🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited to attend the first Conference on Language Modeling 🦙❤️🤩 Very open to talk to anyone about faculty/postdoc/phd opportunities at KAIST, as well as about multilingual multicultural LLM research. Come join the multilingual special session on Wednesday morning, and find my students

I will give a talk at Naver lab (Europe) on Oct 17th, 5 PM (CEST) and 8 AM (PST). This talk is about "how to properly build a metric to evaluate AI-generated text?". I will dive into three main challenges in building a proper evaluation metric and present our proposed

🚀Next step : How to train the model for factor level alignment? Could we tune the model preferences at factor level?

📜Excited to share our comprehensive survey on cultural awareness in #LLMs! 🗺️ We reviewed 300+ papers across diverse modalities (language, vision-language, etc.) Siddhesh Pawar Junyeong Park @ NAACL 2025✈️ Jiho Jin Arnav Arora Junho Myung Inhwa Alice Oh #NLProc openreview.net/forum?id=3gg6G…

This work would not have been possible without my amazing co-authors: JuYoung Suk Seungone Kim Niklas Muennighoff Dongkwan Kim and Alice Oh ! 🙌A big thank you for your contributions and collaboration.

Interviews are the gold standard for evaluating humans; it's usually the final step in admissions & hiring. We introduce LLM-as-an-Interviewer to do the same to benchmark LLMs — a paradigm shift in evals I think. Led by Eunsu Kim @ACL2025 - I highly recommend admitting her for PhDs!

When people hire someone new, they often conduct interviews to understand their traits and strengths in detail. In our new preprint, we extend single-turn interaction-based "LLM-as-a-Judge" to multi-turn interactions with "LLM-as-an-Interviewer"! Check out Eunsu Kim @ACL2025 's post!

This AI Paper Introduces LLM-as-an-Interviewer: A Dynamic AI Framework for Comprehensive and Adaptive LLM Evaluation Researchers from KAIST, Stanford University, Carnegie Mellon University, and Contextual AI have introduced LLM-AS-AN-INTERVIEWER, a novel framework for evaluating

Check out our latest work on self-improving LLMs, where we try to see if LLMs can utilize their internal self consistency as a reward signal to bootstrap itself using RL. TL;DR: it can, to some extent, but then ends up reward hacking the self-consistency objective. We try to see

I’ll be presenting our LLM-as-an-Interviewer work at #ACL2025! 📅 When: July 30 (wed) 11:00-12:30 📍 Where: Hall 4/5 arxiv.org/abs/2412.10424 Feel free to stop by ! Looking forward to discussing (m)LLM evaluation and more!

🗣️ My undergrad mentee Sunwoo Kim is presenting his work at Generation Evaluation & Metrics Workshop (gem-benchmark.com/workshop) Please stop by and say hi 👋 📄 arxiv.org/abs/2506.21961 📅 15:15-15:30, Jul 31 📍 Hall C #ACL2025NLP #ACL2025 ACL 2025