Isabel Cachola
@isabelcachola
NLP Researcher • PhD Student @jhuclsp • Texas Ex • Powerlifter • Previously @allen_ai • she/her/hers
🚨 I am on the faculty job market this year 🚨 I will be presenting at #NeurIPS2024 and am happy to chat in-person or digitally! I work on developing AI agents that can collaborate and communicate robustly with us and each other. My work covers 3 key problems👇 1⃣ Multi-agent +…
Congrats Kuleen! A very well deserved award 🥳
I am pleased to announce that I am a 2025 NSF GRFP award recipient for AI!!!! It has been the roughest PhD cycle for me and this is a small amount of hope and confidence boost to this dire year. I cannot thank enough all my mentors and people who trusted me throughout the years
If someone asked me why do research with Mark, this is an answer🔥 Swords are essential items to defend thesis. We need to be well-equipped.
New PhD tradition at @JHUCompSci @jhuclsp ! 🎓 We now knight our graduating PhD students and present them with a sword. ⚔️🤺 Congratulations @pocaguirre
New PhD tradition at @JHUCompSci @jhuclsp ! 🎓 We now knight our graduating PhD students and present them with a sword. ⚔️🤺 Congratulations @pocaguirre
Congratulations to Carlos Aguirre @pocaguirre on successfully defending his PhD thesis: Improving the Fairness in Language Models for Decision-Making! Next stop? @amazon pocaguirre.com
PhDone! 🎉 Thanks to everyone who was there along the way, family, friends, colleagues and advisors! Yes, I am a doctor now. Yes, I got a sword now (thanks friends!) Yes, we got @mdredze to knight me. What a nice finishing touch for this era!
🚨😱Obligatory job market announcement post‼️🤯 I'm searching for faculty positions/postdocs in multimodal/multilingual NLP and generative AI! I'll be at #NeurIPS2024 presenting our work on meta-evaluation for text-to-image faithfulness! Let's chat! Website in bio, papers in🧵
I am recruiting 1-2 PhD students this cycle @RutgersCS to work on Responsible NLP topics! I will be at #EMNLP2024 next week. If you will be attending the conference and are interested in working with me, please reach out!✨
Thrilled that we won an 🥂Outstanding Paper Award at #EMNLP2024! Super validating for using computational methods to investigate discourse processing via QUDs. Super proud of my students @YatingWu96 @ritikarmangla, amazing team @AlexGDimakis @gregd_nlp
LLMs can mimic human curiosity by generating open-ended inquisitive questions given some context, similar to how humans wonder when they read. But which ones are more important to be answered?🤔 We predict the salience of questions, substantially outperforming GPT-4.🌟 🧵1/5
I’m presenting my Microsoft internship work today at #EMNLP2024! I’ll be in Riverfront from 2-3:30. Come say hi and chat about structured document generation and evaluation! TLDR: We unify the generation and evaluation of templatic views of documents. aclanthology.org/2024.findings-…
Presenting two posters at #EMNLP2024 this week! Come say hi and chat about decompositional entailment and knowledge-constrained dialogue tree generation!
LLMs generations are not always easy to evaluate. Check out our new work: ReIFE, lead by @YixinLiu17 and @shi_kejian, a comprehensive study on how the choice of LLMs and different evaluation strategies can impact the evals. Details below👇
LLMs are often used to evaluate the instruction-following capabilities of other LLMs – but which LLM should we choose, and how should we use it? 🤔 We're excited to share "ReIFE: Re-evaluating Instruction-Following Evaluation"! Preprint: arxiv.org/abs/2410.07069 📊 Our study is…
🤖 LLMs are powerful, but their "one-size-fits-all" safety alignment limits flexibility. Safety standards vary across cultures and users—what’s safe in one context might not be in another. 🌍 We propose ✨Controllable Safety Alignment✨ for inference-time safety adaptation! 🧵👇
Considering a PhD in NLP/Speech? Need guidance with your application materials? 🤔 The Center for Language and Speech Processing @ JohnsHopkins is offering a student-run mentoring program for prospective applicants! 🙌 📝 Apply here: forms.gle/wfJfTmbcuDo58H… 📅 Deadline: Nov 17
As a @upennnlp PhD, my office mates and I brought a couch into our office. It didn't fit, was in the way, but we didn't care. We loved the (already old) couch. ~17 years on, some of my group got a tour to see the couch. It's mostly in one piece! A piece of #nlpproc history.
Introducing ✨Promptriever ✨ the first retriever that can be prompted like an LM with free-form prompts! Our secret: query-level instruction training lets you keep the promptability of the base LM! 🚫 keyword-matching ✅ instruction search 📝 arxiv.org/abs/2409.11136
PhDone! Thank you so much to everyone who's been with me along the way 🎓🥳
Congratulations to @esalesk (esalesky.github.io) on successfully defending her PhD thesis, "Overcoming vocabulary challenges in natural language processing"! Elizabeth was advised by @mjpost and Philipp Koehn. She will join @Google this fall.
Arrived in Bangkok for #ACL2024. Excited to catch up with old and new friends! We, with collaborators, are presenting several papers on evaluation, long-context QA, semi-structured data, and contamination. 👇
|￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣￣| | Don't Push To Production On Friday | |＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿＿| \ (•◡•) / \ / —— | | |_ |_
📢 My lab at Yale is looking for a postdoc to work on LLMs/NLP for health. This is a unique collaboration with a health startup focusing on both cutting-edge AI research and real-world impact to tackle domain-specific challenges of LLMs. Pls help spread the word! 1/2 🧵
iMessage option to summarize long voice notes with AI