🏆 Thrilled to share that in my first time as a paper reviewer, I have been honored with the Best Reviewer Award for the Ethics in NLP track. Heartfelt thanks to the Area Chairs and EMNLP PC Chairs for this recognition. It is a fantastic learning experience! 🙏

✨ #EMNLP paper: Introducing a novel paradigm: On-Demand Information Extraction. We enable personalized info extraction for non-expert users beyond traditional task boundaries.

📜 Paper: arxiv.org/abs/2310.16040
🔗 Code & Dataset: github.com/yzjiao/On-Dema…

1/3

We all know that “recently large language models have”, “large language models are”, and “large language models can.” But why LLMs? How did we get here? (where is “here”?) What forces are shaping NLP, and how recent are they, actually?

To appear at EMNLP: arxiv.org/abs/2310.07715

Finally on the way to Singapore #EMNLP2023 🇸🇬 (❄️✈️❌ Our travel to emnlp is more adventurous than our research in legal #NLProc 🏂)

We are happy to announce that our paper 'Approximating Two-Layer Feedforward Networks for Efficient Transformers' got accepted to EMNLP Findings. With our improved MoE Transformers, we can match the performance of parameter-matched dense models.

Our team is happy to share SteerLM, a simpler alternative to RLHF which allows dynamic model controls during inference (humor, verbosity, etc.). To appear in Findings of EMNLP 2023. It is implemented in NeMo (open-source) and example model is on HF arxiv.org/abs/2310.05344

Our paper, YORC: Yoruba Reading Comprehension dataset was accepted and presented at #WiNLP co-located at #EMNLP in Singapore.
We presented a new reading comprehension dataset for Yorùbá language. We showed that cross-lingual transfer with AfroXLMR-base from an English dataset...

⏰In 1 hour @EMNLP posters! Presenting TreePrompt: next LM call is routed by result of previous calls using a decision tree. My first last-author paper, led by Jack Morris jack morris & Chandan Singh Chandan Singh, under the guidance of Sasha Rush Sasha Rush (ICLR) & Jianfeng Gao Jianfeng Gao

With Christian Federmann, we are presenting a poster on GEMBA-MQM, a SotA metric for MT system ranking, at EMNLP in a moment. Come and have a chat if we should use proprietary LLMs in evaluations of academic results.

I know it's hard to be working on Arabic NLP during such times, but I will stay positive and hopefully, they will see better times one day!
I will be presenting 2 papers in Singapore🇸🇬 next week:
7 Dec: talk at 9:30 - ArabicNLP conference
8 Dec: poster at 11:00 - EMNLP
#EMNLP2023

How should humans supervise AI🤖 if the gold answer is hard to directly verify?

My paper on Scalable Oversight has been accepted to EMNLP 2023:

'Labeling Programs with Non-Programmers Indirectly via Active Examples: A Case Study with Text-to-SQL'

🧵below

Just arrived at #NewOrleans for #NeurIPS2023 (a looong flight from emnlp)! Tomorrow I'll present Multimodal C4 at poster session 1 (#310, Tue 10:45am). Welcome everyone 😄

ChatGPT users know the dreaded “as of my knowledge cutoff…”

Can we keep LLMs up-to-date with continual fine-tuning?

Our EMNLP paper shows LMs may remember only a *tiny* fraction of the info they see in a data stream

It also shows meta-learning can improve knowledge uptake 🥹

That's a wrap for #genbench2023 !

But good news: We'll be back at EMNLP next year for #genbench2024 😍

Keep an eye on our websites for slides and recordings of our keynote speakers.

I am looking for a Ph.D. Level research intern specifically in “multilingual machine translation, tokenization, and speculative decoding” at NVIDIA AI Research in person at Taipei, or remote from Japan, Singapore, Korea - related NLP experience (i.e., ICLR, ICML, EMNLP, ACL) are…

It’s conference time! Come say hello at EMNLP to hear my hot takes on understanding LMs

Is your CS department hiring? Hey nice come talk to me!

Do you know few people at EMNLP? Not for long; come talk to me!

Here’s what I look like at a poster session when the lights go out

A recent thread by Jason Wei on Jacob Devlin's research style reminded me:

Everyone knows ColBERT uses Devlin et al's BERT.

But did you know about Zhou & Devlin (2021) at EMNLP, which extends ColBERT?

aclanthology.org/2021.emnlp-mai…

My 2023 summary:
🎓 PhD graduation
🏆 EMNLP Outstanding Paper
💯 Crossed 1000+ citations
🦙 Met a real Alpaca in Peru 🇵🇪 Tried luring it with 🥕 for a fun photo, but the Alpaca had own thought and DOES NOT follow my instruction at all 🤣

Embracing 2024 with fresh enthusiasm 🚀

did i really just start working on a project for the emnlp deadline?!

EMNLP 2023 に3本の論文が採択されました。また、Findings にも4本の論文が採択されました。 #EMNLP2023 #NLProc
nlp.ecei.tohoku.ac.jp/news-release/9…