Reposted by Amanda BertschAri @ari-holtzman.bsky.social · 09/11/2025LLMs don't accumulate information over the course of a text the way you'd hope! I think this is why LLMs often feel 'fixated on the wrong thing' or 'overly literal'—they are usually responding using the most relevant single thing they remember, not the aggregate of what was said 061
Amanda Bertsch @abertsch.bsky.social · 07/11/2025Can LLMs accurately aggregate information over long, information-dense texts? Not yet… We introduce Oolong, a dataset of simple-to-verify information aggregation questions over long inputs. No model achieves >50% accuracy at 128K on Oolong! 35020
Reposted by Amanda BertschKyle Lo @ ICML2026 🇰🇷 @kylelo.bsky.social · 05/11/2025why intern at Ai2? 🐟interns own major parts of our model development, sometimes even leading whole projects 🐡we're committed to open science & actively help our interns publish their work reach out if u wanna build open language models together 🤝 links 👇 2278
Reposted by Amanda BertschSung Kim @sungkim.bsky.social · 05/11/2025DeltaNet Explained by Sonlin Yang A gentle and comprehensive introduction to the DeltaNet Part 1: sustcsonglin.github.io/blog/2024/de... Part 2: sustcsonglin.github.io/blog/2024/de... Part 3: sustcsonglin.github.io/blog/2024/de... 0152
Reposted by Amanda BertschNatasha Johnson @natashamarie330.bsky.social · 05/11/2025I’ll be presenting this work in **2 hours** at EMNLP’s Gather Session 3. Come by to chat about fanfiction, literary notions of similarity, long-context modeling, and consent-focused data collection! 071
Reposted by Amanda BertschNatasha Johnson @natashamarie330.bsky.social · 05/11/2025Digital humanities researchers often care about fine-grained similarity based on narrative elements like plot or tone, which don’t necessarily correlate with surface-level textual features. Can embedding models capture this? We study this in the context of fanfiction! 13913
Amanda Bertsch @abertsch.bsky.social · 12/09/2025. @gneubig.bsky.social and I are co-teaching a new class on LM inference this fall! We designed this class to give a broad view on the space, from more classical decoding algorithms to recent methods for LLMs, plus a wide range of efficiency-focused work. website: phontron.com/class/lminfe...phontron.com11-664/763 LM InferenceA class at Carnegie Mellon University on language model inference algorithms. 140
Reposted by Amanda BertschLindia Tjuatja @lindiatjuatja.bsky.social · 09/06/2025When it comes to text prediction, where does one LM outperform another? If you've ever worked on LM evals, you know this question is a lot more complex than it seems. In our new #acl2025 paper, we developed a method to find fine-grained differences between LMs: 🧵1/9 27020
Amanda Bertsch @abertsch.bsky.social · 30/04/2025super excited to see folks at #NAACL25 this week! I'll be presenting our work on long-context ICL Wednesday in the 2pm poster session in Hall 3-- would love to chat with folks there or at the rest of the conference about long context data, ICL, inference time methods, New Mexican food, etc :) 1111
Reposted by Amanda BertschAlicia DeVrio @uhleeeeeeeshuh.bsky.social · 06/03/2025How can we better think and talk about human-like qualities attributed to language technologies like LLMs? In our #CHI2025 paper, we taxonomize how text outputs from cases of user interactions with language technologies can contribute to anthropomorphism. arxiv.org/abs/2502.09870 1/n 24311
Reposted by Amanda BertschMax Müller-Eberstein @mxij.me · 23/12/20249.6 million seconds = 1 PhD 🔥 Finally analyzed my PhD time tracking data so you can plan your own research journey more effectively: mxij.me/x/phd-learning-dynamics For current students: I hope this helps put your journey into perspective. Wishing you all the best!mxij.meThe Learning Dynamics of a PhDThis is what a PhD looks like: 9.6 million seconds of research. 0367
Reposted by Amanda BertschSireesh Gururaja @siree.sh · 17/12/2024When I started on ARL project that funds my PhD, the thing we were supposed to build was a "MaterialsGPT". What is a MaterialsGPT? Where does that idea come from? I got to spend a lot of time thinking about that second question with @davidthewid.bsky.social and Lucy Suchman (!) working on this: 1207
Reposted by Amanda Bertsch🌶 David Gray Widder @davidthewid.bsky.social · 09/12/2024📢 NEW Paper! @siree.sh, Lucy Suchman, and I examine a corpus of 7,000 US Military grant solicitations to ask what the world’s largest military wants with to do with AI, by looking at what it seeks to fund. #STS 📄: arxiv.org/pdf/2411.17840 We find… 46632
Reposted by Amanda BertschVicki @vickiboykis.com · 20/11/2024when you try to convert your text into smaller pieces but all it gives you is Elvish, that’s a tolkienizer 341007104
Reposted by Amanda BertschCharles Sutton @randomlywalking.bsky.social · 21/11/2024That’s right. You might think that all successful CS academics are good at running. But that’s only because the ones who weren’t, have been eaten by bears. 5804
Reposted by Amanda BertschLindia Tjuatja @lindiatjuatja.bsky.social · 20/11/2024💬 Have you or a loved one compared LM probabilities to human linguistic acceptability judgments? You may be overcompensating for the effect of frequency and length! 🌟 In our new paper, we rethink how we should be controlling for these factors 🧵: 18519
Reposted by Amanda BertschSireesh Gururaja @siree.sh · 12/11/2024I'm keeping track of people at the CMU Language Technologies Institute here: go.bsky.app/NhTwCVb. Follow along! 073
Reposted by Amanda BertschShaily @shaily99.bsky.social · 14/11/2024Today is the day!! Find me at 2 PM in the Jasmine Hall (the one on the floor near food). 063
Reposted by Amanda BertschLindia Tjuatja @lindiatjuatja.bsky.social · 08/11/2024(Hehe first bsky post!) I'll be at #EMNLP2024 💃🌴! Happy to chat about (among other things): ✨linguistically+cognitively motivated evaluation ✨NLP for low-resource+endangered languages ✨figuring out what features of language data LMs are *actually* learning I'll be presenting two posters 🧵: 1296
Reposted by Amanda BertschNaomi Saphra @nsaphra.bsky.social · 08/11/2024Taking a stand that we aren’t doing the #nlproc tag here. It’s #nlp. We used #nlproc because a decade ago the #nlp tag was full of sleazy scammers selling guides for hypnotizing women into sleeping with you. But guess what? We won. All the sleazy scammers are doing natural language processing now. 1118129
Reposted by Amanda BertschClara Na @clarana.bsky.social · 05/11/2024Building/customizing your own LLM? You'll want to curate training data for it, but how do you know what makes the data good? You can try out recipes👩🍳 iterate on ✨vibes✨ but we can't actually test all possible combos of tweaks,,, right?? 🙅♂️WRONG! arxiv.org/abs/2410.15661 (1/n) 🧵 1498
Reposted by Amanda BertschClara Na @clarana.bsky.social · 12/10/2023bsky.app/profile/sire... it was so interesting to see participants' perceptions of "paradigm shifts" paralleled across eras and cycles of NLP, and at the same time nothing until recent years had reached quite the level of *47%* of ACL papers in 2021 citing BERT 021
Reposted by Amanda BertschSireesh Gururaja @siree.sh · 12/10/2023We all know that “recently large language models have”, “large language models are”, and “large language models can.” But *why* LLMs? How did we get here? (where is “here”?) What forces are shaping NLP, and how recent are they, actually? To appear at EMNLP 2023: arxiv.org/abs/2310.07715 2174
Reposted by Amanda BertschGretchen McCulloch @gretchenmcculloch.com · 11/10/2023Talking to the youths in 2023: did you know that "podcast" comes from a pun on "broadcast" plus the Apple iPod, a precursor to the iPhone that only played music Talking to the youths in 2043: did you know that "tweet" comes from a pun on Twitter, a precursor to various shortform social media 1226047