Huda Khayrallah
@HudaKhay
Followers
1K
Following
5K
Media
24
Statuses
842
Machine Translation/#NLProc/ML Researcher at Microsoft. Past: @UCBerkeley CS ugrad; @LiltHQ research intern; @jhuCLSP/@jhuCompSci PhD
rarely on here; email me
Joined July 2012
Lots of work on cross-lingual alignment encourages multilingual LLMs to generalize knowledge across languages. But this push for uniformity creates a tension: what happens to knowledge that should remain local? We look into this trade-off of transfer and cultural erasure:🧵
3
19
61
🗺️ Are we making our #LLMs multilingual, or anglocentric? Much work brings languages closer to English, but that comes at the cost of crucial #cultural nuance. @h__j___han tackles this trade-off with surgical steering, adapting LLMs to cultural contexts at inference time.
Lots of work on cross-lingual alignment encourages multilingual LLMs to generalize knowledge across languages. But this push for uniformity creates a tension: what happens to knowledge that should remain local? We look into this trade-off of transfer and cultural erasure:🧵
0
12
51
Excited to share that X-ALMA got accepted at #ICLR2025! See you in Singapore!
Multilingual models are usually heavily skewed in favor of high-resource languages. We change this with X-ALMA: an LLM-based translator committed to ensuring top-tier performance across 50 diverse languages, regardless of their resource levels! Paper: https://t.co/O4M5LDGdAB
0
2
7
Excited to share that our VocADT paper got accepted at #ICLR2025✨! I am looking forward to participating in @iclr_conf in Singapore 🇸🇬.
🧐Which languages benefit the most from vocabulary adaptation? We introduce VocADT, a new vocabulary adaptation method using a vocabulary adapter, and explore the impact of various adaptation strategies on languages with diverse scripts and fragmentation to answer this question.
2
9
30
Congratulations @h__j___han 🥳 it was great to work with you!
Excited to share that our VocADT paper got accepted at #ICLR2025✨! I am looking forward to participating in @iclr_conf in Singapore 🇸🇬.
0
3
3
Large Model Inference Efficiency can be tackled from many angles, mixture of experts, efficient self-attention, quantisation, distillation, hardware acceleration.. But what if we could completely avoid redundant computational processing over context window? In our NeurIPS'24
1
11
25
EAMT best thesis award - closes on January 31st. Completed an MT-related PhD in 2024? In Europe, Africa or Middle East. Then why not submit your thesis.
0
4
5
Incredibly proud of Dr Eleftheria Briakou for receiving the first ever Best Thesis Award from the Association for Machine Translation in the Americas!
I’m super thrilled to have won the AMTA Best Thesis Award!! A huge thanks to the AMTA organizers for this recognition ☺️ See you all in Chicago https://t.co/k9nJBl1AcI
3
6
43
🎉🎉🎉🎉🎉🎉
I’m super thrilled to have won the AMTA Best Thesis Award!! A huge thanks to the AMTA organizers for this recognition ☺️ See you all in Chicago https://t.co/k9nJBl1AcI
1
0
6
I’m super thrilled to have won the AMTA Best Thesis Award!! A huge thanks to the AMTA organizers for this recognition ☺️ See you all in Chicago https://t.co/k9nJBl1AcI
10
9
96
On behalf of the AMTA Board of Directors, I am pleased to announce the winner of the first-ever AMTA Best Thesis Award: Dr. Eleftheria Briakou (@ebriakou) for her thesis “Detecting Fine-Grained Semantic Divergences to Improve Translation Understanding Across Languages”. [1/n]
I’m super thrilled to have won the AMTA Best Thesis Award!! A huge thanks to the AMTA organizers for this recognition ☺️ See you all in Chicago https://t.co/k9nJBl1AcI
1
7
17
I'm bummed that family obligations prevented me from presenting this epic paper. This work represented a long journey for me. I first began working on the language of Diplomacy in 2015, and I struggled for years to get funding to build a bot that could play it ...
1⃣Meta’s Cicero by Bakhtin et al. was the talk of town when it was released in November 2022. Even main journals published that Cicero had achieved human-level Diplomacy in strategy and negotiation. Well, had it!? Our paper had this answer: https://t.co/03hjbKi20B
4
10
70
My mom wants to come out of retirement. She was a software validation engineer working on human machine interfaces. She (and I) have no idea where to look. She just wants to spend time testing the things that people build. Does anyone know where she could look??
1
2
7
✨XLAVS-R will be presented during today’s (August 13th) #ACL2024 poster session 4, starting at 10:30 AM. Looking forward to talking with people interested in our work!
🗣️XLAVS-R is accepted at #ACL2024 main! 🚀🚀 We present XLAVS-R, a cross-lingual audio-visual model for noise-robust speech perception in over 100 languages. Very happy to present our work done during my @AIatMeta internship with @ChanghanWang. https://t.co/rBta9M1t4P
0
5
26
🎉🎉🎉🎉🎉🎉
Congratulations to Xuan Zhang (advised by @kevinduh) on successfully defending her PhD thesis “Hyperparameter Optimization for Neural Machine Translation Systems”. https://t.co/LVBqBbT8CV
0
0
1
Great work Albert! Check out the paper at https://t.co/UvloKkYs2e .
aclanthology.org
Albert Sun, Varun Nair, Elliot Schumacher, Anitha Kannan. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolog...
Had a wonderful time presenting my paper from my internship last year with @CuraiHQ at #NAACL2024! Grateful for the opportunity to talk to the awesome and thoughtful people in the NLP community. @elliotschu @anithakan @nairvarun18
0
2
4
NAACL is this week and that means you should read our "history" paper! And if you're in Mexico City then say hi to Eve Fleisig, who is presenting it!
It's not the first time! A dream team of @enfleisig (human eval expert), Adam Lopez (remembers the Stat MT era), @kchonyc (helped end it), and me (pun in title) are here to teach you the history of scale crises and what lessons we can take from them. 🧵 https://t.co/pBUjPNRudf
1
4
41
Three postdocs were too tired to go to the party on the last night of SICB this year, so we decided to order pizza to the hotel and write a paper together instead. Out in @ICB_journal now! https://t.co/thRWfhwDHC
academic.oup.com
Synopsis. Science is becoming increasingly interdisciplinary; the widespread emergence of dedicated interdisciplinary journals, conferences, and graduate p
Today in @ICB_journal - @armanafzadeh, Janneke Schwaner, and I co-led a brief article on Strategies for Organizing Interdisciplinary Events. @SICB_ @SICB_DCB_DVM If you are interested in hosting an interdisciplinary event, we hope it is helpful: https://t.co/dwHG8pfMaX
2
8
46
🚨 Excited to share our new work on **confidence calibration** in LLMs! LLMs are often badly calibrated & overconfident, explicitly (eg. "I'm 100% sure") and implicitly, eg. giving details/authoritative tone. We address both w/ a pragmatic speaker-listener multi-agent method 🧵
3
42
145
Deadline is 6/6 for the AMTA thesis award Apply if you finished a PhD in MT in the Americas in the last year! https://t.co/oEgD1Sj4Xb questions? reach out to mtresearchers@amtaweb.org (Rebecca Knowles and Akiko Eriguchi).
amtaweb.org
Final Call for AMTA Best Thesis Award Submissions To be presented at AMTA 2024, a three-day event under the auspices of the Association for Machine Translation in the Americas Monday, 30 Sept 2024...
🏆 Thrilled to share the launch of the AMTA Best Thesis Award, which aims to highlight the achievements of a recent PhD graduate at an institution in the Americas whose thesis has focused on topics related to machine translation. [1/2]
0
0
1