Chau Minh Pham
@chautmpham
Followers
343
Following
2K
Statuses
110
PhD student @umdcs @ClipUMD | Previously @manningcics @MSFTResearch | Long-form Generation & Long-context Reasoning
Amherst, MA
Joined June 2015
Long-form text generation with multiple stylistic and semantic constraints remains largely unexplored. We present Suri 🦙: a dataset of 20K long-form texts & LLM-generated, backtranslated instructions with complex constraints. 📎
3
26
95
RT @lasha_nlp: We are launching HALoGEN💡, a way to systematically study *when* and *why* LLMs still hallucinate. New work w/ @shrusti_ghel…
0
34
0
RT @_akpiper: 1/ 🌍📚 Introducing Mini Worldlit: A new dataset of 1,192 curated works of contemporary fiction spanning 13 countries, 9 langua…
0
20
0
RT @jennajrussell: People often claim they know when ChatGPT wrote something, but are they as accurate as they think? Turns out that while…
0
148
0
RT @vishakh_pk: If you work on writing with LLMs, consider submitting to the In2Writing workshop at #NAACL2025 that alternates between *CL…
0
8
0
RT @siwu_nlp: Happy New Year everyone! I have a new paper on literary machine translation that's now on arXiv. Please feel free to give any…
0
13
0
RT @niloofar_mire: I've been thinking about Privacy & LLMs work for 2025 - here are 5 research directions and some key papers on privacy/me…
0
55
0
RT @ajscarlatos: Hey folks! Check out our latest paper published at EMNLP this year: "DiVERT: Distractor Generation with Variational Errors…
0
4
0
RT @MSheshera: Okay friends, do you use Google Scholar Alerts to keep up with new papers but find the alert emails too overwhelming? If yes…
0
2
0
RT @marafinkels: LLMs are typically evaluated w/ automatic metrics on standard test sets, but metrics + test sets are developed independent…
0
9
0
RT @mat_jacob1002: It's time to revisit common assumptions in IR! Embeddings have improved drastically, but mainstream IR evals have stagna…
0
43
0
RT @aminkarbasi: Can you select just 1% of the data for instruction tuning and still outperform models trained on the full dataset? 🧐 https…
0
23
0
RT @katie_kang_: LLMs excel at fitting finetuning data, but are they learning to reason or just parroting🦜? We found a way to probe a mode…
0
118
0
RT @clefourrier: For nuanced evaluations of complex generations, people now rely on LLM as judges... but which LLM should you use? Try the…
0
23
0
RT @maria_antoniak: I'm recruiting 1-2 PhD students to work with me at the University of Colorado Boulder! Looking for creative students wi…
0
225
0
I learned a lot about open-ended text evaluation while presenting Suri at #EMNLP2024 last week! Thanks to everyone who stopped by and left insightful comments/questions 🤩
I'll be presenting Suri 🦙 at #EMNLP2024 on Thursday (10:30am) and #wnu2024 on Friday! Please reach out if you want to talk about: 1️⃣ Long-form text generation/evaluation 2️⃣ Synthetic data/Instruction tuning or anything else! Looking forward to meeting old and new friends!
0
3
65
RT @yufei_t: 🤔Could LLMs one day win the Nobel Prize 🏆in literature? 🚀 Thrilled to share our latest paper at #EMNLP2024: "Are Large Languag…
0
20
0
RT @cmalaviya11: Excited to share ✨ Contextualized Evaluations ✨! Benchmarks like Chatbot Arena contain underspecified queries, which can…
0
28
0
RT @yixiao_song: Are you at EMNLP '24, and looking for an accurate metric for factuality evaluation? ✨ Check out our poster presentation o…
0
12
0