📢 It's time to submit your Human-Centered🧑‍🤝‍🧑 #NLP papers to Workshop on Human-Centered Large Language Modeling

🙌 Co-located with ACL 2024 2024

Details in thread 👇

The question below is pretty easy for humans. Why can't GPT-4 get it right? In our new preprint we introduce 'time series reasoning' and show that modern language models are surprisingly bad at interpreting these critical data. arxiv.org/abs/2404.11757

Thanks AK for tweeting our work!

🤝Co-LLM trains a language model to collaboratively decode with other LMs. It decides whether to invoke the other assistant LM for each token. By optimally combining the expertise from each LM, co-llm generation can be better than using…

Helping people practice key skills in situations that are/feel realistic is one of the coolest, most appropriate applications of LMs, IMO. Check out our new work (captained by the intrepid Inna Lin) on helping people communicate effectively in challenging interpersonal convos!

Can LLMs like #ChatGPT help us navigate challenging communication situations?

📢 Introducing ✨IMBUE✨, an LLM-based training system that helps people improve interpersonal effectiveness skills🧠 and manage negative emotions 💖

Happy to share In-Context Pretraining 🖇️ is accepted as an #ICLR2024 spotlight. We study how to pretrain LLMs with improved context understanding ability

paper📄: arxiv.org/pdf/2310.10638…
code: github.com/swj0419/in-con…

Did you know that depending on the format used in few-shot prompting, you may get accuracies ranging 4%-88% for a given task w/LLaMA-2-70B 5-shot? or 47%-85% w/GPT3.5?🤯

We explore this variance in FormatSpread, or: How I learned to start worrying about prompt formatting.

1/n

People are increasingly using LLMs like #ChatGPT for #mentalhealth support. But do we truly understand their capabilities and limitations❓

Introducing 🌟BOLT🌟, a computational framework to assess the behavior of LLMs🤖 when employed as therapists💬

arxiv.org/abs/2401.00820 🧵

Can AI help improve the crisis in well-being? It's clear (to me, at least) that AI will not substitute humans, but it could enhance the abilities of both trained and untrained counselors. A cool paper by Ashish Sharma examines a tool to increase empathy.arxiv.org/pdf/2203.15144…