NLP
. Join the MilaNLP team and contribute to our upcoming research projects (SALMON & TOLD) ๐ Details + how to apply:
milanlproc.github.io/open_positio...
โฐ Deadline: Jan 31, 2026
0
11
11
๐จ(Software) Update: In my PhD, I had a side project to fix an annoying problem: when you ask 5 people to label the same thing, you often get different answers. But in ML (and lots of other analyses), you still need a single aggregated answer. Using the majority vote is easyโbut often wrong. 1/N
loading . . .
GitHub - dirkhovy/MACE: Multi-Annotator Competence Estimation tool
Multi-Annotator Competence Estimation tool. Contribute to dirkhovy/MACE development by creating an account on GitHub.
https://github.com/dirkhovy/MACE
5 months ago
6
75
14
New year, new job? If that is your current mantra, check the open postdoc positions with Debora Nozza and me at our lab. Deadline is January 31st.
milanlproc.github.io/open_positio...
loading . . .
Postdoctoral Researcher โ NLP (2 positions) | MilaNLP Lab @ Bocconi University
Two Postdoctoral Researcher positions โ Deadline January 31st, 2026
https://milanlproc.github.io/open_positions/postdoc_tef/
5 months ago
0
11
11
reposted by
Dirk Hovy
MilaNLP Lab
6 months ago
๐ Weโre opening 2 fully funded postdoc positions in
#NLP
! Join the MilaNLP team and contribute to our upcoming research projects. ๐ More details:
milanlproc.github.io/open_positio...
โฐ Deadline: Jan 31, 2026
0
19
15
Load more
feeds!
log in
