Find my students and collaborators at COLM this week!

Tuesday morning: @juand-r.bsky.social and @ramyanamuduri.bsky.social 's papers (find them if you missed it!)

Wednesday pm: @manyawadhwa.bsky.social 's EvalAgent

Thursday am: @anirudhkhatry.bsky.social 's CRUST-Bench oral spotlight + poster

Before his post-training work, Prasann did a great project on representing LM outputs with lattices, which remains one of my favorite algorithms-oriented papers from my group in the last few years, with a lot of potential for interesting follow-up work!

He then advanced our understanding of online DPO methods: how can we combine the strengths of reward models and DPO? (also at COLM 2024)

...established a critical weakness of RLHF with open reward models: spurious correlation with length (COLM 2024)

Huge congrats to @prasannsinghal.bsky.social for being one of the 8 CRA Outstanding Undergraduate Researcher Award winners! It has been an absolute privilege to work with Prasann during his time at UT. (And he's applying for PhD programs this year...hint hint...)

Prasann's work 🧵

I'll be at #NeurIPS2024 w/

- @fcyin.bsky.social's LoFiT: using interp to improve fine-tuning (Weds pm poster & MINT spotlight talk Sun)
- @thomlake.bsky.social's analysis of Overton pluralism (Pluralistic alignment Sat)

Please reach out to me to chat about interp, factuality, reasoning, &c!

when a famous person just got here and you temporarily have more followers than they do

I won't be at EMNLP, but come and see:
🔍 Detecting factual errors from LLMs (Liyan Tang)
🛠️ Detect, critique, & refine pipeline (Manya Wadhwa and Lucy Zhao)
🏭 Synthetic data generation (Abhishek Divekar)
📄 Fact-checking (Aniruddh Sriram) at FEVER

t.co/fQbl0G7m23

(1st real post in the bluer skies!)