Chieh-Yang Huang
109 posts
Chieh-Yang Huang
@appleternity
PhD candidate at IST, Penn State University. Working on NLP, HCI, and crowdsourcing, especially writing support and language learning systems! 😎😎😎
State College, PA Beigetreten Şubat 2017
145 Folgt137 Follower
Chieh-Yang Huang retweetet
Truly honored and grateful to receive this inspiring #OutstandingPaperAward at #EMNLP2025! 🏆
Heartfelt thanks to dear @tanmit and Nick for such an enjoyable and wonderful collaboration💗. Huge thanks to our amazing general chair @dirk_hovy, program chairs @VioletNPeng, Carolyn Rose, @c_christodoulop, @Tanmoy_Chak, and all SACs, ACs, organizers & volunteers💗. Also deeply thankful to everyone I met and learned from at #EMNLP — you all made #EMNLP2025 in beautiful Suzhou unforgettable!!🌸
@nyuniversity @UW @nyushanghai @uwischool @nyutandon @uwcse
Hua Shen✨@huashen218
🧐Are values in LLMs aligned with humans? 1️⃣ And if they are — do LLMs stay honest to those values, or sometimes say one thing but act another? 2️⃣ ✨ We explore these questions in two papers presented at #EMNLP2025: 1️⃣ ValueCompass: hua-shen.org/assets/files/a… (WiNLP Workshop) 2️⃣ Mind the Value–Action Gap: arxiv.org/pdf/2501.15463 (Main Track) 🔍 Dataset & Code: github.com/huashen218/val… 🌱 I’m also #Hiring multiple PhD students for Fall 2026 @ NYU Courant Computer Science! If you’re passionate about #Human_AI_Alignment, #Value_Alignment, or broad #AI + #Human (society) research, let’s connect at EMNLP2025, NeurIPS2025, or over Zoom! 🎓 NYU CS PhD Apply (NYU Shanghai Track): cs.nyu.edu/dynamic/phd/ad… 💜 This year I’m also co-organizing the #EMNLP2025 WiNLP Workshop and supporting the amazing #Tutorial on Spoken Conversational Agents with LLMs (a short 15min talk)! Come say hi 👋 — I’d love to chat and connect with old and new friends at #EMNLP2025! 🔗 WiNLP Workshop: winlp-workshop.github.io 🔗Tutorial on Spoken Conversational Agents: aclanthology.org/2025.emnlp-tut… 💗Huge thanks to my wonderful paper collaborators — @tanmit,@YunHuang_HCI,@tknearem,@reshmigh,Nicholas Clark,Yu-Ju Yang — and my inspiring workshop/tutorial collaborators @huckiyang, Andreas Stolcke,@TYSSSantosh2,@therealthapa,@MeryemMhamdi1,Chen Zhang, Peerat Limkonchotiwat, Wiem Ben Rim.... 🤗Truly grateful and enjoyable to work with you all! 💫 #HumanAIAlignment #PhDOpening #NYU #NYUShanghai #ValueAlignment #HAI
English
Chieh-Yang Huang retweetet
✨Upcoming Talk✨I’ll be speaking at the UW Data Science Seminar tomorrow (April 9) from 4:30pm - 5:20pm (PST) to share ideas about 👫<>🤖“Towards Bidirectional Human-AI Alignment: Empowering Human Interaction in Building Responsible AI across the Lifecycle”.
Welcome to hang out in person (UW ECE building 125) or join via Zoom! Feel free to check more info: escience.washington.edu/events/uw-data…. If you're interested or around, would love to chat more☕️😉!
English
Chieh-Yang Huang retweetet
🚀 Are you passionate about #Alignment Research? Exciting news! Join us at the ICLR 2025 Workshop on 👫<>🤖Bidirectional Human-AI Alignment (April 27 or 28, Singapore). We're inviting researchers in AI, HCI, NLP, Speech, Vision, Social Science, and beyond domains to submit their work on alignment-related topics!
📄 Paper Formats: 2-page (tiny), 4-page (short), & 9-page (long)
🗓️ Key Dates: Tentative Submission Deadline: Feb 3, 2025 (AoE). Workshop Day: April 27 or 28, 2025
💠Topics:
🔸Position papers and roadmaps for alignment research
🔸Specifying human values, cognition, and societal norms
🔸RLHF and advanced algorithms, interactive/customizable alignment methods
🔸AI safety, interpretability, scalable oversight, and steerability
🔸Red teaming, benchmarks, metrics, and human evaluation for alignment
🔸Dynamic human-AI co-evolvement and societal impact
🌟Speakers: @_beenkim, @bradamyers, @fraukolos, @HungyiLee2, @RichardMCNgo, @danbohus, @Pavel_Izmailov
👫Organizers: @huashen218, @ziqiao_ma, @reshmigh, @tknearem, @lxieyang, @tongshuangwu, @andresmh, @Diyi_Yang, @ABosselut, @furongh, @tanmit, @sled_ai, Marti A. Hearst, @dawnsongtweets, @yangli169
✍️ Interested in joining our Program Committee to help review? Apply here! forms.gle/MapXyCZhbcFr9F…
Join us in advancing the Human-AI Alignment research together🌟!
#ICLR2025 #AIAlignment #HCI #NLP #Speech #ComputerVision
English
Chieh-Yang Huang retweetet
Led by @edhsujourney, we're happy to launch the 2nd SciCap Challenge! It will be held at @IJCAIconf #IJCAI2024 with 2 tracks: Long Caption Track & Short Caption Track.
The winners will be decided by *human evaluation* :)
Submit before June 15, 2024: SciCap.AI
English
Chieh-Yang Huang retweetet
At #CHI2024, we try to do justice to #crowdsourcing by answering this question:
How does GPT-4's labeling ability compare to that of a realistic, well-executed MTurk *pipeline*?
Led by @StevenHe918, we publish our love letter to crowdsourcing: arxiv.org/abs/2402.16795 #LLM 1/🧵
English
Chieh-Yang Huang retweetet
Can #GPT4 ever write fiction that matches the quality of @NewYorker fiction? Bothered by claims about AI surpassing human creativity🤔?
Good news🥁:AI is still 3-10X worse at creativity based on our rubric "Torrance Tests for Creative Writing” #NLProc #HCI
arxiv.org/pdf/2309.14556…
Manhattan, NY 🇺🇸 English
Chieh-Yang Huang retweetet
🤔How can we align AI systems/LLMs 🤖 to better represent diverse human values and perspectives?💡🌍
We outline a roadmap to pluralistic alignment with concrete definitions for how AI systems and benchmarks can be pluralistic!
arxiv.org/abs/2402.05070
First, models can be…
English
Chieh-Yang Huang retweetet
Deadline is coming! Submit your cool work and hot takes before 13 February! #in2writing #chi2024
Kenneth Huang #HCOMP2026 Sep27-30@DC@windx0303
The amazing #In2Writing workshop will be again at #CHI2024! This year we have an very intriguing theme: 🔥Dark Sides: Envisioning, Understanding, and Preventing Harmful Effects of Writing Assistants🔥 Take a look at our website! in2writing.glitch.me
English
Chieh-Yang Huang retweetet
Exciting to see convergent evidence from a bunch of papers in the last couple of months (our ICLL paper + this one + arxiv.org/pdf/2312.04927…) that an important / distinctive inductive bias in Transformers is how easily they learn to match n-grams / use this for copying & ICL
Ekin Akyürek@akyurekekin
We recently showed n-gram heads improves ICLL and LM performance in twitter.com/akyurekekin/st… Can n-gram hybrids from our paper solves copying issue in SSMs? my initial experiments suggests so: char. acc. on |D|=10k, |V|=30, L=300) (cc: @EranMalach @brandfonbrener)
English
Chieh-Yang Huang retweetet
Our paper “Supporting Sensemaking of Large Language Model Outputs at Scale” was accepted to #CHI24!
This paper is about looking at LLM outputs at the “mesoscale”: ~10-100 outputs at once.
Why might you want to look at a bunch of LLM outputs at once? 🧵
arxiv.org/abs/2401.13726
English
Chieh-Yang Huang retweetet
I will be recruiting 2-3 PhD students to start in 2024 Fall at Gatech CSE!
If you are interested in working with me on AI for social impact, ML, optimization, etc., please consider applying by Dec 15th and list my name in the application!
More info: guaguakai.com/team
English
Chieh-Yang Huang retweetet
LLMs are exposed to so many different people’s writings and opinions during training, but how much diversity can we actually extract back given subjective topics? 🧐
Use Criteria-Based Diversity Prompting to extract diverse perspectives! 😉
Paper 📄: arxiv.org/pdf/2311.09799…
English
Chieh-Yang Huang retweetet
How can Copilot improve from human feedback?
💡Idea: learn a model of programmer actions, given a suggestion, will they accept it? If not, don't show the suggestion!
Result: we can hide 1/4 of shown suggestions where 95% of them would be rejected!
🔗arxiv.org/abs/2306.04930
English
Chieh-Yang Huang retweetet
📢How can humans better distinguish LLM-written text from human-written ones?👭Collaboration is What We Need!👬Our human studies w/ expert & non-expert improve detection w/ collab by >6.3%. @adaku_uchendu @jooyounglee7460 will present at #HCOMP today🤗!🧵👇arxiv.org/pdf/2304.01002…
English
Chieh-Yang Huang retweetet
Do you think there's more to conversational AI than cutting and pasting text into ChatGPT? Apply for a Summer '24 research internship at Microsoft Semantic Machines! jobs.careers.microsoft.com/global/en/job/…
English
Come play ConvXAI with Hua today if you are #CSCW2023 <(￣︶￣)>
Hua Shen✨@huashen218
I'll present the Live Demo👩💻 of ConvXAI🤖 at #CSCW2023 today (Monday Oct/16) during 6:30- 8:30pm session. If you wanna play with ConvXAI or talk more about #human + #XAI using LLMs, I'd be very happy to chat more and love to see you there🤗! @windx0303 @tongshuangwu @appleternity
English
Chieh-Yang Huang retweetet
🚨AI-assisted writing is a nebulous space with researchers and writers being both curious & apprehensive. How useful are current SOTA LLMs to writers?What are their needs & expectations?If this intrigues you, then buckle up🚨
Paper: arxiv.org/pdf/2309.12570… #NLProc #HCI #ChatGPT
Manhattan, NY 🇺🇸 English
Chieh-Yang Huang retweetet
NLP research over the years:
1990s: specialized features for NER
2000s: non-parametric prior for unsupervised parsing
2010s: embeddings + a forward/backward, inside/outside RNN
Today: When you say “Super pretty please” to the LLM, performance goes up
English